Search

Background: Data-driven process analysis is an important area that relies on software support. Process variant analysis is a sort of analysis technique in which analysts compare executed process variants, a.k.a. process cohorts. This comparison can help to identify insights for improving processes. There are a few software supports to enable process cohort comparison based on the frequencies of process activities and performance metrics. These metrics are effective in cohort analysis, but they cannot support cohort comparison based on the probability of transitions among states, which is an important enabler for cohort analysis in healthcare.Results: This paper defines an approach to compare process cohorts using Markov models. The approach is formalized, and it is implemented as an open-source python library, named dfgcompare. This library can be used by other researchers to compare process cohorts. The implementation is also used to compare caregivers' behavior when prescribing drugs in the Stockholm Region. The result shows that the approach enables the comparison of process cohorts in practice.Conclusions: We conclude that dfgcompare supports identifying differences among process cohorts. [ABSTRACT FROM AUTHOR]

Background: In recent years, with the development of artificial intelligence, the use of deep learning technology for clinical information extraction has become a new trend. Clinical Event Detection (CED) as its subtask has attracted the attention from academia and industry. However, directly applying the advancements in deep learning to CED task often yields unsatisfactory results. The main reasons are due to the following two points: (1) A great number of obscure professional terms in the electronic medical record leads to poor recognition performance of model. (2) The scarcity of datasets required for the task leads to poor model robustness. Therefore, it is urgent to solve these two problems to improve model performance.Methods: This paper proposes a combining data augmentation and domain information with TENER Model for Clinical Event Detection.Results: We use two evaluation metrics to compare the overall performance of the proposed model with the existing model on the 2012 i2b2 challenge dataset. Experimental results demonstrate that our proposed model achieves the best F1-score of 80.26%, type accuracy of 93% and Span F1-score of 90.33%, and outperforms the state-of-the-art approaches.Conclusions: This paper proposes a multi-granularity information fusion encoder-decoder framework, which applies the TENER model to the CED task for the first time. It uses the pre-trained language model (BioBERT) to generate word-level features, solving the problem of a great number of obscure professional terms in the electronic medical record lead to poor recognition performance of model. In addition, this paper proposes a new data augmentation method for sequence labeling tasks, solving the problem of the scarcity of datasets required for the task leads to poor model robustness. [ABSTRACT FROM AUTHOR]

Background: MiRNA is a class of non-coding single-stranded RNA molecules with a length of approximately 22 nucleotides encoded by endogenous genes, which can regulate the expression of other genes. Therefore, it is very important to predict the associations between miRNA and disease. Predecessors developed a new prediction method of drug-disease association, and it achieved good results.Methods: In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. First, we integrate three associations into a heterogeneous network, such as the known miRNA-disease association, miRNA-miRNA similarities and disease-disease similarities, next we apply graph convolution network to learn the embedding of miRNA and disease. We use an attention mechanism to combine embedding from multiple convolution layers. Unobserved miRNA-disease associations are scored based on integrated embedding.Results: After fivefold cross-validations, the value of AUC is reached 0.9091, which is higher than other prediction methods and baseline methods.Conclusions: In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. LAGCN has achieved good performance in predicting miRNA-disease associations, and it is superior to other association prediction methods and baseline methods. [ABSTRACT FROM AUTHOR]

Background: Traditional approaches to identify missing mechanisms are usually based on the hypothesis test and confronted with both theoretical and practical challenges. It has been proved that the Bayesian network is powerful in integrating, analyzing and visualizing information, and some previous researches have verified the promising features of Bayesian network to deal with the aforementioned challenges in missing mechanism identification. Based on the above reasons, this paper explores the application of Bayesian network to the identification of missing mechanisms for the first time, and proposes a new method, the Bayesian network-based missing mechanism identification (BN-MMI) method, to identify missing mechanism in medical research.Methods: The procedure of BN-MMI method consists three easy-to-implement steps: estimating the missing data structure by the Bayesian network; assessing the credibility of the estimated missing data structure; and identifying the missing mechanism from the estimated missing data structure. The BN-MMI method is verified by simulation research and empirical research.Results: The simulation study verified the validity, consistency and robustness of BN-MMI method, and indicated its outperformance in contrast to the traditional logistic regression method. In addition, the empirical study illustrated the applicability of BN-MMI method in the real world by an example of medical record data.Conclusions: It was confirmed that the BN-MMI method itself, together with human knowledge and expertise, could identify the missing mechanisms according to the probabilistic dependence/independence relations among variables of interest. At the same time, our research shed light upon the potential application of BN-MMI method to a broader range of missing data issues in medical studies. [ABSTRACT FROM AUTHOR]

Background: The overcrowded patients, which cause the long waiting time in public hospitals, become significant problems that affect patient satisfaction toward the hospital. Particularly, the bottleneck usually happens at front-end departments (e.g., the triage and medical record department) as every patient is firstly required to visit these departments. The problem is mainly caused by ineffective resource management. In order to support decision making in the resource management at front-end departments, this paper proposes a framework using simulation and multi-objective optimization techniques considering both operating cost and patient satisfaction.Methods: To develop the framework, first, the timestamp of patient arrival time at each station was collected at the triage and medical record department of Thammasat University Hospital in Thailand. A patient satisfaction assessment method was used to convert the time spend into a satisfaction score. Then, the simulation model was built from the current situation of the hospital and was applied scenario analyses for the model improvement. The models were verified and validated. The weighted max-min for fuzzy multi-objective optimization was done by minimizing the operating cost and maximizing the patient satisfaction score. The operating costs and patient satisfaction scores from various scenarios were statistically compared. Finally, a decision-making guideline was proposed to support suitable resource management at the front-end departments of the hospital.Result: The three scenarios of the simulation model were built (i.e., a real situation, a one-stop service, and partially shared resources) and ensured to be verified and valid. The optimized results were compared and grouped into three situations which are (1) remain the same satisfaction score but decrease the cost (cost decreased by 2.8%) (2) remain the same satisfaction score but increase the cost (cost increased up to 80%) and (3) decrease the satisfaction score and decrease the cost (satisfaction decreased up to 82% and cost decreased up to 59%). According to the guideline, the situations 1 and 3 were recommended to use in the improvement and the situation 2 was rejected.Conclusion: This research demonstrates the resource management framework for the front-end department of the hospital. The experimental results imply that the framework can be used to support the decision making in resource management and used to reduce the risk of applying a non-improvement model in a real situation. [ABSTRACT FROM AUTHOR]

Background: The historical data of rare disease is very scarce in reality, so how to perform drug repositioning for the rare disease is a great challenge. Most existing methods of drug repositioning for the rare disease usually neglect father-son information, so it is extremely difficult to predict drugs for the rare disease.Method: In this paper, we focus on father-son information mining for the rare disease. We propose GRU-Cooperation-Attention-Network (GCAN) to predict drugs for the rare disease. We construct two heterogeneous networks for information enhancement, one network contains the father-nodes of the rare disease and the other network contains the son-nodes information. To bridge two heterogeneous networks, we set a mapping to connect them. What's more, we use the biased random walk mechanism to collect the information smoothly from two heterogeneous networks, and employ a cooperation attention mechanism to enhance repositioning ability of the network.Result: Comparing with traditional methods, GCAN makes full use of father-son information. The experimental results on real drug data from hospitals show that GCAN outperforms state-of-the-art machine learning methods for drug repositioning.Conclusion: The performance of GCAN for drug repositioning is mainly limited by the insufficient scale and poor quality of the data. In future research work, we will focus on how to utilize more data such as drug molecule information and protein molecule information for the drug repositioning of the rare disease. [ABSTRACT FROM AUTHOR]

Background: A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background.Methods: We propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities.Results: We evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%.Conclusions: We propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research. [ABSTRACT FROM AUTHOR]

Background: Standardized coding of plays an important role in radiology reports' secondary use such as data analytics, data-driven decision support, and personalized medicine. RadLex, a standard radiological lexicon, can reduce subjective variability and improve clarity in radiology reports. RadLex coding of radiology reports is widely used in many countries, but translation and localization of RadLex in China are far from being established. Although automatic RadLex coding is a common way for non-standard radiology reports, the high-accuracy cross-language RadLex coding is hardly achieved due to the limitation of up-to-date auto-translation and text similarity algorithms and still requires further research.Methods: We present an effective approach that combines a hybrid translation and a Multilayer Perceptron weighting text similarity ensemble algorithm for automatic RadLex coding of Chinese structured radiology reports. Firstly, a hybrid way to integrate Google neural machine translation and dictionary translation helps to optimize the translation of Chinese radiology phrases to English. The dictionary is made up of 21,863 Chinese-English radiological term pairs extracted from several free medical dictionaries. Secondly, four typical text similarity algorithms are introduced, which are Levenshtein distance, Jaccard similarity coefficient, Word2vec Continuous bag-of-words model, and WordNet Wup similarity algorithms. Lastly, the Multilayer Perceptron model has been used to synthesize the contextual, lexical, character and syntactical information of four text similarity algorithms to promote precision, in which four similarity scores of two terms are taken as input and the output presents whether the two terms are synonyms.Results: The results show the effectiveness of the approach with an F1-score of 90.15%, a precision of 91.78% and a recall of 88.59%. The hybrid translation algorithm has no negative effect on the final coding, F1-score has increased by 21.44% and 8.12% compared with the GNMT algorithm and dictionary translation. Compared with the single similarity, the result of the MLP weighting similarity algorithm is satisfactory that has a 4.48% increase compared with the best single similarity algorithm, WordNet Wup.Conclusions: The paper proposed an innovative automatic cross-language RadLex coding approach to solve the standardization of Chinese structured radiology reports, that can be taken as a reference to automatic cross-language coding. [ABSTRACT FROM AUTHOR]

Background: Vital sign data are important for clinical decision making in emergency care. Clinical Decision Support Systems (CDSS) have been advocated to increase patient safety and quality of care. However, the efficiency of CDSS depends on the quality of the underlying vital sign data. Therefore, possible factors affecting vital sign data quality need to be understood. This study aims to explore the factors affecting vital sign data quality in Swedish emergency departments and to determine in how far clinicians perceive vital sign data to be fit for use in clinical decision support systems. A further aim of the study is to provide recommendations on how to improve vital sign data quality in emergency departments.Methods: Semi-structured interviews were conducted with sixteen physicians and nurses from nine hospitals and vital sign documentation templates were collected and analysed. Follow-up interviews and process observations were done at three of the hospitals to verify the results. Content analysis with constant comparison of the data was used to analyse and categorize the collected data.Results: Factors related to care process and information technology were perceived to affect vital sign data quality. Despite electronic health records (EHRs) being available in all hospitals, these were not always used for vital sign documentation. Only four out of nine sites had a completely digitalized vital sign documentation flow and paper-based triage records were perceived to provide a better mobile workflow support than EHRs. Observed documentation practices resulted in low currency, completeness, and interoperability of the vital signs. To improve vital sign data quality, we propose to standardize the care process, improve the digital documentation support, provide workflow support, ensure interoperability and perform quality control.Conclusions: Vital sign data quality in Swedish emergency departments is currently not fit for use by CDSS. To address both technical and organisational challenges, we propose five steps for vital sign data quality improvement to be implemented in emergency care settings. [ABSTRACT FROM AUTHOR]

Background: An Early Warning Score is a clinical risk score based upon vital signs intended to aid recognition of patients in need of urgent medical attention. The use of an escalation of care policy based upon an Early Warning Score is mandated as the standard of practice in British hospitals. Electronic systems for recording vital sign observations and Early Warning Score calculation offer theoretical benefits over paper-based systems. However, the evidence for their clinical benefit is limited. Previous studies have shown inconsistent results. The majority have employed a "before and after" study design, which may be strongly confounded by simultaneously occurring events. This study aims to examine how the implementation of an electronic early warning score system, System for Notification and Documentation (SEND), affects the recognition of clinical deterioration occurring in hospitalised adult patients.Methods: This study is a non-randomised stepped wedge evaluation carried out across the four hospitals of the Oxford University Hospitals NHS Trust, comparing charting on paper and charting using SEND. We assume that more frequent monitoring of acutely ill patients is associated with better recognition of patient deterioration. The primary outcome measure is the time between a patient's first observations set with an Early Warning Score above the alerting threshold and their subsequent set of observations. Secondary outcome measures are in-hospital mortality, cardiac arrest and Intensive Care admission rates, hospital length of stay and system usability measured using the System Usability Scale. We will also measure Intensive Care length of stay, Intensive Care mortality, Acute Physiology and Chronic Health Evaluation (APACHE) II acute physiology score on admission, to examine whether the introduction of SEND has any effect on Intensive Care-related outcomes.Discussion: The development of this protocol has been informed by guidance from the Agency for Healthcare Research and Quality (AHRQ) Health Information Technology Evaluation Toolkit and Delone and McLeans's Model of Information System Success. Our chosen trial design, a stepped wedge study, is well suited to the study of a phased roll out. The choice of primary endpoint is challenging. We have selected the time from the first triggering observation set to the subsequent observation set. This has the benefit of being easy to measure on both paper and electronic charting and having a straightforward interpretation. We have collected qualitative measures of system quality via a user questionnaire and organisational descriptors to help readers understand the context in which SEND has been implemented. [ABSTRACT FROM AUTHOR]

Background: Clinical notes record the health status, clinical manifestations and other detailed information of each patient. The International Classification of Diseases (ICD) codes are important labels for electronic health records. Automatic medical codes assignment to clinical notes through the deep learning model can not only improve work efficiency and accelerate the development of medical informatization but also facilitate the resolution of many issues related to medical insurance. Recently, neural network-based methods have been proposed for the automatic medical code assignment. However, in the medical field, clinical notes are usually long documents and contain many complex sentences, most of the current methods cannot effective in learning the representation of potential features from document text.Methods: In this paper, we propose a hybrid capsule network model. Specifically, we use bi-directional LSTM (Bi-LSTM) with forwarding and backward directions to merge the information from both sides of the sequence. The label embedding framework embeds the text and labels together to leverage the label information. We then use a dynamic routing algorithm in the capsule network to extract valuable features for medical code prediction task.Results: We applied our model to the task of automatic medical codes assignment to clinical notes and conducted a series of experiments based on MIMIC-III data. The experimental results show that our method achieves a micro F1-score of 67.5% on MIMIC-III dataset, which outperforms the other state-of-the-art methods.Conclusions: The proposed model employed the dynamic routing algorithm and label embedding framework can effectively capture the important features across sentences. Both Capsule networks and domain knowledge are helpful for medical code prediction task. [ABSTRACT FROM AUTHOR]

Background: Text Matching (TM) is a fundamental task of natural language processing widely used in many application systems such as information retrieval, automatic question answering, machine translation, dialogue system, reading comprehension, etc. In recent years, a large number of deep learning neural networks have been applied to TM, and have refreshed benchmarks of TM repeatedly. Among the deep learning neural networks, convolutional neural network (CNN) is one of the most popular networks, which suffers from difficulties in dealing with small samples and keeping relative structures of features. In this paper, we propose a novel deep learning architecture based on capsule network for TM, called CapsTM, where capsule network is a new type of neural network architecture proposed to address some of the short comings of CNN and shows great potential in many tasks.Methods: CapsTM is a five-layer neural network, including an input layer, a representation layer, an aggregation layer, a capsule layer and a prediction layer. In CapsTM, two pieces of text are first individually converted into sequences of embeddings and are further transformed by a highway network in the input layer. Then, Bidirectional Long Short-Term Memory (BiLSTM) is used to represent each piece of text and attention-based interaction matrix is used to represent interactive information of the two pieces of text in the representation layer. Subsequently, the two kinds of representations are fused together by BiLSTM in the aggregation layer, and are further represented with capsules (vectors) in the capsule layer. Finally, the prediction layer is a connected network used for classification. CapsTM is an extension of ESIM by adding a capsule layer before the prediction layer.Results: We construct a corpus of Chinese medical question matching, which contains 36,360 question pairs. This corpus is randomly split into three parts: a training set of 32,360 question pairs, a development set of 2000 question pairs and a test set of 2000 question pairs. On this corpus, we conduct a series of experiments to evaluate the proposed CapsTM and compare it with other state-of-the-art methods. CapsTM achieves the highest F-score of 0.8666.Conclusion: The experimental results demonstrate that CapsTM is effective for Chinese medical question matching and outperforms other state-of-the-art methods for comparison. [ABSTRACT FROM AUTHOR]

Background: The motion capture has been used as the usual method for measuring movement parameters of human, and most of the measuring data are obtained by partial manual process based on commercial software. An automatic kinematics data process was developed by programming on MATLAB software in this paper.Methods: The motion capture measurement of healthy volunteers was carried out and the MATLAB program was used for data process. Firstly, the coordinate data of markers and anatomical points on human lower limb measured by motion capture system were read and repaired through the usual and the patch program. Meantime, the local coordinate systems of human femur and tibia were established with anatomical points. Then flexion/extension, abduction/adduction and internal/external rotation of human knee tibiofemoral joint were obtained by special coordinate transformation program.Results: Using the above methods, motion capture measurements and batch data processing were carried out on squatting and climbing stairs of 29 healthy volunteers. And the motion characteristics (flexion/extension, internal/external rotation and adduction/abduction) of the knee joint were obtained. For example, the maximum internal/external rotation in squatting and climbing stairs were respectively was 30.5 degrees and 14 degrees, etc. Meantime, the results of this paper also were respectively compared with the results processed by other research methods, and the results were basically consistent, thus the reliability of our research method was verified. After calibration processing, the compiled MATLAB program of this paper can directly be used for efficient batch processing and avoiding manual modeling one by one.Conclusion: A novel Patch Program of this paper has been developed, which can make reasonable compensation for missing and noise signals to obtain more complete motion data. At the same time, a universal data processing program has also been developed for obtaining the relative movement of various components of the human body, and the program can be modified for detail special analysis. These motion capture technologies can be used to judge whether the human body functions are abnormal, provide a reference for rehabilitation treatment and design of rehabilitation equipment, and evaluate the effectiveness before and after surgery. [ABSTRACT FROM AUTHOR]

Background: Knowledge is often produced from data generated in scientific investigations. An ever-growing number of scientific studies in several domains result into a massive amount of data, from which obtaining new knowledge requires computational help. For example, Alzheimer's Disease, a life-threatening degenerative disease that is not yet curable. As the scientific community strives to better understand it and find a cure, great amounts of data have been generated, and new knowledge can be produced. A proper representation of such knowledge brings great benefits to researchers, to the scientific community, and consequently, to society.Methods: In this article, we study and evaluate a semi-automatic method that generates knowledge graphs (KGs) from biomedical texts in the scientific literature. Our solution explores natural language processing techniques with the aim of extracting and representing scientific literature knowledge encoded in KGs. Our method links entities and relations represented in KGs to concepts from existing biomedical ontologies available on the Web. We demonstrate the effectiveness of our method by generating KGs from unstructured texts obtained from a set of abstracts taken from scientific papers on the Alzheimer's Disease. We involve physicians to compare our extracted triples from their manual extraction via their analysis of the abstracts. The evaluation further concerned a qualitative analysis by the physicians of the generated KGs with our software tool.Results: The experimental results indicate the quality of the generated KGs. The proposed method extracts a great amount of triples, showing the effectiveness of our rule-based method employed in the identification of relations in texts. In addition, ontology links are successfully obtained, which demonstrates the effectiveness of the ontology linking method proposed in this investigation.Conclusions: We demonstrate that our proposal is effective on building ontology-linked KGs representing the knowledge obtained from biomedical scientific texts. Such representation can add value to the research in various domains, enabling researchers to compare the occurrence of concepts from different studies. The KGs generated may pave the way to potential proposal of new theories based on data analysis to advance the state of the art in their research domains. [ABSTRACT FROM AUTHOR]

Background: The social Q&A community quickly becomes a popular platform for consumers to find health information because of its convenience and interactivity.Methods: Based on the 10,861 depression questions collected in the Zhihu, the largest Q&A platform in China, we divided the healthy information needs description into nine categories with Latent Dirichlet Allocation (LDA). We also divided the healthy information needs type into Physiological, affective and cognitive needs based on the Wilson model.Results: The results show that the largest categories are depression symptom and social activities while the less concerned health information is prevention and medical insurance. More attention is paid to cognitive needs. We also find there is no strong correlation between attention and needs type.Conclusions: The purpose of this paper is to refine the consumer health information needs types to better understand the consumer health information characteristic in China. [ABSTRACT FROM AUTHOR]

Background: Electronic medical records contain a variety of valuable medical information for patients. So, when we are able to recognize and extract risk factors for disease from EMRs of patients with cardiovascular disease (CVD), and are able to use them to predict CVD, we have the ability to automatically process clinical texts, resulting in an improved accuracy of supporting doctors for the clinical diagnosis of CVD. In the case where CVD is becoming more worldwide, predictive CVD based on EMRs has been studied by many researchers to address this important aspect of improving diagnostic efficiency.Methods: This paper proposes an Enhanced Character-level Deep Convolutional Neural Networks (EnDCNN) model for cardiovascular disease prediction.Results: On the manually annotated Chinese EMRs corpus, our risk factor identification extraction model achieved 0.9073 of F-score, our prediction model achieved 0.9516 of F-score, and the prediction result is better than the most previous methods.Conclusions: The character-level model based on text region embedding can well map risk factors and their labels as a unit into a vector, and downsampling plays a crucial role in improving the training efficiency of deep CNN. What's more, the shortcut connections with pre-activation used in our model architecture implements dimension-matching free in training. [ABSTRACT FROM AUTHOR]

Background: Hepatocellular carcinoma is one of the most general malignant neoplasms in adults with high mortality. Mining relative medical knowledge from rapidly growing text data and integrating it with other existing biomedical resources will provide support to the research on the hepatocellular carcinoma. To this purpose, we constructed a knowledge graph for Hepatocellular Carcinoma (KGHC).Methods: We propose an approach to build a knowledge graph for hepatocellular carcinoma. Specifically, we first extracted knowledge from structured data and unstructured data. Since the extracted entities may contain some noise, we applied a biomedical information extraction system, named BioIE, to filter the data in KGHC. Then we introduced a fusion method which is used to fuse the extracted data. Finally, we stored the data into the Neo4j which can help researchers analyze the network of hepatocellular carcinoma.Results: KGHC contains 13,296 triples and provides the knowledge of hepatocellular carcinoma for healthcare professionals, making them free of digging into a large amount of biomedical literatures. This could hopefully improve the efficiency of researches on the hepatocellular carcinoma. KGHC is accessible free for academic research purpose at http://202.118.75.18:18895/browser/ .Conclusions: In this paper, we present a knowledge graph associated with hepatocellular carcinoma, which is constructed with vast amounts of structured and unstructured data. The evaluation results show that the data in KGHC is of high quality. [ABSTRACT FROM AUTHOR]

Background: Personal digital assistants (PDA) offer putative advantages over paper for collecting research data. However, there are no data prospectively comparing PDA and paper in the emergency department. The aim of this study was to prospectively compare the performance of PDA and paper enrollment instruments with respect to time required and errors generated. Methods: We randomized consecutive patients enrolled in an ongoing prospective study to having their data recorded either on a PDA or a paper data collection instrument. For each method, we recorded the total time required for enrollment, and the time required for manual transcription (paper) onto a computer database. We compared data error rates by examining missing data, nonsensical data, and errors made during the transcription of paper forms. Statistical comparisons were performed by Kruskal-Wallis and Poisson regression analyses for time and errors, respectively. Results: We enrolled 68 patients (37 PDA, 31 paper). Two of 31 paper forms were not available for analysis. Total data gathering times, inclusive of transcription, were significantly less for PDA (6:13 min per patient) compared to paper (9:12 min per patient; p < 0.001). There were a total of 0.9 missing and nonsense errors per paper form compared to 0.2 errors per PDA form (p < 0.001). An additional 0.7 errors per paper form were generated during transcription. In total, there were 1.6 errors per paper form and 0.2 errors per PDA form (p < 0.001). Conclusion: Using a PDA-based data collection instrument for clinical research reduces the time required for data gathering and significantly improves data integrity. [ABSTRACT FROM AUTHOR]

Background: The accelerated growth of elderly population is creating a heavy burden to the healthcare system in many developed countries and regions. Electrocardiogram (ECG) analysis has been recognized as effective approach to cardiovascular disease diagnosis and widely utilized for monitoring personalized health conditions.Method: In this study, we present a novel approach to forecasting one-day-forward wellness conditions for community-dwelling elderly by analyzing single lead short ECG signals acquired from a station-based monitoring device. More specifically, exponentially weighted moving-average (EWMA) method is employed to eliminate the high-frequency noise from original signals at first. Then, Fisher-Yates normalization approach is used to adjust the self-evaluated wellness score distribution since the scores among different individuals are skewed. Finally, both deep learning-based and traditional machine learning-based methods are utilized for building wellness forecasting models.Results: The experiment results show that the deep learning-based methods achieve the best fitted forecasting performance, where the forecasting accuracy and F value are 93.21% and 91.98% respectively. The deep learning-based methods, with the merit of non-hand-crafted engineering, have superior wellness forecasting performance towards the competitive traditional machine learning-based methods.Conclusion: The developed approach in this paper is effective in wellness forecasting for community-dwelling elderly, which can provide insights in terms of implementing a cost-effective approach to informing healthcare provider about health conditions of elderly in advance and taking timely interventions to reduce the risk of malignant events. [ABSTRACT FROM AUTHOR]

Background: A collection of disease-associated data contributes to study the association between diseases. Discovering closely related diseases plays a crucial role in revealing their common pathogenic mechanisms. This might further imply treatment that can be appropriated from one disease to another. During the past decades, a number of approaches for calculating disease similarity have been developed. However, most of them are designed to take advantage of single or few data sources, which results in their low accuracy.Methods: In this paper, we propose a novel method, called MultiSourcDSim, to calculate disease similarity by integrating multiple data sources, namely, gene-disease associations, GO biological process-disease associations and symptom-disease associations. Firstly, we establish three disease similarity networks according to the three disease-related data sources respectively. Secondly, the representation of each node is obtained by integrating the three small disease similarity networks. In the end, the learned representations are applied to calculate the similarity between diseases.Results: Our approach shows the best performance compared to the other three popular methods. Besides, the similarity network built by MultiSourcDSim suggests that our method can also uncover the latent relationships between diseases.Conclusions: MultiSourcDSim is an efficient approach to predict similarity between diseases. [ABSTRACT FROM AUTHOR]

Background: With the advent of new high-throughput electron microscopy techniques such as serial block-face scanning electron microscopy (SBF-SEM) and focused ion-beam scanning electron microscopy (FIB-SEM) biomedical scientists can study sub-cellular structural mechanisms of heart disease at high resolution and high volume. Among several key components that determine healthy contractile function in cardiomyocytes are Z-disks or Z-lines, which are located at the lateral borders of the sarcomere, the fundamental unit of striated muscle. Z-disks play the important role of anchoring contractile proteins within the cell that make the heartbeat. Changes to their organization can affect the force with which the cardiomyocyte contracts and may also affect signaling pathways that regulate cardiomyocyte health and function. Compared to other components in the cell, such as mitochondria, Z-disks appear as very thin linear structures in microscopy data with limited difference in contrast to the remaining components of the cell.Methods: In this paper, we propose to generate a 3D model of Z-disks within single adult cardiac cells from an automated segmentation of a large serial-block-face scanning electron microscopy (SBF-SEM) dataset. The proposed fully automated segmentation scheme is comprised of three main modules including "pre-processing", "segmentation" and "refinement". We represent a simple, yet effective model to perform segmentation and refinement steps. Contrast stretching, and Gaussian kernels are used to pre-process the dataset, and well-known "Sobel operators" are used in the segmentation module.Results: We have validated our model by comparing segmentation results with ground-truth annotated Z-disks in terms of pixel-wise accuracy. The results show that our model correctly detects Z-disks with 90.56% accuracy. We also compare and contrast the accuracy of the proposed algorithm in segmenting a FIB-SEM dataset against the accuracy of segmentations from a machine learning program called Ilastik and discuss the advantages and disadvantages that these two approaches have.Conclusions: Our validation results demonstrate the robustness and reliability of our algorithm and model both in terms of validation metrics and in terms of a comparison with a 3D visualisation of Z-disks obtained using immunofluorescence based confocal imaging. [ABSTRACT FROM AUTHOR]

Background: Traditional Chinese medicine (TCM) is a highly important complement to modern medicine and is widely practiced in China and in many other countries. The work of Chinese medicine is subject to the two factors of the inheritance and development of clinical experience of famous Chinese medicine practitioners and the difficulty in improving the service capacity of basic Chinese medicine practitioners. Heterogeneous information networks (HINs) are a kind of graphical model for integrating and modeling real-world information. Through HINs, we can integrate and model the large-scale heterogeneous TCM data into structured graph data and use this as a basis for analysis.Methods: Mining categorizations from TCM data is an important task for precision medicine. In this paper, we propose a novel structured learning model to solve the problem of formula regularity, a pivotal task in prescription optimization. We integrate clustering with ranking in a heterogeneous information network.Results: The results from experiments on the Pharmacopoeia of the People's Republic of China (ChP) demonstrate the effectiveness and accuracy of the proposed model for discovering useful categorizations of formulas.Conclusions: We use heterogeneous information networks to model TCM data and propose a TCM-HIN. Combining the heterogeneous graph with the probability graph, we proposed the TCM-Clus algorithm, which combines clustering with ranking and classifies traditional Chinese medicine prescriptions. The results of the categorizations can help Chinese medicine practitioners to make clinical decision. [ABSTRACT FROM AUTHOR]

Background: Globally, the cases of diabetes mellitus (diabetes) have increased in the past three decades, and it is recorded as one of the leading cause of death. This epidemic is a metabolic condition where the body cannot regulate blood glucose, thereby leading to abnormally high blood sugar. Genetic condition plays a significant role to determine a person susceptibility to the condition, a sedentary lifestyle and an unhealthy diet are behaviour that supports the current global epidemic. The complication that arises from diabetes includes loss of vision, peripheral neuropathy, cardiovascular complications and so on. Victims of this condition require constant monitoring of blood glucose which is done by the pricking of the finger. This procedure is painful, inconvenient and can lead to disease infection. Therefore, it is important to find a way to measure blood glucose non-invasively to minimize or eliminate the disadvantages encountered with the usual monitoring of blood glucose.Method: In this paper, we performed two experiments on 16 participants while electrocardiogram (ECG) data was continuously captured. In the first experiment, participants are required to consume 75 g of anhydrous glucose solution (oral glucose tolerance test) and the second experiment, no glucose solution was taken. We explored statistical and spectral analysis on HRV, HR, R-H, P-H, PRQ, QRS, QT, QTC and ST segments derived from ECG signal to investigate which segments should be considered for the possibility of achieving non-invasive blood glucose monitoring. In the statistical analysis, we examined the pattern of the data with the boxplot technique to reveal the change in the statistical properties of the data. Power spectral density estimation was adopted for the spectral analysis to show the frequency distribution of the data.Results: HRV segment obtained a statistical score of 81% for decreasing pattern and HR segment have the same statistical score for increasing pattern among the participants in the first quartile, median and mean properties. While ST segment has a statistical score of 81% for decreasing pattern in the third quartile, QT segment has 81% for increasing pattern for the median. From a total change score of 6, ST, QT, PRQ, P-H, HR and HRV obtained 4, 5, 4, 5 and 6 respectively. For spectral analysis, HRV and HR segment scored 81 and 75% respectively. ST, QT, PRQ have 75, 62 and 68% respectively.Conclusions: The results obtained demonstrate that HR, HRV, PRQ, QT and ST segments under a normal, healthy condition are affected by glucose and should be considered for modelling a system to achieve the possibility of non-invasive blood glucose measurement with ECG. [ABSTRACT FROM AUTHOR]

Background: In low-income settings, community health workers (CHWs) are frequently the first point of contact for newborns. Mobile technology may aid health workers in classifying illness and providing referral and management guidance for newborn care. This study evaluates the potential for mobile health technology to improve diagnosis and case management of newborns in Bangladesh.Methods: A mobile application based on Bangladesh's Comprehensive Newborn Care Package national guidelines (mCNCP) was developed to aid CHWs in identifying and managing small and sick infants. After a 2-day training, CHWs assessed newborns at Sylhet Osmani Medical College Hospital and in the Projahnmo research site (Sylhet, Bangladesh) using either mCNCP or a comparable paper form (pCNCP), similar to standard IMCI-formatted paper forms. CHWs were randomized to conduct a block of ~ 6 newborn assessments starting with either mCNCP or pCNCP, then switched to the alternate method. Physicians using mCNCP served as gold standard assessors. CHW performance with mCNCP and pCNCP were compared using chi-squared tests of independence for equality of proportions, and logistic regressions clustered by CHW.Results: Two hundred seven total CHW assessments were completed on 101 enrolled infants. mCNCP assessments were more often fully completed and completed faster than pCNCP assessments (100% vs 23.8%, p < 0.001; 17.5 vs 23.6 min; p < 0.001). mCNCP facilitated calculations of respiratory rate, temperature, and gestational age. CHWs using mCNCP were more likely to identify small newborns (Odds Ratio (OR): 20.8, Confidence Interval (CI): (7.1, 60.8), p < 0.001), and to correctly classify 7 out of 16 newborn conditions evaluated, including severe weight loss (OR: 13.1, CI: (4.6, 37.5), p < 0.001), poor movement (OR: 6.6, CI: (2.3, 19.3), p = 0.001), hypothermia (OR: 14.9, CI: (2.7, 82.2), p = 0.002), and feeding intolerance (OR: 2.1, CI: (1.3, 3.3), p = 0.003). CHWs with mCNCP were more likely to provide counseling as needed on 4 out of 7 case management recommendations evaluated, including kangaroo mother care.Conclusions: CHWs in rural Bangladesh with limited experience using tablets successfully used a mobile application for neonatal assessment after a two-day training. mCNCP may aid frontline health workers in Bangladesh to improve completion of neonatal assessment, classification of illnesses, and adherence to neonatal management guidelines. [ABSTRACT FROM AUTHOR]

Background: A pandemic affects healthcare delivery and consequently leads to socioeconomic complications. During a pandemic, a community where there lives an asymptomatic patient (AP) becomes a potential endemic zone. Assuming we want to monitor the travel and/or activity of an AP in a community where there is a pandemic. Presently, most monitoring algorithms are relatively less efficient to find a suitable solution as they overlook the continuous mobility instances and activities of the AP over time. Conversely, this paper proposes an EDDAMAP as a compelling data-dependent technique and/or algorithm towards efficient continuous monitoring of the travel and/or activity of an AP.Methods: In this paper, it is assumed that an AP is infected with a contagious disease in which the EDDAMAP technique exploits a GPS-enabled mobile device by tagging it to the AP along with its travel within a community. The technique further examines the Spatio-temporal trajectory of the AP to infer its spatial time-bounded activity. The technique aims to learn the travels of the AP and correlates them to its activities to derive some classes of point of interests (POIs) in a location. Further, the technique explores the natural occurring POIs via modelling to identify some regular stay places (SP) and present them as endemic zones. The technique adopts concurrent object feature localization and recognition, branch and bound formalism and graph theory to cater for the worst error-guaranteed approximation to obtain a valid and efficient query solution and also experiments with a real-world GeoLife dataset to confirm its performance.Results: The EDDAMAP technique proofs a compelling technique towards efficient monitoring of an AP in case of a pandemic.Conclusions: The EDDAMAP technique will promote the discovery of endemic zones and hence some public healthcare facilities can rely on it to facilitate the design of patient monitoring system applications to curtail a global pandemic. [ABSTRACT FROM AUTHOR]

Background: As the implementation of Electronic Medical Records (EMRs) in hospitals may be challenged by different responses of different user groups, this paper examines the differences between doctors and nurses in their response to the implementation and use of EMRs in their hospital and how this affects the perceived quality of the data in EMRs.Methods: Questionnaire data of 402 doctors and 512 nurses who had experience with the implementation and the use of EMRs in hospitals was analysed with Multi group Structural equation modelling (SEM). The models included measures of organisational factors, results of the implementation (ease of use and alignment of EMR with daily routine), perceived added value, timeliness of use and perceived quality of patient data.Results: Doctors and nurses differ in their response to the organisational factors (support of IT, HR and administrative departments) considering the success of the implementation. Nurses respond to culture while doctors do not. Doctors and nurses agree that an EMR that is easier to work with and better aligned with their work has more added value, but for the doctors this is more pronounced. The doctors and nurses perceive that the quality of the patient data is better when EMRs are easier to use and better aligned with their daily routine.Conclusions: The result of the implementation, in terms of ease of use and alignment with work, seems to affect the perceived quality of patient data more strongly than timeliness of entering patient data. Doctors and nurses value bottom-up communication and support of the IT department for the result of the implementation, and nurses respond to an open and innovative organisational culture. [ABSTRACT FROM AUTHOR]

Background: The influenza surveillance has been received much attention in public health area. For the cases with excessive zeroes, the zero-inflated Poisson process is widely used. However, the traditional control charts based on zero-inflated Poisson model, ignore the association between influenza cases and risk factors, and thus may lead to unexpected mistakes when implementing monitoring charts.Method: In this paper, we proposed risk-adjusted zero-inflated Poisson cumulative sum control charts, in which the risk factors were put to adjust the risk of influenza and the adjustment was made by zero-inflated Poisson regression. We respectively proposed the control chart monitoring the parameters individually and simultaneously.Results: The performance of our proposed risk-adjusted zero-inflated Poisson cumulative sum control chart was evaluated and compared with the unadjusted standard cumulative sum control charts in simulation studies. The results show that for different distribution of impact factors and different coefficients, the risk-adjusted cumulative sum charts can generate much less false alarm than the standard ones. Finally, the influenza surveillance data from Hong Kong is used to illustrate the application of the proposed chart.Conclusions: Our results suggest that the adjusted cumulative sum control chart we proposed is more accurate and credible than the unadjusted standard control charts because of the lower false alarm rate of the adjusted ones. Even the unadjusted control charts may signal a little faster than the adjusted ones, the alarm they raise may have low credibility since they also raise alarm frequently even the processes are in control. Thus we suggest using the risk-adjusted cumulative sum control charts to monitor the influenza surveillance data to alert accurately, credibly and relatively quickly. [ABSTRACT FROM AUTHOR]

Background: The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the past decades. However, those linear approaches are inable to capture the non-linear interactions between risk factors, which have been proved to play an important role in the complex physiology of the human body, and thus may attenuate the performance of surgical risk calculators.Methods: In this paper, we presented a new surgical risk calculator based on a non-linear ensemble algorithm named Gradient Boosting Decision Tree (GBDT) model, and explored the corresponding pipeline to support it. In order to improve the practicability of our approach, we designed three different modes to deal with different data situations. Meanwhile, considering that one of the obstacles to clinical acceptance of surgical risk calculators was that the model was too complex to be used in practice, we reduced the number of input risk factors according to the importance of them in GBDT. In addition, we also built some baseline models and similar models to compare with our approach.Results: The data we used was three-year clinical data from Surgical Outcome Monitoring and Improvement Program (SOMIP) launched by the Hospital Authority of Hong Kong. In all experiments our approach shows excellent performance, among which the best result of area under curve (AUC), Hosmer-Lemeshow test ([Formula: see text]) and brier score (BS) can reach 0.902, 7.398 and 0.047 respectively. After feature reduction, the best result of AUC, [Formula: see text] and BS of our approach can still be maintained at 0.894, 7.638 and 0.060, respectively. In addition, we also performed multiple groups of comparative experiments. The results show that our approach has a stable advantage in each evaluation indicator.Conclusions: The experimental results demonstrate that NL-SRC can not only improve the accuracy of predicting the surgical risk of patients, but also effectively capture important risk factors and their interactions. Meanwhile, it also has excellent performance on the mixed data from multiple surgical fields. [ABSTRACT FROM AUTHOR]

Background: Implementation delays are common in health information technology (HIT) projects. In this paper, we sought to explore the reasons for delays in implementing major hospital-based HIT, through studying computerized physician order entry (CPOE) and clinical decision support (CDS) systems for prescribing and to develop a provisional taxonomy of causes of implementation delays.Methods: We undertook a series of longitudinal, qualitative case studies to investigate the implementation and adoption of CPOE and CDS systems for prescribing in hospitals in the U.K. We used a combination of semi-structured interviews from six case study sites and two whole day expert roundtable discussions to collect data. Interviews were carried out with users, implementers and suppliers of CPOE/CDS systems. We used thematic analysis to examine the results, drawing on perspectives surrounding the biography of artefacts.Results: We identified 15 major factors contributing to delays in implementation of CPOE and CDS systems. These were then categorized in a two-by-two delay classification matrix: one axis distinguishing tactical versus unintended causes of delay, and the second axis illustrating internal i.e., (the adopting hospital) versus external (i.e., suppliers, other hospitals, policymakers) related causes.Conclusions: Our taxonomy of delays in HIT implementation should enable system developers, implementers and policymakers to better plan and manage future implementations. More detailed planning at the outset, considering long-term strategies, sustained user engagement, and phased implementation approaches appeared to reduce the risks of delays. It should however be noted that whilst some delays are likely to be preventable, other delays cannot be easily avoided and taking steps to minimize these may negatively affect the longer-term use of the system. [ABSTRACT FROM AUTHOR]

Background: Patient-reported outcomes (PRO) provide a more comprehensive picture of patients' quality of life than do mere physicians' ratings. Electronic data collection of PRO offers several advantages and allows assessments at patients' homes as well. This study reports on patients' personal internet use, their attitudes towards electronic and web-based PRO assessment (clinic-ePRO and home-ePRO) and the feasibility of these two assessment modes.Methods: At the Medical University of Innsbruck and Kufstein County Hospital, cancer patients who participated in clinic-ePRO/home-ePRO were asked to complete a comprehensive evaluation form on their personal internet usage, attitudes towards and the feasibility of routine clinic-ePRO/home-ePRO with the Computer-based Health Evaluation System (CHES) software.Results: In total, 113 patients completed the evaluation form for clinic-ePRO (Ø 45 years, SD 14) and 45 patients for home-ePRO (Ø 58 years, SD 10; 33.1 per cent inclusion rate for this sample). Most patients expressed willingness to complete routine clinic-ePRO assessments in the future (94.7 per cent of clinic-ePRO patients and 84.4 per cent of home-ePRO patients) and to discuss their data with attending physicians (82.2 per cent, home-ePRO patients only). Overall, patients preferred the software over paper-pencil questionnaires (67.2 per cent of clinic-ePRO patients and 60 per cent of home-ePRO patients) and experienced it as easy to use. Only a few minor suggestions for improvement were made (e.g. adjustable font sizes).Conclusions: The use of clinic-ePRO/home-ePRO was in general shown to be feasible and well accepted. However, to be more inclusive in the implementation of clinic-ePRO/home-ePRO, educational programs concerning their particular benefit in oncology practice potentially could enhance patients' attitudes towards, and consequently their acceptance of and compliance with electronic PRO assessments. [ABSTRACT FROM AUTHOR]

Background: Colorectal cancer (CRC) has a high incidence, especially in New Zealand. The reasons for this are unknown. While most cancers develop sporadically, a positive family history, determined by the number and age at diagnosis of affected first and second degree relatives with CRC is one of the major factors, which may increase an individual's lifetime risk. Before a patient can be enrolled in a surveillance program a detailed assessment and documentation of the family history is important but time consuming and often inaccurate. The documentation is usually paper-based. Our aim was therefore to develop and validate the usability and efficacy of a web-based family history assessment tool for CRC suitable for the general population. The tool was also to calculate the risk and make a recommendation for surveillance.Methods: Two versions of an electronic assessment tool, diagram-based and questionnaire-based, were developed with the risk analysis and recommendations for surveillance based on the New Zealand Guidelines Group recommendations. Accuracy of our tool was tested prior to the study by comparing risk calculations based on family history by experienced gastroenterologists with the electronic assessment. The general public, visiting a local science fair were asked to use and comment on the usability of the two interfaces.Results: Ninety people assessed and commented on the two interfaces. Both interfaces were effective in assessing the risk to develop CRC through their familial history for CRC. However, the questionnaire-based interface performed with significantly better satisfaction (p = 0.001) than the diagram-based interface. There was no difference in efficacy though.Conclusion: We conclude that a web-based questionnaire tool can assist in the accurate documentation and analysis of the family history relevant to determine the individual risk of CRC based on local guidelines. The calculator is now implemented and assessable through the web-page of a local charity for colorectal cancer awareness and integral part of the local general practitioners' e-referral system for colonic imaging. [ABSTRACT FROM AUTHOR]

Background: Cancer-related fatigue is a distressing symptom experienced by many after cancer treatment. An exploratory randomised controlled trial was conducted to test proof of concept of RESTORE: a web-based tool to enhance self-efficacy to manage cancer-related fatigue. This paper reports findings from a qualitative process evaluation to determine feasibility and acceptability of the intervention and trial processes.Method: Qualitative process evaluation carried out at the end of the trial to explore participants' experiences using semi-structured telephone interviews with a purposive sample of participants from both trial arms. Normalisation Process Theory informed data collection and analysis. Analysis involved directed content analysis within a Framework Approach.Results: Nineteen participants took part. They understood the purpose and requirements of the trial and identified beneficial outcomes from taking part. For the majority, the work of the trial was easily accommodated into daily routines and did not require new skills. There were mixed views about the value of the information provided by RESTORE, depending on time since diagnosis and treatment. Personal factors, constraints of the intervention, and environmental context inhibited the integration and embedding of RESTORE into everyday life. Access to the intervention at an early stage in the treatment trajectory was important to effective utilisation, as were individual preferences for delivery of information.Conclusion: The theoretical foundations of the intervention were sound. Participants derived benefits from the intervention but barriers to implementation and integration suggest that RESTORE and the trial processes require some modification before testing in a full trial.Trial Registration: ISRCTN67521059 (10(th) October 2012). [ABSTRACT FROM AUTHOR]

Background: Semantic web technology has been applied widely in the biomedical informatics field. Large numbers of biomedical datasets are available online in the resource description framework (RDF) format. Semantic relationship mining among genes, disorders, and drugs is widely used in, for example, precision medicine and drug repositioning. However, most of the existing studies focused on a single dataset. It is not easy to find the most current relationships among disorder-gene-drug relationships since the relationships are distributed in heterogeneous datasets. How to mine their semantic relationships from different biomedical datasets is an important issue.Methods: First, a variety of biomedical datasets were converted into RDF triple data; then, multisource biomedical datasets were integrated into a storage system using a data integration algorithm. Second, nine query patterns among genes, disorders, and drugs from different biomedical datasets were designed. Third, the gene-disorder-drug semantic relationship mining algorithm is presented. This algorithm can query the relationships among various entities from different datasets.Results and Conclusions: We focused on mining the putative and the most current disorder-gene-drug relationships about Parkinson's disease (PD). The results demonstrate that our method has significant advantages in mining and integrating multisource heterogeneous biomedical datasets. Twenty-five new relationships among the genes, disorders, and drugs were mined from four different datasets. The query results showed that most of them came from different datasets. The precision of the method increased by 2.51% compared to that of the multisource linked open data fusion method presented in the 4th International Workshop on Semantics-Powered Data Mining and Analytics (SEPDA 2019). Moreover, the number of query results increased by 7.7%, and the number of correct queries increased by 9.5%. [ABSTRACT FROM AUTHOR]

Background: Extracting relationships between chemicals and diseases from unstructured literature have attracted plenty of attention since the relationships are very useful for a large number of biomedical applications such as drug repositioning and pharmacovigilance. A number of machine learning methods have been proposed for chemical-induced disease (CID) extraction due to some publicly available annotated corpora. Most of them suffer from time-consuming feature engineering except deep learning methods. In this paper, we propose a novel document-level deep learning method, called recurrent piecewise convolutional neural networks (RPCNN), for CID extraction.Results: Experimental results on a benchmark dataset, the CDR (Chemical-induced Disease Relation) dataset of the BioCreative V challenge for CID extraction show that the highest precision, recall and F-score of our RPCNN-based CID extraction system are 65.24, 77.21 and 70.77%, which is competitive with other state-of-the-art systems.Conclusions: A novel deep learning method is proposed for document-level CID extraction, where domain knowledge, piecewise strategy, attention mechanism, and multi-instance learning are combined together. The effectiveness of the method is proved by experiments conducted on a benchmark dataset. [ABSTRACT FROM AUTHOR]

Background: Agile projects are statistically more likely to succeed then waterfall projects. The overall aim of this study was to explore the nursing staffs' experiences with an agile development process, from its initial requirements to the deployment of its outcome of ICT solutions aimed at supporting discharge planning.Methods: An explorative design with quantitative and qualitative methods was used. Qualitative data was collected through seven focus group interviews. Quantitative data was collected via an ICT-system, and with an evaluation form submitted by fourteen registered nurses and nine district nurses.Results: Qualitative result of the experiences with the agile development process and its outcome resulted in one theme, four categories, and ten subcategories. The theme was found to be about time and timing, namely the amount of time for the different activities and the timing of activities within and between organisations. The agile development process increased the participants' readiness for change by offering time to learn, practice, engage and reflect, and then adopt the ICT as a support to daily practice. Quantitative results showed a variated adoption of the ICT.Conclusion: There is a need for time to prepare, understand and adopt new tools, services and procedures and a need for additional time to prepare, understand and adopt the new among individuals, collectives, organizations, and sometimes even between different collectives or organizations. The agile development process offered the end-users involvement through the development process, which gave them time to change it both individually and collectively. However, there is a need for close collaboration between the development project team and management to reach an organizational change that is timely for both the individual and the collective change. When time or timing fails in the development or implementation process, there is a huge risk of non-adoption of new tools, services, or procedures or among the end-users. [ABSTRACT FROM AUTHOR]

Background: Prescription opioid misuse is a serious national crisis; in 2018 the top drugs involved in prescription overdose deaths included pain medications (opioids), benzodiazepines, and stimulants. Health information technology (health IT) provides a means to address this crisis through technologies that streamline the prescribing and discontinuation process. CancelRx is a health IT function that communicates when medications, such as controlled substances, are discontinued at the clinic and therefore should not be filled at the pharmacy. Prior to CancelRx, the communication of discontinued medications was a manual process, requiring the patient or a clinic staff member to personally contact the pharmacy to inform them of the change. The objective of this study was to assess how controlled substance medication discontinuations were communicated over time, before and after the implementation of CancelRx.Methods: Secondary data from a midwestern academic health system electronic health record and pharmacy platform were collected 12-months prior to CancelRx implementation and for 12-months post implementation. The study utilized an interrupted time series analysis (ITSA) to capture the percentage of controlled substance medications that were discontinued in the clinic's electronic health record and discontinued in the pharmacy's dispensing software. The ITSA plotted the percentage of successful discontinuation messages over time, particularly after the health system's implementation of CancelRx, a novel technology.Results: After CancelRx implementation there was an immediate (change = 77.7 percentage point) and significant (p < 0.001) increase in the number of controlled substance medications that were successfully discontinued at the pharmacy after being discontinued in the clinic. This change was sustained in the year following CancelRx (slope = 0.03 pp, 95% CI - 0.050 to 0.110) and did not revert to pre-CancelRx levels. The health IT functionality was able to effectively complete discontinuation tasks and potentially reduce workload for clinic staff.Conclusions: Overall, this study demonstrates the role that technology can play in promoting communication between clinics and pharmacies, especially when medications such as controlled substances are discontinued. [ABSTRACT FROM AUTHOR]

Background: Automated ICD coding on medical texts via machine learning has been a hot topic. Related studies from medical field heavily relies on conventional bag-of-words (BoW) as the feature extraction method, and do not commonly use more complicated methods, such as word2vec (W2V) and large pretrained models like BERT. This study aimed at uncovering the most effective feature extraction methods for coding models by comparing BoW, W2V and BERT variants.Methods: We experimented with a Chinese dataset from Fuwai Hospital, which contains 6947 records and 1532 unique ICD codes, and a public Spanish dataset, which contains 1000 records and 2557 unique ICD codes. We designed coding tasks with different code frequency thresholds (denoted as [Formula: see text]), with a lower threshold indicating a more complex task. Using traditional classifiers, we compared BoW, W2V and BERT variants on accomplishing these coding tasks.Results: When [Formula: see text] was equal to or greater than 140 for Fuwai dataset, and 60 for the Spanish dataset, the BERT variants with the whole network fine-tuned was the best method, leading to a Micro-F1 of 93.9% for Fuwai data when [Formula: see text], and a Micro-F1 of 85.41% for the Spanish dataset when [Formula: see text]. When [Formula: see text] fell below 140 for Fuwai dataset, and 60 for the Spanish dataset, BoW turned out to be the best, leading to a Micro-F1 of 83% for Fuwai dataset when [Formula: see text], and a Micro-F1 of 39.1% for the Spanish dataset when [Formula: see text]. Our experiments also showed that both the BERT variants and BoW possessed good interpretability, which is important for medical applications of coding models.Conclusions: This study shed light on building promising machine learning models for automated ICD coding by revealing the most effective feature extraction methods. Concretely, our results indicated that fine-tuning the whole network of the BERT variants was the optimal method for tasks covering only frequent codes, especially codes that represented unspecified diseases, while BoW was the best for tasks involving both frequent and infrequent codes. The frequency threshold where the best-performing method varied differed between different datasets due to factors like language and codeset. [ABSTRACT FROM AUTHOR]

Background: Loss to follow-up (LFTU) among HIV patients remains a major obstacle to achieving treatment goals with the risk of failure to achieve viral suppression and thereby increased HIV transmission. Although use of clinical decision support systems (CDSS) has been shown to improve adherence to HIV clinical guidance, to our knowledge, this is among the first studies conducted to show its effect on LTFU in low-resource settings.Methods: We analyzed data from a cluster randomized controlled trial in adults and children (aged ≥ 18 months) who were receiving antiretroviral therapy at 20 HIV clinics in western Kenya between Sept 1, 2012 and Jan 31, 2014. Participating clinics were randomly assigned, via block randomization. Clinics in the control arm had electronic health records (EHR) only while the intervention arm had an EHR with CDSS. The study objectives were to assess the effects of a CDSS, implemented as alerts on an EHR system, on: (1) the proportion of patients that were LTFU, (2) LTFU patients traced and successfully linked back to treatment, and (3) time from enrollment on the study to documentation of LTFU.Results: Among 5901 eligible patients receiving ART, 40.6% (n = 2396) were LTFU during the study period. CDSS was associated with lower LTFU among the patients (Adjusted Odds Ratio-aOR 0.70 (95% CI 0.65-0.77)). The proportions of patients linked back to treatment were 25.8% (95% CI 21.5-25.0) and 30.6% (95% CI 27.9-33.4)) in EHR only and EHR with CDSS sites respectively. CDSS was marginally associated with reduced time from enrollment on the study to first documentation of LTFU (adjusted Hazard Ratio-aHR 0.85 (95% CI 0.78-0.92)).Conclusion: A CDSS can potentially improve quality of care through reduction and early detection of defaulting and LTFU among HIV patients and their re-engagement in care in a resource-limited country. Future research is needed on how CDSS can best be combined with other interventions to reduce LTFU. Trial registration NCT01634802. Registered at www.clinicaltrials.gov on 12-Jul-2012. Registered prospectively. [ABSTRACT FROM AUTHOR]

Background: A large number of biological studies have shown that miRNAs are inextricably linked to many complex diseases. Studying the miRNA-disease associations could provide us a root cause understanding of the underlying pathogenesis in which promotes the progress of drug development. However, traditional biological experiments are very time-consuming and costly. Therefore, we come up with an efficient models to solve this challenge.Results: In this work, we propose a deep learning model called EOESGC to predict potential miRNA-disease associations based on embedding of embedding and simplified convolutional network. Firstly, integrated disease similarity, integrated miRNA similarity, and miRNA-disease association network are used to construct a coupled heterogeneous graph, and the edges with low similarity are removed to simplify the graph structure and ensure the effectiveness of edges. Secondly, the Embedding of embedding model (EOE) is used to learn edge information in the coupled heterogeneous graph. The training rule of the model is that the associated nodes are close to each other and the unassociated nodes are far away from each other. Based on this rule, edge information learned is added into node embedding as supplementary information to enrich node information. Then, node embedding of EOE model training as a new feature of miRNA and disease, and information aggregation is performed by simplified graph convolution model, in which each level of convolution can aggregate multi-hop neighbor information. In this step, we only use the miRNA-disease association network to further simplify the graph structure, thus reducing the computational complexity. Finally, feature embeddings of both miRNA and disease are spliced into the MLP for prediction. On the EOESGC evaluation part, the AUC, AUPR, and F1-score of our model are 0.9658, 0.8543 and 0.8644 by 5-fold cross-validation respectively. Compared with the latest published models, our model shows better results. In addition, we predict the top 20 potential miRNAs for breast cancer and lung cancer, most of which are validated in the dbDEMC and HMDD3.2 databases.Conclusion: The comprehensive experimental results show that EOESGC can effectively identify the potential miRNA-disease associations. [ABSTRACT FROM AUTHOR]

Background: Clinical notes are unstructured text documents generated by clinicians during patient encounters, generally are annotated with International Classification of Diseases (ICD) codes, which give formatted information about the diagnosis and treatment. ICD code has shown its potentials in many fields, but manual coding is labor-intensive and error-prone, lead to researches of automatic coding. Two specific challenges of this task are (1) given an annotated clinical notes, the reasons behind specific diagnoses and treatments are  implicit; (2) explainability is important for practical automatic coding method, the method should not only explain its prediction output but also have explainable internal mechanics. This study aims to develop an explainable CNN approach to address these two challenges.Method: Our key idea is that for the automatic ICD coding task, the presence of informative snippets in the clinical text that correlated with each code plays an important role in the prediction of codes, and an informative snippet can be considered as a local and low-level feature. We infer that there exists a correspondence between a convolution filter and a local and low-level feature. Base on the inference, we come up with the Shallow and Wide Attention convolutional Mechanism (SWAM) to improve the CNN-based models' ability to learn local and low-level features for each label.Results: We evaluate our approach on MIMIC-III, an open-access dataset of ICU medical records. Our approach substantially outperforms previous results on top-50 medical code prediction on MIMIC-III dataset, the precision of the worst-performing 10% labels in previous works is increased from 0% to 53% on average. We attribute this improvement to SWAM, by which the wide architecture with attention mechanism gives the model ability to more extensively learn the unique features of different codes, and we prove it by an ablation experiment. Besides, we perform manual analysis of the performance imbalance between different codes, and preliminary conclude the characteristics that determine the difficulty of learning specific codes.Conclusions: Our main contributions can be summarized into the following three: (1) We present local and low-level features, a.k.a. informative snippets play an important role in the automatic ICD coding task, and the informative snippets extracted from the clinical text provide explanations for each code. (2) We propose that there exists a correspondence between a convolution filter and a local and low-level feature. A combination of wide and shallow convolutional layer and attention layer can help the CNN-based models better learn local and low-level features. (3) We improved the precision of the worst-performing 10% labels from 0 to 53% on average. [ABSTRACT FROM AUTHOR]

Background: Occlusions of intravenous (IV) tubing can prevent vital and time-critical medication or solutions from being delivered into the bloodstream of patients receiving IV therapy. At low flow rates (≤ 1 ml/h) the alarm delay (time to an alert to the user) can be up to 2 h using conventional pressure threshold algorithms. In order to reduce alarm delays we developed and evaluated the performance of two new real-time occlusion detection algorithms and one co-occlusion detector that determines the correlation in trends in pressure changes for multiple pumps.Methods: Bench-tested experimental runs were recorded in triplicate at rates of 1, 2, 4, 8, 16, and 32 ml/h. Each run consisted of 10 min of non-occluded infusion followed by a period of occluded infusion of 10 min or until a conventional occlusion alarm at 400 mmHg occurred. The first algorithm based on binary logistic regression attempts to detect occlusions based on the pump's administration rate Q(t) and pressure sensor readings P(t). The second algorithm continuously monitored whether the actual variation in the pressure exceeded a threshold of 2 standard deviations (SD) above the baseline pressure. When a pump detected an occlusion using the SD algorithm, a third algorithm correlated the pressures of multiple pumps to detect the presence of a shared occlusion. The algorithms were evaluated using 6 bench-tested baseline single-pump occlusion scenarios, 9 single-pump validation scenarios and 7 multi-pump co-occlusion scenarios (i.e. with flow rates of 1 + 1, 1 + 2, 1 + 4, 1 + 8, 1 + 16, and 1 + 32 ml/h respectively). Alarm delay was the primary performance measure.Results: In the baseline single-pump occlusion scenarios, the overall mean ± SD alarm delay of the regression and SD algorithms were 1.8 ± 0.8 min and 0.4 ± 0.2 min, respectively. Compared to the delay of the conventional alarm this corresponds to a mean time reduction of 76% (P = 0.003) and 95% (P = 0.001), respectively. In the validation scenarios the overall mean ± SD alarm delay of the regression and SD algorithms were respectively 1.8 ± 1.6 min and 0.3 ± 0.2 min, corresponding to a mean time reduction of 77% and 95%. In the multi-pump scenarios a correlation > 0.8 between multiple pump pressures after initial occlusion detection by the SD algorithm had a mean ± SD alarm delay of 0.4 ± 0.2 min. In 2 out of the 9 validation scenarios an occlusion was not detected by the regression algorithm before a conventional occlusion alarm occurred. Otherwise no occlusions were missed.Conclusions: In single pumps, both the regression and SD algorithm considerably reduced alarm delay compared to conventional pressure limit-based detection. The SD algorithm appeared to be more robust than the regression algorithm. For multiple pumps the correlation algorithm reliably detected co-occlusions. The latter may be used to localize the segment of tubing in which the occlusion occurs. Trial registration Not applicable. [ABSTRACT FROM AUTHOR]

Background: Diabetic Retinopathy (DR) is the most common and serious microvascular complication in the diabetic population. Using computer-aided diagnosis from the fundus images has become a method of detecting retinal diseases, but the detection of multiple lesions is still a difficult point in current research.Methods: This study proposed a multi-label classification method based on the graph convolutional network (GCN), so as to detect 8 types of fundus lesions in color fundus images. We collected 7459 fundus images (1887 left eyes, 1966 right eyes) from 2282 patients (1283 women, 999 men), and labeled 8 types of lesions, laser scars, drusen, cup disc ratio ([Formula: see text]), hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates. We constructed a specialized corpus of the related fundus lesions. A multi-label classification algorithm for fundus images was proposed based on the corpus, and the collected data were trained.Results: The average overall F1 Score (OF1) and the average per-class F1 Score (CF1) of the model were 0.808 and 0.792 respectively. The area under the ROC curve (AUC) of our proposed model reached 0.986, 0.954, 0.946, 0.957, 0.952, 0.889, 0.937 and 0.926 for detecting laser scars, drusen, cup disc ratio, hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates, respectively.Conclusions: Our results demonstrated that our proposed model can detect a variety of lesions in the color images of the fundus, which lays a foundation for assisting doctors in diagnosis and makes it possible to carry out rapid and efficient large-scale screening of fundus lesions. [ABSTRACT FROM AUTHOR]

Background: Computed tomography (CT) reports record a large volume of valuable information about patients' conditions and the interpretations of radiology images from radiologists, which can be used for clinical decision-making and further academic study. However, the free-text nature of clinical reports is a critical barrier to use this data more effectively. In this study, we investigate a novel deep learning method to extract entities from Chinese CT reports for lung cancer screening and TNM staging.Methods: The proposed approach presents a new named entity recognition algorithm, namely the BERT-based-BiLSTM-Transformer network (BERT-BTN) with pre-training, to extract clinical entities for lung cancer screening and staging. Specifically, instead of traditional word embedding methods, BERT is applied to learn the deep semantic representations of characters. Following the long short-term memory layer, a Transformer layer is added to capture the global dependencies between characters. Besides, pre-training technique is employed to alleviate the problem of insufficient labeled data.Results: We verify the effectiveness of the proposed approach on a clinical dataset containing 359 CT reports collected from the Department of Thoracic Surgery II of Peking University Cancer Hospital. The experimental results show that the proposed approach achieves an 85.96% macro-F1 score under exact match scheme, which improves the performance by 1.38%, 1.84%, 3.81%,4.29%,5.12%,5.29% and 8.84% compared to BERT-BTN, BERT-LSTM, BERT-fine-tune, BERT-Transformer, FastText-BTN, FastText-BiLSTM and FastText-Transformer, respectively.Conclusions: In this study, we developed a novel deep learning method, i.e., BERT-BTN with pre-training, to extract the clinical entities from Chinese CT reports. The experimental results indicate that the proposed approach can efficiently recognize various clinical entities about lung cancer screening and staging, which shows the potential for further clinical decision-making and academic research. [ABSTRACT FROM AUTHOR]

Background: Accurately segment the tumor region of MRI images is important for brain tumor diagnosis and radiotherapy planning. At present, manual segmentation is wildly adopted in clinical and there is a strong need for an automatic and objective system to alleviate the workload of radiologists.Methods: We propose a parallel multi-scale feature fusing architecture to generate rich feature representation for accurate brain tumor segmentation. It comprises two parts: (1) Feature Extraction Network (FEN) for brain tumor feature extraction at different levels and (2) Multi-scale Feature Fusing Network (MSFFN) for merge all different scale features in a parallel manner. In addition, we use two hybrid loss functions to optimize the proposed network for the class imbalance issue.Results: We validate our method on BRATS 2015, with 0.86, 0.73 and 0.61 in Dice for the three tumor regions (complete, core and enhancing), and the model parameter size is only 6.3 MB. Without any post-processing operations, our method still outperforms published state-of-the-arts methods on the segmentation results of complete tumor regions and obtains competitive performance in another two regions.Conclusions: The proposed parallel structure can effectively fuse multi-level features to generate rich feature representation for high-resolution results. Moreover, the hybrid loss functions can alleviate the class imbalance issue and guide the training process. The proposed method can be used in other medical segmentation tasks. [ABSTRACT FROM AUTHOR]

Background: As proven to reflect the work state of heart and physiological situation objectively, electrocardiogram (ECG) is widely used in the assessment of human health, especially the diagnosis of heart disease. The accuracy and reliability of abnormal ECG (AECG) decision depend to a large extent on the feature extraction. However, it is often uneasy or even impossible to obtain accurate features, as the detection process of ECG is easily disturbed by the external environment. And AECG got many species and great variation. What's more, the ECG result obtained after a long time past, which can not reach the purpose of early warning or real-time disease diagnosis. Therefore, developing an intelligent classification model with an accurate feature extraction method to identify AECG is of quite significance. This study aimed to explore an accurate feature extraction method of ECG and establish a suitable model for identifying AECG and the diagnosis of heart disease.Methods: In this research, the wavelet combined with four operations and adaptive threshold methods were applied to filter the ECG and extract its feature waves first. Then, a BP neural network (BPNN) intelligent model and a particle swarm optimization (PSO) improved BPNN (PSO-BPNN) intelligent model based on MIT-BIH open database was established to identify ECG. To reduce the complexity of the model, the principal component analysis (PCA) was used to minimize the feature dimension.Results: Wavelet transforms combined four operations and adaptive threshold methods were capable of ECG filtering and feature extraction. PCA can significantly deduce the modeling feature dimension to minimize the complexity and save classification time. The PSO-BPNN intelligent model was suitable for identifying five types of ECG and showed better effects while comparing it with the BPNN model.Conclusion: In summary, it was further concluded that the PSO-BPNN intelligent model would be a suitable way to identify AECG and provide a tool for the diagnosis of heart disease. [ABSTRACT FROM AUTHOR]

Background: Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data.Methods: An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories.Results: Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement.Conclusions: A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance. [ABSTRACT FROM AUTHOR]

Background: Epilepsy is one of the diseases of the nervous system, which has a large population in the world. Traditional diagnosis methods mostly depended on the professional neurologists' reading of the electroencephalogram (EEG), which was time-consuming, inefficient, and subjective. In recent years, automatic epilepsy diagnosis of EEG by deep learning had attracted more and more attention. But the potential of deep neural networks in seizure detection had not been fully developed.Methods: In this article, we used a one-dimensional convolutional neural network (1-D CNN) to replace the residual network architecture's traditional convolutional neural network (CNN). Moreover, we combined the Independent recurrent neural network (indRNN) and CNN to form a new residual network architecture-independent convolutional recurrent neural network (RCNN). Our model can achieve an automatic diagnosis of epilepsy EEG. Firstly, the important features of EEG were learned by using the residual network architecture of 1-D CNN. Then the relationship between the sequences were learned by using the recurrent neural network. Finally, the model outputted the classification results.Results: On the small sample data sets of Bonn University, our method was superior to the baseline methods and achieved 100% classification accuracy, 100% classification specificity. For the noisy real-world data, our method also exhibited powerful performance.Conclusion: The model we proposed can quickly and accurately identify the different periods of EEG in an ideal condition and the real-world condition. The model can provide automatic detection capabilities for clinical epilepsy EEG detection. We hoped to provide a positive significance for the prediction of epileptic seizures EEG. [ABSTRACT FROM AUTHOR]

Background: Transformer is an attention-based architecture proven the state-of-the-art model in natural language processing (NLP). To reduce the difficulty of beginning to use transformer-based models in medical language understanding and expand the capability of the scikit-learn toolkit in deep learning, we proposed an easy to learn Python toolkit named transformers-sklearn. By wrapping the interfaces of transformers in only three functions (i.e., fit, score, and predict), transformers-sklearn combines the advantages of the transformers and scikit-learn toolkits.Methods: In transformers-sklearn, three Python classes were implemented, namely, BERTologyClassifier for the classification task, BERTologyNERClassifier for the named entity recognition (NER) task, and BERTologyRegressor for the regression task. Each class contains three methods, i.e., fit for fine-tuning transformer-based models with the training dataset, score for evaluating the performance of the fine-tuned model, and predict for predicting the labels of the test dataset. transformers-sklearn is a user-friendly toolkit that (1) Is customizable via a few parameters (e.g., model_name_or_path and model_type), (2) Supports multilingual NLP tasks, and (3) Requires less coding. The input data format is automatically generated by transformers-sklearn with the annotated corpus. Newcomers only need to prepare the dataset. The model framework and training methods are predefined in transformers-sklearn.Results: We collected four open-source medical language datasets, including TrialClassification for Chinese medical trial text multi label classification, BC5CDR for English biomedical text name entity recognition, DiabetesNER for Chinese diabetes entity recognition and BIOSSES for English biomedical sentence similarity estimation. In the four medical NLP tasks, the average code size of our script is 45 lines/task, which is one-sixth the size of transformers' script. The experimental results show that transformers-sklearn based on pretrained BERT models achieved macro F1 scores of 0.8225, 0.8703 and 0.6908, respectively, on the TrialClassification, BC5CDR and DiabetesNER tasks and a Pearson correlation of 0.8260 on the BIOSSES task, which is consistent with the results of transformers.Conclusions: The proposed toolkit could help newcomers address medical language understanding tasks using the scikit-learn coding style easily. The code and tutorials of transformers-sklearn are available at https://doi.org/10.5281/zenodo.4453803 . In future, more medical language understanding tasks will be supported to improve the applications of transformers_sklearn. [ABSTRACT FROM AUTHOR]

Background: Diabetes Mellitus (DM) has become the third chronic non-communicable disease that hits patients after tumors, cardiovascular and cerebrovascular diseases, and has become one of the major public health problems in the world. Therefore, it is of great importance to identify individuals at high risk for DM in order to establish prevention strategies for DM.Methods: Aiming at the problem of high-dimensional feature space and high feature redundancy of medical data, as well as the problem of data imbalance often faced. This study explored different supervised classifiers, combined with SVM-SMOTE and two feature dimensionality reduction methods (Logistic stepwise regression and LAASO) to classify the diabetes survey sample data with unbalanced categories and complex related factors. Analysis and discussion of the classification results of 4 supervised classifiers based on 4 data processing methods. Five indicators including Accuracy, Precision, Recall, F1-Score and AUC are selected as the key indicators to evaluate the performance of the classification model.Results: According to the result, Random Forest Classifier combining SVM-SMOTE resampling technology and LASSO feature screening method (Accuracy = 0.890, Precision = 0.869, Recall = 0.919, F1-Score = 0.893, AUC = 0.948) proved the best way to tell those at high risk of DM. Besides, the combined algorithm helps enhance the classification performance for prediction of high-risk people of DM. Also, age, region, heart rate, hypertension, hyperlipidemia and BMI are the top six most critical characteristic variables affecting diabetes.Conclusions: The Random Forest Classifier combining with SVM-SMOTE and LASSO feature reduction method perform best in identifying high-risk people of DM from individuals. And the combined method proposed in the study would be a good tool for early screening of DM. [ABSTRACT FROM AUTHOR]

Background: The Ministry of Health in Saudi Arabia is expanding the country's telemedicine services by using advanced technology in health services. In doing so, an e-health application (app), Seha, was introduced in 2018 that allows individuals to have face-to-face visual medical consultations with their doctors on their smartphones.Objective: This study evaluated the effectiveness of the app in improving healthcare delivery by ensuring patient satisfaction with the care given, increasing access to care, and improving efficiency in the healthcare system.Methods: A cross-sectional study design was used to assess the perceptions of users of the Seha app and non-users who continued with traditional health services. The data were collected using an online survey via Google Forms between June 2020 and September 2020. Independent t tests and chi-square (χ2) tests were conducted to answer the research questions.Results: There was a significant difference between users and non-users in terms of ease of access to health services (t =  - 9.38, p < 0.05), with app users having a higher mean score (4.19 ± 0.91) than non-users (3.41 ± 1.00); satisfaction with health services (t =  - 6.33, p < 0.05), with users having a higher mean score (3.96 ± 0.91) than non-users (3.45 ± 0.94); and efficiency (only one visit needed for treatment) (t =  - 3.20, p < 0.05), with users having a higher mean score (3.71 ± 0.93) than non-users (3.45 ± 0.93). There were significant associations between the use of the Seha app and age (χ2 = 8.79, p < 0.05), gender (χ2 = 22.19, p < 0.05), region (χ2 = 19.74, p < 0.05), and occupation (χ2 = 22.05, p < 0.05). There were significant relationships between the three items (on access, satisfaction, and efficiency) and experiencing technical issues (t = 4.47, t = 8.11, and t = 3.24, respectively, p < 0.05), with users who faced technical problems having significantly lower mean scores for all three items.Conclusion: This study provided evidence that the Seha app improved the delivery of healthcare in Saudi Arabia. Users of the app had a better health experience in terms of their perceived ease of access to healthcare services; their satisfaction with healthcare services; and the efficiency of the system, measured by the number of required doctor visits. Other factors that appeared to influence the use of the app included age, gender, usual source of care, and technical difficulties. [ABSTRACT FROM AUTHOR]