Search

Objective: We propose a MATLAB-based tool to convert electrocardiography (ECG) waveforms from paper-based ECG records into digitized ECG signals that is vendor-agnostic. The tool is packaged as an open source standalone graphical user interface (GUI) based application. Methods and procedures: To reach this objective we: (1) preprocess the ECG records, which includes skew correction, background grid removal and linear filtering; (2) segment ECG signals using Connected Components Analysis (CCA); (3) implement Optical Character Recognition (OCR) for removal of overlapping ECG lead characters and for interfacing of patients’ demographic information with their research records or their electronic medical record (EMR). The ECG digitization results are validated through a reader study where clinically salient features, such as intervals of QRST complex, between the paper ECG records and the digitized ECG records are compared. Results: Comparison of clinically important features between the paper-based ECG records and the digitized ECG signals, reveals intra- and inter-observer correlations of 0.86–0.99 and 0.79–0.94, respectively. The kappa statistic was found to average at 0.86 and 0.72 for intra- and inter-observer correlations, respectively. Conclusion: The clinically salient features of the ECG waveforms such as the intervals of QRST complex, are preserved during the digitization procedure. Clinical and Healthcare Impact: This open-source digitization tool can be used as a research resource to digitize paper ECG records thereby enabling development of new prediction algorithms to risk stratify individuals with cardiovascular disease, and/or allow for development of ECG-based cardiovascular diagnoses relying upon automated digital algorithms.

Background When using machine learning in the real world, the missing value problem is the first problem encountered. Methods to impute this missing value include statistical methods such as mean, expectation-maximization, and multiple imputations by chained equations (MICE) as well as machine learning methods such as multilayer perceptron, k-nearest neighbor, and decision tree. Objective The objective of this study was to impute numeric medical data such as physical data and laboratory data. We aimed to effectively impute data using a progressive method called self-training in the medical field where training data are scarce. Methods In this paper, we propose a self-training method that gradually increases the available data. Models trained with complete data predict the missing values in incomplete data. Among the incomplete data, the data in which the missing value is validly predicted are incorporated into the complete data. Using the predicted value as the actual value is called pseudolabeling. This process is repeated until the condition is satisfied. The most important part of this process is how to evaluate the accuracy of pseudolabels. They can be evaluated by observing the effect of the pseudolabeled data on the performance of the model. Results In self-training using random forest (RF), mean squared error was up to 12% lower than pure RF, and the Pearson correlation coefficient was 0.1% higher. This difference was confirmed statistically. In the Friedman test performed on MICE and RF, self-training showed a P value between .003 and .02. A Wilcoxon signed-rank test performed on the mean imputation showed the lowest possible P value, 3.05e-5, in all situations. Conclusions Self-training showed significant results in comparing the predicted values and actual values, but it needs to be verified in an actual machine learning system. And self-training has the potential to improve performance according to the pseudolabel evaluation method, which will be the main subject of our future research.

Radiological measurements are reported in free text reports, and it is challenging to extract such measures for treatment planning such as lesion summarization and cancer response assessment. The purpose of this work is to develop and evaluate a natural language processing (NLP) pipeline that can extract measurements and their core descriptors, such as temporality, anatomical entity, imaging observation, RadLex descriptors, series number, image number, and segment from a wide variety of radiology reports (MR, CT, and mammogram). We created a hybrid NLP pipeline that integrates rule-based feature extraction modules and conditional random field (CRF) model for extraction of the measurements from the radiology reports and links them with clinically relevant features such as anatomical entities or imaging observations. The pipeline was trained on 1117 CT/MR reports, and performance of the system was evaluated on an independent set of 100 expert-annotated CT/MR reports and also tested on 25 mammography reports. The system detected 813 out of 806 measurements in the CT/MR reports; 784 were true positives, 29 were false positives, and 0 were false negatives. Similarly, from the mammography reports, 96% of the measurements with their modifiers were extracted correctly. Our approach could enable the development of computerized applications that can utilize summarized lesion measurements from radiology report of varying modalities and improve practice by tracking the same lesions along multiple radiologic encounters.

Background One of the major challenges in the health care sector is that approximately 80% of generated data remains unstructured and unused. Since it is difficult to handle unstructured data from electronic medical record systems, it tends to be neglected for analyses in most hospitals and medical centers. Therefore, there is a need to analyze unstructured big data in health care systems so that we can optimally utilize and unearth all unexploited information from it. Objective In this study, we aimed to extract a list of diseases and associated keywords along with the corresponding time durations from an indigenously developed electronic medical record system and describe the possibility of analytics from the acquired datasets. Methods We propose a novel, finite-state machine to sequentially detect and cluster disease names from patients’ medical history. We defined 3 states in the finite-state machine and transition matrix, which depend on the identified keyword. In addition, we also defined a state-change action matrix, which is essentially an action associated with each transition. The dataset used in this study was obtained from an indigenously developed electronic medical record system called eyeSmart that was implemented across a large, multitier ophthalmology network in India. The dataset included patients’ past medical history and contained records of 10,000 distinct patients. Results We extracted disease names and associated keywords by using the finite-state machine with an accuracy of 95%, sensitivity of 94.9%, and positive predictive value of 100%. For the extraction of the duration of disease, the machine’s accuracy was 93%, sensitivity was 92.9%, and the positive predictive value was 100%. Conclusions We demonstrated that the finite-state machine we developed in this study can be used to accurately identify disease names, associated keywords, and time durations from a large cohort of patient records obtained using an electronic medical record system.

Background Fractures as a result of osteoporosis and low bone mass are common and give rise to significant clinical, personal, and economic burden. Even after a fracture occurs, high fracture risk remains widely underdiagnosed and undertreated. Common fracture risk assessment tools utilize a subset of clinical risk factors for prediction, and often require manual data entry. Furthermore, these tools predict risk over the long term and do not explicitly provide short-term risk estimates necessary to identify patients likely to experience a fracture in the next 1-2 years. Objective The goal of this study was to develop and evaluate an algorithm for the identification of patients at risk of fracture in a subsequent 1- to 2-year period. In order to address the aforementioned limitations of current prediction tools, this approach focused on a short-term timeframe, automated data entry, and the use of longitudinal data to inform the predictions. Methods Using retrospective electronic health record data from over 1,000,000 patients, we developed Crystal Bone, an algorithm that applies machine learning techniques from natural language processing to the temporal nature of patient histories to generate short-term fracture risk predictions. Similar to how language models predict the next word in a given sentence or the topic of a document, Crystal Bone predicts whether a patient’s future trajectory might contain a fracture event, or whether the signature of the patient’s journey is similar to that of a typical future fracture patient. A holdout set with 192,590 patients was used to validate accuracy. Experimental baseline models and human-level performance were used for comparison. Results The model accurately predicted 1- to 2-year fracture risk for patients aged over 50 years (area under the receiver operating characteristics curve [AUROC] 0.81). These algorithms outperformed the experimental baselines (AUROC 0.67) and showed meaningful improvements when compared to retrospective approximation of human-level performance by correctly identifying 9649 of 13,765 (70%) at-risk patients who did not receive any preventative bone-health-related medical interventions from their physicians. Conclusions These findings indicate that it is possible to use a patient’s unique medical history as it changes over time to predict the risk of short-term fracture. Validating and applying such a tool within the health care system could enable automated and widespread prediction of this risk and may help with identification of patients at very high risk of fracture.

Background Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. Objective We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Methods Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. Results With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. Conclusions For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.

Background Many public health departments use record linkage between surveillance data and external data sources to inform public health interventions. However, little guidance is available to inform these activities, and many health departments rely on deterministic algorithms that may miss many true matches. In the context of public health action, these missed matches lead to missed opportunities to deliver interventions and may exacerbate existing health inequities. Objective This study aimed to compare the performance of record linkage algorithms commonly used in public health practice. Methods We compared five deterministic (exact, Stenger, Ocampo 1, Ocampo 2, and Bosh) and two probabilistic record linkage algorithms (fastLink and beta record linkage [BRL]) using simulations and a real-world scenario. We simulated pairs of datasets with varying numbers of errors per record and the number of matching records between the two datasets (ie, overlap). We matched the datasets using each algorithm and calculated their recall (ie, sensitivity, the proportion of true matches identified by the algorithm) and precision (ie, positive predictive value, the proportion of matches identified by the algorithm that were true matches). We estimated the average computation time by performing a match with each algorithm 20 times while varying the size of the datasets being matched. In a real-world scenario, HIV and sexually transmitted disease surveillance data from King County, Washington, were matched to identify people living with HIV who had a syphilis diagnosis in 2017. We calculated the recall and precision of each algorithm compared with a composite standard based on the agreement in matching decisions across all the algorithms and manual review. Results In simulations, BRL and fastLink maintained a high recall at nearly all data quality levels, while being comparable with deterministic algorithms in terms of precision. Deterministic algorithms typically failed to identify matches in scenarios with low data quality. All the deterministic algorithms had a shorter average computation time than the probabilistic algorithms. BRL had the slowest overall computation time (14 min when both datasets contained 2000 records). In the real-world scenario, BRL had the lowest trade-off between recall (309/309, 100.0%) and precision (309/312, 99.0%). Conclusions Probabilistic record linkage algorithms maximize the number of true matches identified, reducing gaps in the coverage of interventions and maximizing the reach of public health action.

BackgroundPatient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text.ObjectiveThis study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats.MethodsClinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy.ResultsAmong 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events.ConclusionsAutomated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems. Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether. The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.

Motivation Pedigree analysis is a longstanding and powerful approach to gain insight into the underlying genetic factors in human health, but identifying, recruiting and genotyping families can be difficult, time consuming and costly. Development of high throughput methods to identify families and foster downstream analyses are necessary. Results This paper describes simple methods that allowed us to identify 173 368 family pedigrees with high probability using basic demographic data available in most electronic health records (EHRs). We further developed and validate a novel statistical method that uses EHR data to identify families more likely to have a major genetic component to their diseases risk. Lastly, we showed that incorporating EHR-linked family data into genetic association testing may provide added power for genetic mapping without additional recruitment or genotyping. The totality of these results suggests that EHR-linked families can enable classical genetic analyses in a high-throughput manner. Availability and implementation Pseudocode is provided as supplementary information Supplementary information Supplementary data are available at Bioinformatics online.

Background Falls are common adverse events in hospitals, frequently leading to additional health costs due to prolonged stays and extra care. Therefore, reliable fall detection is vital to develop and test fall prevention strategies. However, conventional methods—voluntary incident reports and manual chart reviews—are error-prone and time consuming, respectively. Using a search algorithm to examine patients’ electronic health record data and flag fall indicators offers an inexpensive, sensitive, cost-effective alternative. Objective This study’s purpose was to develop a fall detection algorithm for use with electronic health record data, then to evaluate it alongside the Global Trigger Tool, incident reports, a manual chart review, and patient-reported falls. Methods Conducted on 2 campuses of a large hospital system in Switzerland, this retrospective diagnostic accuracy study consisted of 2 substudies: the first, targeting 240 patients, for algorithm development and the second, targeting 298 patients, for validation. In the development study, we compared the new algorithm’s in-hospital fall rates with those indicated by the Global Trigger Tool and incident reports; in the validation study, we compared the algorithm’s in-hospital fall rates with those from patient-reported falls and manual chart review. We compared the various methods by calculating sensitivity, specificity, and predictive values. Results Twenty in-hospital falls were discovered in the development study sample. Of these, the algorithm detected 19 (sensitivity 95%), the Global Trigger Tool detected 18 (90%), and incident reports detected 14 (67%). Of the 15 falls found in the validation sample, the algorithm identified all 15 (100%), the manual chart review identified 14 (93%), and the patient-reported fall measure identified 5 (33%). Owing to relatively high numbers of false positives based on falls present on admission, the algorithm’s positive predictive values were 50% (development sample) and 47% (validation sample). Instead of requiring 10 minutes per case for a full manual review or 20 minutes to apply the Global Trigger Tool, the algorithm requires only a few seconds, after which only the positive results (roughly 11% of the full case number) require review. Conclusions The newly developed electronic health record algorithm demonstrated very high sensitivity for fall detection. Applied in near real time, the algorithm can record in-hospital falls events effectively and help to develop and test fall prevention measures.

Background Blockchain has the potential to disrupt the current modes of patient data access, accumulation, contribution, exchange, and control. Using interoperability standards, smart contracts, and cryptographic identities, patients can securely exchange data with providers and regulate access. The resulting comprehensive, longitudinal medical records can significantly improve the cost and quality of patient care for individuals and populations alike. Objective This work presents HealthChain, a novel patient-centered blockchain framework. The intent is to bolster patient engagement, data curation, and regulated dissemination of accumulated information in a secure, interoperable environment. A mixed-block blockchain is proposed to support immutable logging and redactable patient blocks. Patient data are generated and exchanged through Health Level-7 Fast Healthcare Interoperability Resources, allowing seamless transfer with compliant systems. In addition, patients receive cryptographic identities in the form of public and private key pairs. Public keys are stored in the blockchain and are suitable for securing and verifying transactions. Furthermore, the envisaged system uses proxy re-encryption (PRE) to share information through revocable, smart contracts, ensuring the preservation of privacy and confidentiality. Finally, several PRE improvements are offered to enhance performance and security. Methods The framework was formulated to address key barriers to blockchain adoption in health care, namely, information security, interoperability, data integrity, identity validation, and scalability. It supports 16 configurations through the manipulation of 4 modes. An open-source, proof-of-concept tool was developed to evaluate the performance of the novel patient block components and system configurations. To demonstrate the utility of the proposed framework and evaluate resource consumption, extensive testing was performed on each of the 16 configurations over a variety of scenarios involving a variable number of existing and imported records. Results The results indicate several clear high-performing, low-bandwidth configurations, although they are not the strongest cryptographically. Of the strongest models, one’s anticipated cumulative record size is shown to influence the selection. Although the most efficient algorithm is ultimately user specific, Advanced Encryption Standard–encrypted data with static keys, incremental server storage, and no additional server-side encryption are the fastest and least bandwidth intensive, whereas proxy re-encrypted data with dynamic keys, incremental server storage, and additional server-side encryption are the best performing of the strongest configurations. Conclusions Blockchain is a potent and viable technology for patient-centered access to and exchange of health information. By integrating a structured, interoperable design with patient-accumulated and generated data shared through smart contracts into a universally accessible blockchain, HealthChain presents patients and providers with access to consistent and comprehensive medical records. Challenges addressed include data security, interoperability, block storage, and patient-administered data access, with several configurations emerging for further consideration regarding speed and security.

Objective: Clinical notes, typically written in natural language, often contain substructure that divides them into sections, such as “History of Present Illness” or “Family Medical History.” The authors designed and evaluated an algorithm (“SecTag”) to identify both labeled and unlabeled (implied) note section headers in “history and physical examination” documents (“H&P notes”). Design: The SecTag algorithm uses a combination of natural language processing techniques, word variant recognition with spelling correction, terminology-based rules, and naive Bayesian scoring methods to identify note section headers. Eleven physicians evaluated SecTag's performance on 319 randomly chosen H&P notes. Measurements: The primary outcomes were the algorithm's recall and precision in identifying all document sections and a predefined list of twenty-nine major sections. A secondary outcome was to evaluate the algorithm's ability to recognize the correct start and end boundaries of identified sections. Results: The SecTag algorithm identified 16,036 total sections and 7,858 major sections. Physician evaluators classified 15,329 as true positives and identified 160 sections omitted by SecTag. The recall and precision of the SecTag algorithm were 99.0 and 95.6% for all sections, 98.6 and 96.2% for major sections, and 96.6 and 86.8% for unlabeled sections. The algorithm determined the correct starting and ending text boundaries for 94.8% of labeled sections and 85.9% of unlabeled sections. Conclusions: The SecTag algorithm accurately identified both labeled and unlabeled sections in history and physical documents. This type of algorithm may assist in natural language processing applications, such as clinical decision support systems or competency assessment for medical trainees.

Objective Although electronic notes have advantages compared to handwritten notes, they take longer to write and promote information redundancy in electronic health records (EHRs). We sought to quantify redundancy in clinical documentation by studying collections of physician notes in an EHR. Design and methods We implemented a retrospective design to gather all electronic admission, progress, resident signout and discharge summary notes written during 100 randomly selected patient admissions within a 6 month period. We modified and applied a Levenshtein edit-distance algorithm to align and compare the documents written for each of the 100 admissions. We then identified and measured the amount of text duplicated from previous notes. Finally, we manually reviewed the content that was conserved between note types in a subsample of notes. Measurements We measured the amount of new information in a document, which was calculated as the number of words that did not match with previous documents divided by the length, in words, of the document. Results are reported as the percentage of information in a document that had been duplicated from previously written documents. Results Signout and progress notes proved to be particularly redundant, with an average of 78% and 54% information duplicated from previous documents respectively. There was also significant information duplication between document types (eg, from an admission note to a progress note). Conclusion The study established the feasibility of exploring redundancy in the narrative record with a known sequence alignment algorithm used frequently in the field of bioinformatics. The findings provide a foundation for studying the usefulness and risks of redundancy in the EHR.

The maintenance and sharing of electronic medical records are one of the essential tasks in the medical treatment combination. Traditional cloud-based electronic medical record storage system is difficult to realize data security sharing. The tamper resistance and traceability of blockchain technology provide the possibility for the sharing of highly sensitive medical data. This paper proposes a safe sharing scheme of stroke electronic medical records based on the consortium blockchain. The scheme adopts the storage method of ciphertext of medical records stored in the cloud and index of medical records stored on the blockchain. The privacy protection mechanism proposed in this paper innovatively combines proxy reencryption and searchable encryption which supports patient pseudoidentity search. The mechanism could achieve controllable sharing of medical records and precise search. According to the organizational characteristics of the stroke medical treatment combination, this paper proposes an improved Practical Byzantine Fault Tolerance mechanism to reach a consensus between consensus nodes. Then, the proposed scheme is analyzed and evaluated from three aspects of medical record integrity, user privacy, and data security. The results show that the scheme can not only ensure the privacy of patient identity information and private key data but also resist the tampering and deletion attacks of internal and external malicious nodes on the medical record data. Therefore, the proposed scheme is conducive to the improvement of the timeliness of stroke treatment and the safe sharing of electronic medical records in stroke medical treatment combination.

Background The main goal of this study is to explore the use of features representing patient-level electronic health record (EHR) data, generated by the unsupervised deep learning algorithm autoencoder, in predictive modeling. Since autoencoder features are unsupervised, this paper focuses on their general lower-dimensional representation of EHR information in a wide variety of predictive tasks. Methods We compare the model with autoencoder features to traditional models: logistic model with least absolute shrinkage and selection operator (LASSO) and Random Forest algorithm. In addition, we include a predictive model using a small subset of response-specific variables (Simple Reg) and a model combining these variables with features from autoencoder (Enhanced Reg). We performed the study first on simulated data that mimics real world EHR data and then on actual EHR data from eight Advocate hospitals. Results On simulated data with incorrect categories and missing data, the precision for autoencoder is 24.16% when fixing recall at 0.7, which is higher than Random Forest (23.61%) and lower than LASSO (25.32%). The precision is 20.92% in Simple Reg and improves to 24.89% in Enhanced Reg. When using real EHR data to predict the 30-day readmission rate, the precision of autoencoder is 19.04%, which again is higher than Random Forest (18.48%) and lower than LASSO (19.70%). The precisions for Simple Reg and Enhanced Reg are 18.70 and 19.69% respectively. That is, Enhanced Reg can have competitive prediction performance compared to LASSO. In addition, results show that Enhanced Reg usually relies on fewer features under the setting of simulations of this paper. Conclusions We conclude that autoencoder can create useful features representing the entire space of EHR data and which are applicable to a wide array of predictive tasks. Together with important response-specific predictors, we can derive efficient and robust predictive models with less labor in data extraction and model training.

Background Ontology has attracted substantial attention from both academia and industry. Handling uncertainty reasoning is important in researching ontology. For example, when a patient is suffering from cirrhosis, the appearance of abdominal vein varices is four times more likely than the presence of bitter taste. Such medical knowledge is crucial for decision-making in various medical applications but is missing from existing medical ontologies. In this paper, we aim to discover medical knowledge probabilities from electronic medical record (EMR) texts to enrich ontologies. First, we build an ontology by identifying meaningful entity mentions from EMRs. Then, we propose a symptom-dependency-aware naïve Bayes classifier (SDNB) that is based on the assumption that there is a level of dependency among symptoms. To ensure the accuracy of the diagnostic classification, we incorporate the probability of a disease into the ontology via innovative approaches. Results We conduct a series of experiments to evaluate whether the proposed method can discover meaningful and accurate probabilities for medical knowledge. Based on over 30,000 deidentified medical records, we explore 336 abdominal diseases and 81 related symptoms. Among these 336 gastrointestinal diseases, the probabilities of 31 diseases are obtained via our method. These 31 probabilities of diseases and 189 conditional probabilities between diseases and the symptoms are added into the generated ontology. Conclusion In this paper, we propose a medical knowledge probability discovery method that is based on the analysis and extraction of EMR text data for enriching a medical ontology with probability information. The experimental results demonstrate that the proposed method can effectively identify accurate medical knowledge probability information from EMR data. In addition, the proposed method can efficiently and accurately calculate the probability of a patient suffering from a specified disease, thereby demonstrating the advantage of combining an ontology and a symptom-dependency-aware naïve Bayes classifier.

PURPOSE Synoptic reporting provides a mechanism for uniform and structured pathology diagnostics. This paper demonstrates the functionality of Perl alternation and grouping expressions to classify electronic pathology reports generated from military treatment facilities. Eight Perl-based algorithms are validated to classify malignant melanoma, Hodgkin lymphoma, non-Hodgkin lymphoma, leukemia, and malignant neoplasms of the breast, ovary, testis, and thyroid. METHODS Case finding cohorts were developed using diagnostic codes for neoplasm groups and matched by unique identifiers to obtain pathology records. Preprocessing techniques and Perl-based algorithms were applied to classify records as malignant, in situ, suspect, or nonapplicable, followed by a hand-review process to determine the accuracy of the algorithm classifications. Interrater reliability, sensitivity, specificity, positive predictive values, and negative predictive values were computed following abstractor adjudication. RESULTS The specificity of the Perl-based algorithms was consistently high, over 98%. Very few benign results were classified as malignant or in situ by the Perl-based algorithms; the leukemia algorithm classification was the only group to demonstrate a positive predictive value below 95%, at 91.9%. Three algorithm classification groups demonstrated a sensitivity of < 80%, including malignant neoplasm of the ovary (33.3%), leukemia (52.8%), and non-Hodgkin lymphoma (62.9%). The pathology records for these results included substantial linguistic variation. CONCLUSION This paper contextualizes the utility and value of an algorithm logic built around synoptic reporting to identify neoplasms from electronic pathology results. The major strength includes the application of Perl-based coding in SAS, an accessible software application, to develop highly specific algorithms across institutional variation in diagnostic documentation.

Background. Nowadays, with the digitalization of healthcare systems, huge amounts of clinical narratives are available. However, despite the wealth of information contained in them, interoperability and extraction of relevant information from documents remains a challenge. Objective. This work presents an approach towards automatically standardizing Spanish Electronic Discharge Summaries (EDS) following the HL7 Clinical Document Architecture. We address the task of section annotation in EDSs written in Spanish, experimenting with three different approaches, with the aim of boosting interoperability across healthcare systems and hospitals. Methods. The paper presents three different methods, ranging from a knowledge-based solution by means of manually constructed rules to supervised Machine Learning approaches, using state of the art algorithms like the Perceptron and transfer learning-based Neural Networks. Results. The paper presents a detailed evaluation of the three approaches on two different hospitals. Overall, the best system obtains a 93.03% F-score for section identification. It is worth mentioning that this result is not completely homogeneous over all section types and hospitals, showing that cross-hospital variability in certain sections is bigger than in others. Conclusions. As a main result, this work proves the feasibility of accurate automatic detection and standardization of section blocks in clinical narratives, opening the way to interoperability and secondary use of clinical data.

Mobile health (m-health) is the term of monitoring the health using mobile phones and patient monitoring devices etc. It has been often deemed as the substantial breakthrough in technology in this modern era. Recently, artificial intelligence (AI) and big data analytics have been applied within the m-health for providing an effective healthcare system. Various types of data such as electronic health records (EHRs), medical images, and complicated text which are diversified, poorly interpreted, and extensively unorganized have been used in the modern medical research. This is an important reason for the cause of various unorganized and unstructured datasets due to emergence of mobile applications along with the healthcare systems. In this paper, a systematic review is carried out on application of AI and the big data analytics to improve the m-health system. Various AI-based algorithms and frameworks of big data with respect to the source of data, techniques used, and the area of application are also discussed. This paper explores the applications of AI and big data analytics for providing insights to the users and enabling them to plan, using the resources especially for the specific challenges in m-health, and proposes a model based on the AI and big data analytics for m-health. Findings of this paper will guide the development of techniques using the combination of AI and the big data as source for handling m-health data more effectively.

Nowadays, Cancer diagnosis is one of the major challenging characteristics for treating cancer. The reality of cancer patients rely on the diagnosis of cancer at the early stages (either in stage 1 or stage 2). If the cancer is diagnosed in stage 3 or later stages means the changes of survival of the patient will become more critical. Normally, single patient records will generate a huge amount of data if the data could be manage and analyze means to solve many problems for identifying the patterns it will leads to diagnose the cancer. Recent work several machine learning algorithms are introduced for the classification of cancer. However still the classification accuracy of machine learning algorithms are reduced because of huge number of samples. So the proposed work introduces a new Hadoop Distributed File System (HDFS) is focused in this work. In this paper, the proposed phenotype techniques are used which handle and classifies the raw EHR (Electronic Health Record) and EMR (Electronic Medical Record). It is based on the HDFS and Two-Phase Map Reduce. Phenotype algorithm uses NLP (National Language Processing) tool which will analyze and classify the cancer patient data like gene mapping, age related data, image and ultrasonic frequency processing, identification and analysis of irregularities, disease and personal histories. In this paper, the three factorized model is used which calculates the mean score values. The values are calculated by disease stage, pain status, etc. This paper focuses big data analytics for cancer diagnosis and the simulation results shows the proposed system produces the highest performance.

To provide a search functionality for encrypted data, public key encryption with keyword search (PEKS) has been widely recognized. In actual usage, a PEKS scheme should be employed with a PKE scheme since PEKS itself does not support the decryption of data. Since a naive composition of a PEKS ciphertext and a PKE ciphertext does not provide CCA security, several attempts have been made to integrate PEKS and PKE in a joint CCA manner (PEKS/PKE for short). In this paper, we further extend these works by integrating secure-channel free PEKS (SCF-PEKS) and PKE, which we call SCF-PEKS/PKE, where no secure channel is required to send trapdoors. We give a formal security definition of SCF-PEKS/PKE in a joint CCA manner, and propose a generic construction of SCF-PEKS/PKE based on anonymous identity-based encryption, tag-based encryption, and one-time signature. We also strengthen the current consistency definition according to the secure-channel free property, and show that our construction is strongly consistent if the underlying IBE provides unrestricted strong collision-freeness which is defined in this paper. We also show that such an IBE scheme can be constructed by employing the Abdalla et al. transformations (TCC 2010/J. Cryptology 2018). Finally, as an application of SCF-PEKS/PKE, we strengthen the security of encrypted Electronic Medical Record (EMR) system proposed by Guo and Yau (J. Medical Sys. 2015).

In order to improve medical quality, shorten hospital stays, and reduce redundant treatment, an optimization of diagnosis and treatment of chronic diseases based on association analysis under the background of regional integration in the paper was proposed, which was to expand the scope of application of the clinical pathway standard diagnosis and treatment program in the context of regional medical integration and mass medical data, so that it had a larger group of patients within the region. In the context of regional medical integration, owing to the types of medical data were diverse, the preprocessing requirements and process specifications for diagnosis and treatment data were firstly proposed. At the stage of diagnosis and treatment unit optimization, the correlation between clinical behaviors was analyzed by using association rules of the FP-growth and Apriori algorithm. Through the optimization and combination of diagnosis and treatment units, the optimized clinical pathway was finally achieved. Experiments showed that after the optimization strategy by the paper proposed, the clinical path diagnosis and treatment achieved obvious improvement in medical quality under the condition that the medical cost was basically flat.

Summary Objective: To summarize recent research and present a selection of the best papers published in 2015 in the field of clinical Natural Language Processing (NLP). Method: A systematic review of the literature was performed by the two section editors of the IMIA Yearbook NLP section by searching bibliographic databases with a focus on NLP efforts applied to clinical texts or aimed at a clinical outcome. Section editors first selected a shortlist of candidate best papers that were then peer-reviewed by independent external reviewers. Results: The clinical NLP best paper selection shows that clinical NLP is making use of a variety of texts of clinical interest to contribute to the analysis of clinical information and the building of a body of clinical knowledge. The full review process highlighted five papers analyzing patient-authored texts or seeking to connect and aggregate multiple sources of information. They provide a contribution to the development of methods, resources, applications, and sometimes a combination of these aspects. Conclusions: The field of clinical NLP continues to thrive through the contributions of both NLP researchers and healthcare professionals interested in applying NLP techniques to impact clinical practice. Foundational progress in the field makes it possible to leverage a larger variety of texts of clinical interest for healthcare purposes.

Display Omitted ODM is used in study design, setup, execution, analysis, submissions, and archival.Much of ODM the literature addresses integrating EHR and clinical research data.ODM has been used as much as a study metadata standard as it has for data exchange.ODM's simplicity and readability have contributed to its success.Future ODM success may depend on improved links to external standards and semantics. IntroductionIn order to further advance research and development on the Clinical Data Interchange Standards Consortium (CDISC) Operational Data Model (ODM) standard, the existing research must be well understood. This paper presents a methodological review of the ODM literature. Specifically, it develops a classification schema to categorize the ODM literature according to how the standard has been applied within the clinical research data lifecycle. This paper suggests areas for future research and development that address ODM's limitations and capitalize on its strengths to support new trends in clinical research informatics. MethodsA systematic scan of the following databases was performed: (1) ABI/Inform, (2) ACM Digital, (3) AIS eLibrary, (4) Europe Central PubMed, (5) Google Scholar, (5) IEEE Xplore, (7) PubMed, and (8) ScienceDirect. A Web of Science citation analysis was also performed. The search term used on all databases was "CDISC ODM." The two primary inclusion criteria were: (1) the research must examine the use of ODM as an information system solution component, or (2) the research must critically evaluate ODM against a stated solution usage scenario. Out of 2686 articles identified, 266 were included in a title level review, resulting in 183 articles. An abstract review followed, resulting in 121 remaining articles; and after a full text scan 69 articles met the inclusion criteria. ResultsAs the demand for interoperability has increased, ODM has shown remarkable flexibility and has been extended to cover a broad range of data and metadata requirements that reach well beyond ODM's original use cases. This flexibility has yielded research literature that covers a diverse array of topic areas. A classification schema reflecting the use of ODM within the clinical research data lifecycle was created to provide a categorized and consolidated view of the ODM literature. The elements of the framework include: (1) EDC (Electronic Data Capture) and EHR (Electronic Health Record) infrastructure; (2) planning; (3) data collection; (4) data tabulations and analysis; and (5) study archival. The analysis reviews the strengths and limitations of ODM as a solution component within each section of the classification schema. This paper also identifies opportunities for future ODM research and development, including improved mechanisms for semantic alignment with external terminologies, better representation of the CDISC standards used end-to-end across the clinical research data lifecycle, improved support for real-time data exchange, the use of EHRs for research, and the inclusion of a complete study design. ConclusionsODM is being used in ways not originally anticipated, and covers a diverse array of use cases across the clinical research data lifecycle. ODM has been used as much as a study metadata standard as it has for data exchange. A significant portion of the literature addresses integrating EHR and clinical research data. The simplicity and readability of ODM has likely contributed to its success and broad implementation as a data and metadata standard. Keeping the core ODM model focused on the most fundamental use cases, while using extensions to handle edge cases, has kept the standard easy for developers to learn and use.

Background and Objective The quality of data is crucial for clinical registry studies as it impacts credibility. In the regular practice of most such studies, a vulnerability arises from researchers recording data on paper-based case report forms (CRFs) and further transcribing them onto registry databases. To ensure the quality of data, verifying data in the registry is necessary. However, traditional manual data verification methods are time-consuming, labor-intensive and of limited-effect. As paper-based CRFs and electronic medical records (EMRs) are two sources for verification, we propose an automated data verification approach based on the techniques of optical character recognition (OCR) and information retrieval to identify data errors in a registry more efficiently. Methods Three steps are involved to develop the automated verification approach. First, we analyze the scanned images of paper-based CRFs with machine learning enhanced OCR to recognize the checkbox marks and hand-writing. Then, we retrieve the related patient information from the EMRs using natural language processing (NLP) techniques. Finally, we compare the retrieved information in the previous two steps with the data in the registry, and synthesize the results accordingly. The proposed automated method has been applied in a Chinese registry study and the difference between automated and manual approach has been evaluated. Results The automated approach has been implemented in The Chinese Coronary Artery Disease Registry. For CRF data recognition, the accuracy of recognition for checkboxes marks and hand-writing are 0.93 and 0.74, respectively. For EMR data extraction, the accuracy of information retrieval from textual electronic medical records is 0.97. The accuracy, recall and time consumption of the automated approach are 0.93, 0.96 and 0.5 h, better than the corresponding values of the manual approach, which are 0.92, 0.71 and 7.5 h. Conclusions Compared to the manual data verification approach, the automated approach enhances the recall of identify data errors and has a higher accuracy. The time consumed is far less. The results show that the automated approach is more effective and efficient for identifying incomplete data and incorrect data in a registry. The proposed approach has potential to improve the quality of registry data.

This paper introduces Lynx, an intelligent system for personal safety at home environments, oriented to elderly people living independently, which encompasses a decision support machine for automatic home risk prevention, tested in real-life environments to respond to real time situations. The automatic system described in this paper prevents such risks by an advanced analytic methods supported by an expert knowledge system. It is minimally intrusive, using plug-and-play sensors and machine learning algorithms to learn the elder’s daily activity taking into account even his health records. If the system detects that something unusual happens (in a wide sense) or if something is wrong relative to the user’s health habits or medical recommendations, it sends at real-time alarm to the family, care center, or medical agents, without human intervention. The system feeds on information from sensors deployed in the home and knowledge of subject physical activities, which can be collected by mobile applications and enriched by personalized health information from clinical reports encoded in the system. The system usability and reliability have been tested in real-life conditions, with an accuracy larger than 81%.

As datasets grow and analytic algorithms become more complex, the typical workflow of analysts launching an analytic, waiting for it to complete, inspecting the results, and then re-Iaunching the computation with adjusted parameters is not realistic for many real-world tasks. This paper presents an alternative workflow, progressive visual analytics, which enables an analyst to inspect partial results of an algorithm as they become available and interact with the algorithm to prioritize subspaces of interest. Progressive visual analytics depends on adapting analytical algorithms to produce meaningful partial results and enable analyst intervention without sacrificing computational speed. The paradigm also depends on adapting information visualization techniques to incorporate the constantly refining results without overwhelming analysts and provide interactions to support an analyst directing the analytic. The contributions of this paper include: a description of the progressive visual analytics paradigm; design goals for both the algorithms and visualizations in progressive visual analytics systems; an example progressive visual analytics system (Progressive Insights) for analyzing common patterns in a collection of event sequences; and an evaluation of Progressive Insights and the progressive visual analytics paradigm by clinical researchers analyzing electronic medical records.

Objective In this paper, we focus on three aspects: (1) to annotate a set of standard corpus in Chinese discharge summaries; (2) to perform word segmentation and named entity recognition in the above corpus; (3) to build a joint model that performs word segmentation and named entity recognition. Design Two independent systems of word segmentation and named entity recognition were built based on conditional random field models. In the field of natural language processing, while most approaches use a single model to predict outputs, many works have proved that performance of many tasks can be improved by exploiting combined techniques. Therefore, in this paper, we proposed a joint model using dual decomposition to perform both the two tasks in order to exploit correlations between the two tasks. Three sets of features were designed to demonstrate the advantage of the joint model we proposed, compared with independent models, incremental models and a joint model trained on combined labels. Measurements Micro-averaged precision (P), recall (R), and F-measure (F) were used to evaluate results. Results The gold standard corpus is created using 336 Chinese discharge summaries of 71 355 words. The framework using dual decomposition achieved 0.2% improvement for segmentation and 1% improvement for recognition, compared with each of the two tasks alone. Conclusions The joint model is efficient and effective in both segmentation and recognition compared with the two individual tasks. The model achieved encouraging results, demonstrating the feasibility of the two tasks.

This paper addresses an information-extraction problem that aims to identify semantic relations among medical concepts (problems, tests, and treatments) in clinical text. The objectives of the paper are twofold. First, we extend an earlier one-page description (appearing as a part of [5]) of a top-ranked model in the 2010 I2B2 NLP Challenge to a necessary level of details, with the belief that feature design is the most crucial factor to the success of our system and hence deserves a more detailed discussion. We present a precise quantification of the contributions of a wide variety of knowledge sources. In addition, we show the end-to-end results obtained on the noisy output of a top-ranked concept detector, which could help construct a more complete view of the state of the art in the real-world scenario. As the second major objective, we reformulate our models into a composite-kernel framework and present the best result, according to our knowledge, on the same dataset.

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.

Summary Objective: To summarize recent research and to propose a selection of best papers published in 2014 in the field of Clinical Information Systems (CIS).Method: A query with search terms from the Medical Subject Headings (MeSH) catalog as well as additional free text search terms was designed to identify relevant publications in the field of clinical information systems from PubMed and Web of Science®. The retrieved articles were then categorized in a multi-pass review carried out separately by the section editors. The final selection of 15 candidate papers was then peer-reviewed by Yearbook editors and external reviewers. Based on the review results the four best papers were then selected at the best papers selection meeting with the IMIA Yearbook editorial board. Results: The query was carried out in mid-January 2015, yielding a combined result set of 1525 articles which were published in 722 different journals. Among these articles two main thematic sections were identified: i) Interoperability from a syntactical and semantic point of view as well as from a long-term preservation and organizational/legal point of view and ii) secondary use of existing health data in all its shades. Here, patient safety was a major scope of application. Conclusions: CIS have become mature over the last years. The focus has now moved beyond data acquisition for just supporting the local care workflows. Actual research efforts in the CIS domain comprise the breakdown of information silos, the reduction of barriers between different systems of different care providers and secondary use of accumulated health data for multiple purposes.

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.

High-risk prediction of cardiovascular disease is of great significance and impendency in medical fields with the increasing phenomenon of sub-health these years. Most existing pathological methods for the prognosis prediction are either costly or prone to misjudgement. Therefore, plenty of automated models based on machine learning have been proposed to predict the onset of cardiovascular disease with the premorbid information of patients extracted from their historical Electronic Health Records (EHRs). However, it is a tough job to select proper features from longitudinal and heterogeneous EHRs, and also a great challenge to obtain accurate and robust representations for patients. In this paper, we propose an entirely end-to-end model called DeepRisk based on attention mechanism and deep neural networks, which can not only learn high-quality features automatically from EHRs, but also efficiently integrate heterogeneous and time-ordered medical data, and finally predict patients' risk of cardiovascular diseases. Experiments are carried out on a real medical dataset and results show that DeepRisk can significantly improve the high-risk prediction accuracy for cardiovascular disease compared with state-of-the-art approaches.

At present, human health is threatened by many diseases, and lung cancer is one of the most dangerous tumors that threaten human life. In most developing countries, due to the large population and lack of medical resources, it is difficult for doctors to meet patients’ needs for medical treatment only by relying on the manual diagnosis. Based on massive medical information, the intelligent decision-making system has played a great role in assisting doctors in analyzing patients’ conditions, improving the accuracy of clinical diagnosis, and reducing the workload of medical staff. This article is based on the data of 8,920 nonsmall cell lung cancer patients collected by different medical systems in three hospitals in China. Based on the intelligent medical system, on the basis of the intelligent medical system, this paper constructs a nonsmall cell lung cancer staging auxiliary diagnosis model based on convolutional neural network (CNNSAD). CNNSAD converts patient medical records into word sequences, uses convolutional neural networks to extract semantic features from patient medical records, and combines dynamic sampling and transfer learning technology to construct a balanced data set. The experimental results show that the model is superior to other methods in terms of accuracy, recall, and precision. When the number of samples reaches 3000, the accuracy of the system will reach over 80%, which can effectively realize the auxiliary diagnosis of nonsmall cell lung cancer and combine dynamic sampling and migration learning techniques to train nonsmall cell lung cancer staging auxiliary diagnosis models, which can effectively achieve the auxiliary diagnosis of nonsmall cell lung cancer. The simulation results show that the model is better than the other methods in the experiment in terms of accuracy, recall, and precision.

With the development of online medical service platform, patients can find more medical information resources and obtain better medical treatment. However, it is difficult for patients to discover the most suitable doctors from the complex information resources. Therefore, the analysis and mining of Electronic Health Record(EHR) is very important for patients' timely and accurate treatment. Discovering the most suitable doctor is actually predicting the exact performance of the doctor for a specific disease. We believe that "a curative/bad treatment is likely to be caused by a good/bad doctor, and a good/bad doctor has a higher/lower evaluation by the patient(s)". In this paper, we propose a novel approach named SeekDoc, which is to seek the most effective doctor for a specific disease. Specifically, we build a doctor-disease heterogeneous information network and collect patients reviews and rating records for doctors. Then, we embed the comprehensive comment data for doctors and the constructed heterogeneous information network. Next, we use the autoencoder mechanism to learn the embedded features, which is an effective learning algorithm for constructing the latent feature representation in an unsupervised manner. After this learning, the latent features are input into the extreme gradient boosting (XGBoost) algorithm to improve their detection capabilities. Finally, extensive experiments show that our method can effectively and efficiently predict the doctor's experience score for specific diseases and has good performance compared with other algorithms.

Electronic health records (EHRs) have become a platform for data-driven granular-level surveillance in recent years. In this paper, we make use of EHRs for early prevention of childhood obesity. The proposed method simultaneously provides smooth disease mapping and outlier information for obesity prevalence, which are useful for raising public awareness and facilitating targeted intervention. More precisely, we consider a penalized multilevel generalized linear model. We decompose regional contribution into smooth and sparse signals, which are automatically identified by a combination of fusion and sparse penalties imposed on the likelihood function. In addition, we weigh the proposed likelihood to account for the missingness and potential non-representativeness arising from the EHR data. We develop a novel alternating minimization algorithm, which is computationally efficient, easy to implement, and guarantees convergence. Simulation studies demonstrate superior performance of the proposed method. Finally, we apply our method to the University of Wisconsin Population Health Information Exchange database. This article is protected by copyright. All rights reserved.

Background Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful. Method In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector. Results Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the “Deep Feature” represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations. Conclusion We propose an effective unsupervised RNN-DAE method to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.

Modern AI-based clinical decision support models owe their success in part to the very large number of predictors they use. Safe and robust decision support, especially for intervention planning, requires causal, not associative, relationships. Traditional methods of causal discovery, clinical trials and extracting biochemical pathways, are resource intensive and may not scale up to the number and complexity of relationships sufficient for precision treatment planning. Computational causal structure discovery (CSD) from electronic health records (EHR) data can represent a solution, however, current CSD methods fall short on EHR data. This paper presents a CSD method tailored to the EHR data. The application of the proposed methodology was demonstrated on type-2 diabetes mellitus. A large EHR dataset from Mayo Clinic was used as development cohort, and another large dataset from an independent health system, M Health Fairview, as external validation cohort. The proposed method achieved very high recall (.95) and substantially higher precision than the general-purpose methods (.84 versus .29, and .55). The causal relationships extracted from the development and external validation cohorts had a high (81%) overlap. Due to the adaptations to EHR data, the proposed method is more suitable for use in clinical decision support than the general-purpose methods.

International audience; In the latest years, the healthcare domain has seen an increasing interest in the definition of intelligent systems to support clinicians in their everyday tasks and activities. Among others, also the field of Evidence-Based Medicine is impacted by this twist, with the aim to combine the reasoning frameworks proposed thus far in the field with mining algorithms to extract structured information from clinical trials, clinical guidelines, and Electronic Health Records. In this paper, we go beyond the state of the art by proposing a new end-to-end pipeline to address argumentative outcome analysis on clinical trials. More precisely, our pipeline is composed of (i) an Argument Mining module to extract and classify argumentative components (i.e., evidence and claims of the trial) and their relations (i.e., support, attack), and (ii) an outcome analysis module to identify and classify the effects (i.e., improved, increased, decreased, no difference, no occurrence) of an intervention on the outcome of the trial, based on PICO elements. We annotated a dataset composed of more than 500 abstracts of Randomized Controlled Trials (RCT) from the MEDLINE database, leading to a labeled dataset with 4198 argument components, 2601 argument relations, and 3351 outcomes on five different diseases (i.e., neoplasm, glaucoma, hepatitis, diabetes, hypertension). We experiment with deep bidirectional transformers in combination with different neural architectures (i.e., LSTM, GRU and CRF) and obtain a macro F1-score of .87 for component detection and .68 for relation prediction, outperforming current state-of-the-art end-to-end Argument Mining systems, and a macro F1-score of .80 for outcome classification.

In China, emergency room residents (EMRs) generally face high working intensity. It is particularly important to arrange the working shifts of EMRs in a scientific way to balance their work and rest time. However, in existing studies, most of the scheduling models are based on the individual doctor or nurse as a unit, less considering the actuality of operation and management of emergency department (ED) in large public hospitals in China. Besides, the depiction of the hard and soft constraints of EMR scheduling in China is insufficient. So in order to obtain the scientific and reasonable scheduling shifts, this paper considers various management rules in a hospital, physicians’ personal preferences, and the time requirements of their personal learning and living and takes the minimum deviation variables from the soft constraints as the objective function to construct a mixed integer programming model with the doctor group as the scheduling unit. The analytic hierarchy process (AHP) is used to determine the weights of deviation variables. Then, IBM ILOG CPLEX 12.8 is used to solve the model. The feasibility and effectiveness of the scheduling method are verified by the actual case from West China Hospital of Sichuan University. The scheduling results can meet the EMRs’ flexible work plans and the preferences of the doctor teams for the shifts and rest days. Compared with the current manual scheduling, the proposed method can greatly improve the efficiency and rationality of shift scheduling. In addition, the proposed scheduling method also provides a reference for EMR scheduling in other China’s high-grade large public hospitals.

Background Hospital discharge summaries offer a potentially rich resource to enhance pharmacovigilance efforts to evaluate drug safety in real-world clinical practice. However, it is infeasible for experts to read through all discharge summaries to find cases of drug-adverse event (AE) relations. Purpose The objective of this paper is to develop a natural language processing (NLP) framework to detect drug-AE relations from unstructured hospital discharge summaries. Basic procedures An NLP algorithm was designed using customized dictionaries of drugs, adverse event (AE) terms, and rules based on trigger phrases, negations, fuzzy logic and word distances to recognize drug, AE terms and to detect drug-AE relations. Furthermore, a customized annotation tool was developed to facilitate expert review of discharge summaries from a tertiary hospital in Singapore in 2011. Main findings A total of 33 trial sets with 50 to 100 records per set were evaluated (1620 discharge summaries) by our algorithm and reviewed by pharmacovigilance experts. After every 6 trial sets, drug and AE dictionaries were updated, and rules were modified to improve the system. Excellent performance was achieved for drug and AE entity recognition with over 92% precision and recall. On the final 6 sets of discharge summaries (600 records), our algorithm achieved 75% precision and 59% recall for identification of valid drug-AE relations. Principal conclusions Adverse drug reactions are a significant contributor to health care costs and utilization. Our algorithm is not restricted to particular drugs, drug classes or specific medical specialties, which is an important attribute for a national regulatory authority to carry out comprehensive safety monitoring of drug products. Drug and AE dictionaries may be updated periodically to ensure that the tool remains relevant for performing surveillance activities. The development of the algorithm, and the ease of reviewing and correcting the results of the algorithm as part of an iterative machine learning process, is an important step towards use of hospital discharge summaries for an active pharmacovigilance program.

Background Imaging examinations, such as ultrasonography, magnetic resonance imaging and computed tomography scans, play key roles in healthcare settings. To assess and improve the quality of imaging diagnosis, we need to manually find and compare the pre-existing reports of imaging and pathology examinations which contain overlapping exam body sites from electrical medical records (EMRs). The process of retrieving those reports is time-consuming. In this paper, we propose a convolutional neural network (CNN) based method which can better utilize semantic information contained in report texts to accelerate the retrieving process. Methods We included 16,354 imaging and pathology report-pairs from 1926 patients who admitted to Shanghai Tongren Hospital and had ultrasonic examinations between 1st May 2017 and 31st July 2017. We adapted the CNN model to calculate the similarities among the report-pairs to identify target report-pairs with overlapping body sites, and compared the performance with other six conventional models, including keyword mapping, latent semantic analysis (LSA), latent Dirichlet allocation (LDA), Doc2Vec, Siamese long short term memory (LSTM) and a model based on named entity recognition (NER). We also utilized graph embedding method to enhance the word representation by capturing the semantic relations information from medical ontologies. Additionally, we used LIME algorithm to identify which features (or words) are decisive for the prediction results and improved the model interpretability. Results Experiment results showed that our CNN model gained significant improvement compared to all other conventional models on area under the receiver operating characteristic (AUROC), precision, recall and F1-score in our test dataset. The AUROC of our CNN models gained approximately 3–7% improvement. The AUROC of CNN model with graph-embedding and ontology based medical concept vectors was 0.8% higher than the model with randomly initialized vectors and 1.5% higher than the one with pre-trained word vectors. Conclusion Our study demonstrates that CNN model with pre-trained medical concept vectors could accurately identify target report-pairs with overlapping body sites and potentially accelerate the retrieving process for imaging diagnosis quality measurement.

Launching biomedical innovations based on clinical demands instead of translating basic research findings to practice reduces the risk that the results will not fit the clinical routine. To realize this type of innovation, a meta-analysis of the body of research is necessary to reveal demand-matching concepts. However, both the data deluge and the narrow time constraints for innovation make it impossible to perform such reviews manually. Thus, this paper proposes a specifically adapted “Potential Technologies Review” approach focusing on automated text mining and information retrieval techniques. The novel framework combines features from both systematic and scoping reviews. It aims at high coverage and reproducibility while mapping technologies-even with a fuzzy initial scope. To achieve these goals for search and triage, a set of closely interrelated methods has been developed: (a) automated query optimization, (b) screening prioritization, and (c) recall estimation. To determine appropriate parameters, a variety of published literature corpora were used and compared with an evaluation on a real-world dataset. Our results show that it is feasible to automate the identification of relevant works using this newly introduced framework. It achieved a workload reduction of up to 91% “Work-saved-over Sampling (WSS)” with a 76% overall recall compared with manually screening search results. Reducing the workload is a prerequisite for a rapid Potential Technologies Review when conducting demand-pull innovations. Moreover, it facilitates the updating and closer monitoring of latest findings. Studying the robustness of the framework and expanding it to patent documents are future tasks.

Background Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM. Methods A two-step model is applied in our study. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. There are two data sets used in the experiments. One is a plain text data set indexed by medical experts. The other is a structured dataset on primary hypertension. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. Two conventional shallow models (support vector machine / SVM and decision tree / DT) are applied as the comparisons to show the superiority of our proposed approach. Results The deep learning (DBN + SVM) model outperforms simple SVM and DT on two data sets in terms of all the evaluation measures, which confirms our motivation that the deep model is good at capturing the key features with less dependence when the index is built up by manpower. Conclusions Our study shows the two-step deep learning model achieves high performance for medical information retrieval over the conventional shallow models. It is able to capture the features of both plain text and the highly-structured database of EMR data. The performance of the deep model is superior to the conventional shallow learning models such as SVM and DT. It is an appropriate knowledge-learning model for information retrieval of EMR system. Therefore, deep learning provides a good solution to improve the performance of CAMDM systems.

Background Diabetes has become one of the hot topics in life science researches. To support the analytical procedures, researchers and analysts expend a mass of labor cost to collect experimental data, which is also error-prone. To reduce the cost and to ensure the data quality, there is a growing trend of extracting clinical events in form of knowledge from electronic medical records (EMRs). To do so, we first need a high-coverage knowledge base (KB) of a specific disease to support the above extraction tasks called KB-based Extraction. Methods We propose an approach to build a diabetes-centric knowledge base (a.k.a. DKB) via mining the Web. In particular, we first extract knowledge from semi-structured contents of vertical portals, fuse individual knowledge from each site, and further map them to a unified KB. The target DKB is then extracted from the overall KB based on a distance-based Expectation-Maximization (EM) algorithm. Results During the experiments, we selected eight popular vertical portals in China as data sources to construct DKB. There are 7703 instances and 96,041 edges in the final diabetes KB covering diseases, symptoms, western medicines, traditional Chinese medicines, examinations, departments, and body structures. The accuracy of DKB is 95.91%. Besides the quality assessment of extracted knowledge from vertical portals, we also carried out detailed experiments for evaluating the knowledge fusion performance as well as the convergence of the distance-based EM algorithm with positive results. Conclusions In this paper, we introduced an approach to constructing DKB. A knowledge extraction and fusion pipeline was first used to extract semi-structured data from vertical portals and individual KBs were further fused into a unified knowledge base. After that, we develop a distance based Expectation Maximization algorithm to extract a subset from the overall knowledge base forming the target DKB. Experiments showed that the data in DKB are rich and of high-quality.

Analyzing patients' health data using machine learning techniques can improve both patient outcomes and hospital operations. However, heterogeneous patient data (e.g., vital signs) and inefficient feature learning methods affect the implementation of machine learning-based patient data analysis. In this paper, we present a novel unsupervised deep learning-based feature learning (DFL) framework to automatically learn compact representations from patient health data for efficient clinical decision making. Real-world pneumonia patient data from the National University Hospital in Singapore are collected and analyzed to evaluate the performance of DFL. Furthermore, publicly available electroencephalogram data are extracted from the UCI Machine Learning Repository to test and support our findings. Using both data sets, we compare the performance of DFL to that of several popular feature learning methods and demonstrate its advantages.

With increased use of electronic medical records (EMRs), data mining on medical data has great potential to improve the quality of hospital treatment and increase the survival rate of patients. Early readmission prediction enables early intervention, which is essential to preventing serious or life-threatening events, and act as a substantial contributor to reduce healthcare costs. Existing works on predicting readmission often focus on certain vital signs and diseases by extracting statistical features. They also fail to consider skewness of class labels in medical data and different costs of misclassification errors. In this paper, we recur to the merits of convolutional neural networks (CNN) to automatically learn features from time series of vital sign, and categorical feature embedding to effectively encode feature vectors with heterogeneous clinical features, such as demographics, hospitalization history, vital signs, and laboratory tests. Then, both learnt features via CNN and statistical features via feature embedding are fed into a multilayer perceptron (MLP) for prediction. We use a cost-sensitive formulation to train MLP during prediction to tackle the imbalance and skewness challenge. We validate the proposed approach on two real medical datasets from Barnes-Jewish Hospital, and all data is taken from historical EMR databases and reflects the kinds of data that would realistically be available at the clinical prediction system in hospitals. We find that early prediction of readmission is possible and when compared with state-of-the-art existing methods used by hospitals, our methods perform significantly better. For example, using the general hospital wards data for 30-day readmission prediction, the area under the curve (AUC) for the proposed model was 0.70, significantly higher than all the baseline methods. Based on these results, a system is being deployed in hospital settings with the proposed forecasting algorithms to support treatment.

As digitalization becomes more common, patients’ concerns about the leakage of private information, such as electronic medical record, are increasing, and those concerns motivated this case study of secure covert communication. Therefore, in this paper, a novel reversible data hiding method based on pixel rotation is proposed for medical images. Using pixel rotation, a state mapping model is constructed to represent the payload. More specifically, many intermediate states are derived from an image block, and each of them is used to form a one-to-one mapping relationship with a specific sequence of payload bits. In addition, to ensure the visual quality of stego-medical-images, the payload bits are only concealed in the regular blocks and the other blocks are unchanged. Moreover, the smoother regular image block will be priority to be used to embed the payload to enhance the visual quality of stego-medical-image. The experimental results showed that the stego-medical-images generated by the proposed reversible data hiding method have better visual quality with an average PSNR of 47.0307 dB, which is higher than that provided by some state-of-the-art methods.