Search

Abstract With the progress and development of computer technology, applying machine learning methods to cancer research has become an important research field. To analyze the most recent research status and trends, main research topics, topic evolutions, research collaborations, and potential directions of this research field, this study conducts a bibliometric analysis on 6206 research articles worldwide collected from PubMed between 2011 and 2021 concerning cancer research using machine learning methods. Python is used as a tool for bibliometric analysis, Gephi is used for social network analysis, and the Latent Dirichlet Allocation model is used for topic modeling. The trend analysis of articles not only reflects the innovative research at the intersection of machine learning and cancer but also demonstrates its vigorous development and increasing impacts. In terms of journals, Nature Communications is the most influential journal and Scientific Reports is the most prolific one. The United States and Harvard University have contributed the most to cancer research using machine learning methods. As for the research topic, “Support Vector Machine,” “classification,” and “deep learning” have been the core focuses of the research field. Findings are helpful for scholars and related practitioners to better understand the development status and trends of cancer research using machine learning methods, as well as to have a deeper understanding of research hotspots.

BackgroundCOVID-19–related health inequalities were reported in some studies, showing the failure in public health and communication. Studies investigating the contexts and causes of these inequalities pointed to the contribution of communication inequality or poor health literacy and information access to engagement with health care services. However, no study exclusively dealt with health inequalities induced by the use of social media during COVID-19. ObjectiveThis review aimed to identify and summarize COVID-19–related health inequalities induced by the use of social media and the associated contributing factors and to characterize the relationship between the use of social media and health disparities during the COVID-19 pandemic. MethodsA systematic review was conducted on this topic in light of the protocol of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 statement. Keyword searches were performed to collect papers relevant to this topic in multiple databases: PubMed (which includes MEDLINE [Ovid] and other subdatabases), ProQuest (which includes APA PsycINFO, Biological Science Collection, and others), ACM Digital Library, and Web of Science, without any year restriction. Of the 670 retrieved publications, 10 were initially selected based on the predefined selection criteria. These 10 articles were then subjected to quality analysis before being analyzed in the final synthesis and discussion. ResultsOf the 10 articles, 1 was further removed for not meeting the quality assessment criteria. Finally, 9 articles were found to be eligible and selected for this review. We derived the characteristics of these studies in terms of publication years, journals, study locations, locations of study participants, study design, sample size, participant characteristics, and potential risk of bias, and the main results of these studies in terms of the types of social media, social media use–induced health inequalities, associated factors, and proposed resolutions. On the basis of the thematic synthesis of these extracted data, we derived 4 analytic themes, namely health information inaccessibility–induced health inequalities and proposed resolutions, misinformation-induced health inequalities and proposed resolutions, disproportionate attention to COVID-19 information and proposed resolutions, and higher odds of social media–induced psychological distress and proposed resolutions. ConclusionsThis paper was the first systematic review on this topic. Our findings highlighted the great value of studying the COVID-19–related health knowledge gap, the digital technology–induced unequal distribution of health information, and the resulting health inequalities, thereby providing empirical evidence for understanding the relationship between social media use and health inequalities in the context of COVID-19 and suggesting practical solutions to such disparities. Researchers, social media, health practitioners, and policy makers can draw on these findings to promote health equality while minimizing social media use–induced health inequalities.

Background Persistence of long-term COVID-19 pandemic is putting high pressure on healthcare services worldwide for several years. This article aims to establish models to predict infection levels and mortality of COVID-19 patients in China. Methods Machine learning models and deep learning models have been built based on the clinical features of COVID-19 patients. The best models are selected by area under the receiver operating characteristic curve (AUC) scores to construct two homogeneous ensemble models for predicting infection levels and mortality, respectively. The first-hand clinical data of 760 patients are collected from Zhongnan Hospital of Wuhan University between 3 January and 8 March 2020. We preprocess data with cleaning, imputation, and normalization. Results Our models obtain AUC = 0.7059 and Recall (Weighted avg) = 0.7248 in predicting infection level, while AUC=0.8436 and Recall (Weighted avg) = 0.8486 in predicting mortality ratio. This study also identifies two sets of essential clinical features. One is C-reactive protein (CRP) or high sensitivity C-reactive protein (hs-CRP) and the other is chest tightness, age, and pleural effusion. Conclusions Two homogeneous ensemble models are proposed to predict infection levels and mortality of COVID-19 patients in China. New findings of clinical features for benefiting the machine learning models are reported. The evaluation of an actual dataset collected from January 3 to March 8, 2020 demonstrates the effectiveness of the models by comparing them with state-of-the-art models in prediction.

Abstract 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.

BackgroundThe usability of mobile health (mHealth) apps needs to be effectively evaluated before they are officially approved to be used to deliver health interventions. To this end, the mHealth App Usability Questionnaire (MAUQ) has been designed and proved valid and reliable in assessing the usability of mHealth apps. However, this English questionnaire needs to be translated into other languages, adapted, and validated before being utilized to evaluate the usability of mHealth apps. ObjectiveThis study aims to improve, further adapt, and validate the Chinese version of the MAUQ (C-MAUQ; interactive for patients) on Left-handed Doctor, one of the most popular “reaching out to patients” interactive mHealth apps with chatbot function in China, to test the reliability and cross-cultural adaptability of the questionnaire. MethodsThe MAUQ (interactive for patients) has been translated into Chinese and validated for its reliability on Good Doctor, one of the most influential “reaching out to patients” mHealth apps without chatbot function in China. After asking for the researchers’ approval to use this Chinese version, we adjusted and further adapted the C-MAUQ by checking it against the original English version and improving its comprehensibility, readability, idiomaticity, and cross-cultural adaptability. Following a trial survey completed by 50 respondents on wenjuanxing, the most popular online questionnaire platform in China, the improved version of the C-MAUQ (I-C-MAUQ) was finally used to evaluate the usability of Left-handed Doctor through an online questionnaire survey (answered by 322 participants) on wenjuanxing, to test its internal consistency, reliability, and validity. ResultsThe I-C-MAUQ still retained the 21 items and 3 dimensions of the original MAUQ: 8 items for usability and satisfaction, 6 items for system information arrangement, and 7 items for efficiency. The translation problems in the C-MAUQ, including (1) redundancy, (2) incompleteness, (3) misuse of parts of speech, (4) choice of inappropriate words, (5) incomprehensibility, and (6) cultural difference–induced improper translation, were improved. As shown in the analysis of data obtained through the online survey, the I-C-MAUQ had a better internal consistency (ie, the correlation coefficient between the score of each item and the total score of the questionnaire determined within the range of 0.861-0.938; P

BackgroundGiven the growing significance of conversational agents (CAs), researchers have conducted a plethora of relevant studies on various technology- and usability-oriented issues. However, few investigations focus on language use in CA-based health communication to examine its influence on the user perception of CAs and their role in delivering health care services. ObjectiveThis review aims to present the language use of CAs in health care to identify the achievements made and breakthroughs to be realized to inform researchers and more specifically CA designers. MethodsThis review was conducted by following the protocols of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 statement. We first designed the search strategy according to the research aim and then performed the keyword searches in PubMed and ProQuest databases for retrieving relevant publications (n=179). Subsequently, 3 researchers screened and reviewed the publications independently to select studies meeting the predefined selection criteria. Finally, we synthesized and analyzed the eligible articles (N=11) through thematic synthesis. ResultsAmong the 11 included publications, 6 deal exclusively with the language use of the CAs studied, and the remaining 5 are only partly related to this topic. The language use of the CAs in these studies can be roughly classified into six themes: (1) personal pronouns, (2) responses to health and lifestyle prompts, (3) strategic wording and rich linguistic resources, (4) a 3-staged conversation framework, (5) human-like well-manipulated conversations, and (6) symbols and images coupled with phrases. These derived themes effectively engaged users in health communication. Meanwhile, we identified substantial room for improvement based on the inconsistent responses of some CAs and their inability to present large volumes of information on safety-critical health and lifestyle prompts. ConclusionsThis is the first systematic review of language use in CA-based health communication. The results and limitations identified in the 11 included papers can give fresh insights into the design and development, popularization, and research of CA applications. This review can provide practical implications for incorporating positive language use into the design of health CAs and improving their effective language output in health communication. In this way, upgraded CAs will be more capable of handling various health problems particularly in the context of nationwide and even worldwide public health crises.

BackgroundLong before the outbreak of COVID-19, chatbots had been playing an increasingly crucial role and gaining growing popularity in health care. In the current omicron waves of this pandemic when the most resilient health care systems at the time are increasingly being overburdened, these conversational agents (CA) are being resorted to as preferred alternatives for health care information. For many people, especially adolescents and the middle-aged, mobile phones are the most favored source of information. As a result of this, it is more important than ever to investigate the user experience of and satisfaction with chatbots on mobile phones. ObjectiveThe objective of this study was twofold: (1) Informed by Deneche and Warren’s evaluation framework, Zhu et al’s measures of variables, and the theory of consumption values (TCV), we designed a new assessment model for evaluating the user experience of and satisfaction with chatbots on mobile phones, and (2) we aimed to validate the newly developed model and use it to gain an understanding of the user experience of and satisfaction with popular health care chatbots that are available for use by young people aged 17-35 years in southeast China in self-diagnosis and for acquiring information about COVID-19 and virus variants that are currently spreading. MethodsFirst, to assess user experience and satisfaction, we established an assessment model based on relevant literature and TCV. Second, the chatbots were prescreened and selected for investigation. Subsequently, 413 informants were recruited from Nantong University, China. This was followed by a questionnaire survey soliciting the participants’ experience of and satisfaction with the selected health care chatbots via wenjuanxing, an online questionnaire survey platform. Finally, quantitative and qualitative analyses were conducted to find the informants’ perception. ResultsThe data collected were highly reliable (Cronbach α=.986) and valid: communalities=0.632-0.823, Kaiser-Meyer-Olkin (KMO)=0.980, and percentage of cumulative variance (rotated)=75.257% (P

BackgroundOver 30% of university students from 8 countries were afflicted with mental distress according to a World Health Organization survey. Undergraduate students in increasing numbers in China have also been reported to suffer from different mental problems. Various psychological distresses significantly impact their academic and daily life, thereby causing role impairments and unsatisfactory academic achievements. While the prevalence of, diverse underlying factors for, and interventions of social support in college students’ mental health have extensively been investigated in China, there is no study exclusively focusing on the impact of interventions on their psychological well-being. ObjectiveThe aim of this review was to identify and synthesize the interventions in the mental health concerns of Chinese undergraduate students studying in China reported in the literature to inform educational authorities, college and university management, students’ affairs counselors, and mental health providers. MethodsWe performed a systematic review and reported the research findings of previous studies according to the protocol of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 statement. First, based on the predefined search strategy, keyword searches were performed in the PubMed and ProQuest databases to retrieve relevant studies. Subsequently, we screened the candidate articles based on predefined inclusion and exclusion criteria. Finally, we analyzed the included papers for qualitative synthesis. ResultsWe retrieved a total of 675 studies from the PubMed and ProQuest databases using the search strategy on March 15, 2022. Among these candidate studies, 15 that were not written in English, 76 duplicates, and 149 studies of other document types were removed before screening. An additional 313 studies were excluded in the screening process, with 73 articles ruled out for being not relevant to interventions, not related to mental health, or not focused on undergraduate students in the full-text review. As a result, 49 papers were eligible and included in this systematic review. In the qualitative synthesis, we divided the interventions reported in the selected studies into two categories: (1) social support from government authorities, university authorities, students’ affairs counselors and teachers, family members, health care authorities and professionals, and the media (various online platforms), and (2) various coping strategies adopted by undergraduate students themselves. We identified further research on mental health interventions that may be delivered by digital medical platforms, conversational agents (eg, chatbots), and researchers. ConclusionsThis was the first systematic review of interventions to address the mental health concerns of Chinese undergraduate students studying in China. The categorization of reported interventions and the identification of new intervention channels can effectively inform stakeholders. Interventions for undergraduate students’ mental health is a research topic worth further investigation.

Abstract Background With China experiencing unprecedented economic development and social change over the past three decades, Chinese policy makers and health care professionals have come to view mental health as an important outcome to monitor. Our study conducted an epidemiological study of psychosis in Guangdong province, with 20 million real-world follow-up records in the last decade. Methods Data was collected from Guangdong mental health information platform from 2010 to 2019, which had standardized disease registration and follow-up management for nearly 600,000 patients with six categories of mental diseases and 400,000 patients with schizophrenia. We conducted clinical staging for the disease course of the patients and divided the data with various factors into different stages of disease. Quantitative analysis was utilized to investigate the high relevant indicators to the disease. The results were projected on geography map for regional distribution analysis. Results The majority cases of mental disease incidence were between the age of 15 and 29, while the peak age for both male and female was between 20 to 24 years old. The disease course with the largest number of patients’ cases was between 5 to 10 years. The therapeutic effect of patients gradually decreased with the development of disease course, while the risk increased with the disease course. The analysis of influencing factors showed that poor economic conditions incurred higher risk scores, and good medication adherence was effective in improving treatment outcomes. In addition, receiving good education contributed to the reduction of the risk of schizophrenia and the improvement of the efficiency of early treatment. Through the analysis of regional distribution of schizophrenia disease, developed economic conditions and favorable resource conditions could promote the reduction of disease risk, while in economically backward regions, it often accompanied with lower therapeutic effect and higher disease risk. Conclusions Certain demographic factors had a relatively prominent impact on the therapeutic effect and risk of schizophrenia, such as high-quality medication adherence. Therapeutic effect and risk were highly correlated. Backward economic conditions often associated with poor efficacy and higher risk assessment, and the developed economy and better medical resource are beneficial for the treatment of psychotic.

With the rapid growth of information technology, the necessity for processing substantial amounts of health data using advanced information technologies is increasing. A large amount of valuable data exists in natural text such as diagnosis text, discharge summaries, online health discussions, and eligibility criteria of clinical trials. Health natural language processing, as an interdisciplinary field of natural language processing and health care, plays a substantial role in a wide scope of both methodology development and applications. This editorial shares the most recent methodology innovations of health natural language processing and applications in the medical domain published in this JMIR Medical Informatics special theme issue entitled "Health Natural Language Processing: Methodology Development and Applications".

BackgroundThere is an increasing body of research on the development of machine learning algorithms in the evaluation of online health educational resources for specific readerships. Machine learning algorithms are known for their lack of interpretability compared with statistics. Given their high predictive precision, improving the interpretability of these algorithms can help increase their applicability and replicability in health educational research and applied linguistics, as well as in the development and review of new health education resources for effective and accessible health education. ObjectiveOur study aimed to develop a linguistically enriched machine learning model to predict binary outcomes of online English health educational resources in terms of their easiness and complexity for international tertiary students. MethodsLogistic regression emerged as the best performing algorithm compared with support vector machine (SVM) (linear), SVM (radial basis function), random forest, and extreme gradient boosting on the transformed data set using L2 normalization. We applied recursive feature elimination with SVM to perform automatic feature selection. The automatically selected features (n=67) were then further streamlined through expert review. The finalized feature set of 22 semantic features achieved a similar area under the curve, sensitivity, specificity, and accuracy compared with the initial (n=115) and automatically selected feature sets (n=67). Logistic regression with the linguistically enhanced feature set (n=22) exhibited important stability and robustness on the training data of different sizes (20%, 40%, 60%, and 80%), and showed consistently high performance when compared with the other 4 algorithms (SVM [linear], SVM [radial basis function], random forest, and extreme gradient boosting). ResultsWe identified semantic features (with positive regression coefficients) contributing to the prediction of easy-to-understand online health texts and semantic features (with negative regression coefficients) contributing to the prediction of hard-to-understand health materials for readers with nonnative English backgrounds. Language complexity was explained by lexical difficulty (rarity and medical terminology), verbs typical of medical discourse, and syntactic complexity. Language easiness of online health materials was associated with features such as common speech act verbs, personal pronouns, and familiar reasoning verbs. Successive permutation of features illustrated the interaction between these features and their impact on key performance indicators of the machine learning algorithms. ConclusionsThe new logistic regression model developed exhibited consistency, scalability, and, more importantly, interpretability based on existing health and linguistic research. It was found that low and high linguistic accessibilities of online health materials were explained by 2 sets of distinct semantic features. This revealed the inherent complexity of effective health communication beyond current readability analyses, which were limited to syntactic complexity and lexical difficulty.

Background: Due to its convenience, wide availability, low usage cost, neural machine translation (NMT) has increasing applications in diverse clinical settings and web-based self-diagnosis of diseases. Given the developing nature of NMT tools, this can pose safety risks to multicultural communities with limited bilingual skills, low education, and low health literacy. Research is needed to scrutinise the reliability, credibility, usability of automatically translated patient health information.Objective: We aimed to develop high-performing Bayesian machine learning classifiers to assist clinical professionals and healthcare workers in assessing the quality and usability of NMT on depressive disorders. The tool did not require any prior knowledge from frontline health and medical professionals of the target language used by patients.Methods: We used Relevance Vector Machine (RVM) to increase generalisability and clinical interpretability of classifiers. It is a typical sparse Bayesian classifier less prone to overfitting with small training datasets. We optimised RVM by leveraging automatic recursive feature elimination and expert feature refinement from the perspective of health linguistics. We evaluated the diagnostic utility of the Bayesian classifier under different probability cut-offs in terms of sensitivity, specificity, positive and negative likelihood ratios against clinical thresholds for diagnostic tests. Finally, we illustrated interpretation of RVM tool in clinic using Bayes' nomogram.Results: After automatic and expert-based feature optimisation, the best-performing RVM classifier (RVM_DUFS12) gained the highest AUC (0.8872) among 52 competing models with distinct optimised, normalised features sets. It also had statistically higher sensitivity and specificity compared to other models. We evaluated the diagnostic utility of the best-performing model using Bayes' nomogram: it had a positive likelihood ratio (LR+) of 4.62 (95% C.I.: 2.53, 8.43), and the associated posterior probability (odds) was 83% (5.0) (95% C.I.: 73%, 90%), meaning that approximately 10 in 12 English texts with positive test are likely to contain information that would cause clinically significant conceptual errors if translated by Google; it had a negative likelihood ratio (LR-) of 0.18 (95% C.I.: 0.10,0.35) and associated posterior probability (odds) was 16% (0.2) (95% C.I: 10%, 27%), meaning that about 10 in 12 English texts with negative test can be safely translated using Google.

BackgroundCurrent health information understandability research uses medical readability formulas to assess the cognitive difficulty of health education resources. This is based on an implicit assumption that medical domain knowledge represented by uncommon words or jargon form the sole barriers to health information access among the public. Our study challenged this by showing that, for readers from non-English speaking backgrounds with higher education attainment, semantic features of English health texts that underpin the knowledge structure of English health texts, rather than medical jargon, can explain the cognitive accessibility of health materials among readers with better understanding of English health terms yet limited exposure to English-based health education environments and traditions. ObjectiveOur study explores multidimensional semantic features for developing machine learning algorithms to predict the perceived level of cognitive accessibility of English health materials on health risks and diseases for young adults enrolled in Australian tertiary institutes. We compared algorithms to evaluate the cognitive accessibility of health information for nonnative English speakers with advanced education levels yet limited exposure to English health education environments. MethodsWe used 113 semantic features to measure the content complexity and accessibility of original English resources. Using 1000 English health texts collected from Australian and international health organization websites rated by overseas tertiary students, we compared machine learning (decision tree, support vector machine [SVM], ensemble tree, and logistic regression) after hyperparameter optimization (grid search for the best hyperparameter combination of minimal classification errors). We applied 5-fold cross-validation on the whole data set for the model training and testing, and calculated the area under the operating characteristic curve (AUC), sensitivity, specificity, and accuracy as the measurement of the model performance. ResultsWe developed and compared 4 machine learning algorithms using multidimensional semantic features as predictors. The results showed that ensemble classifier (LogitBoost) outperformed in terms of AUC (0.858), sensitivity (0.787), specificity (0.813), and accuracy (0.802). Support vector machine (AUC 0.848, sensitivity 0.783, specificity 0.791, and accuracy 0.786) and decision tree (AUC 0.754, sensitivity 0.7174, specificity 0.7424, and accuracy 0.732) followed. Ensemble classifier (LogitBoost), support vector machine, and decision tree achieved statistically significant improvement over logistic regression in AUC, sensitivity, specificity, and accuracy. Support vector machine reached statistically significant improvement over decision tree in AUC and accuracy. As the best performing algorithm, ensemble classifier (LogitBoost) reached statistically significant improvement over decision tree in AUC, sensitivity, specificity, and accuracy. ConclusionsOur study shows that cognitive accessibility of English health texts is not limited to word length and sentence length as had been conventionally measured by medical readability formulas. We compared machine learning algorithms based on semantic features to explore the cognitive accessibility of health information for nonnative English speakers. The results showed the new models reached statistically increased AUC, sensitivity, and accuracy to predict health resource accessibility for the target readership. Our study illustrated that semantic features such as cognitive ability–related semantic features, communicative actions and processes, power relationships in health care settings, and lexical familiarity and diversity of health texts are large contributors to the comprehension of health information; for readers such as international students, semantic features of health texts outweigh syntax and domain knowledge.

BackgroundMedical writing styles can have an impact on the understandability of health educational resources. Amid current web-based health information research, there is a dearth of research-based evidence that demonstrates what constitutes the best practice of the development of web-based health resources on children’s health promotion and education. ObjectiveUsing authoritative and highly influential web-based children’s health educational resources from the Nemours Foundation, the largest not-for-profit organization promoting children’s health and well-being, we aimed to develop machine learning algorithms to discriminate and predict the writing styles of health educational resources on children versus adult health promotion using a variety of health educational resources aimed at the general public. MethodsThe selection of natural language features as predicator variables of algorithms went through initial automatic feature selection using ridge classifier, support vector machine, extreme gradient boost tree, and recursive feature elimination followed by revision by education experts. We compared algorithms using the automatically selected (n=19) and linguistically enhanced (n=20) feature sets, using the initial feature set (n=115) as the baseline. ResultsUsing five-fold cross-validation, compared with the baseline (115 features), the Gaussian Naive Bayes model (20 features) achieved statistically higher mean sensitivity (P=.02; 95% CI −0.016 to 0.1929), mean specificity (P=.02; 95% CI −0.016 to 0.199), mean area under the receiver operating characteristic curve (P=.02; 95% CI −0.007 to 0.140), and mean macro F1 (P=.006; 95% CI 0.016-0.167). The statistically improved performance of the final model (20 features) is in contrast to the statistically insignificant changes between the original feature set (n=115) and the automatically selected features (n=19): mean sensitivity (P=.13; 95% CI −0.1699 to 0.0681), mean specificity (P=.10; 95% CI −0.1389 to 0.4017), mean area under the receiver operating characteristic curve (P=.008; 95% CI 0.0059-0.1126), and mean macro F1 (P=.98; 95% CI −0.0555 to 0.0548). This demonstrates the importance and effectiveness of combining automatic feature selection and expert-based linguistic revision to develop the most effective machine learning algorithms from high-dimensional data sets. ConclusionsWe developed new evaluation tools for the discrimination and prediction of writing styles of web-based health resources for children’s health education and promotion among parents and caregivers of children. User-adaptive automatic assessment of web-based health content holds great promise for distant and remote health education among young readers. Our study leveraged the precision and adaptability of machine learning algorithms and insights from health linguistics to help advance this significant yet understudied area of research.

Abstract Background Gender information frequently exists in the eligibility criteria of clinical trial text as essential information for participant population recruitment. Particularly, current eligibility criteria text contains the incompleteness and ambiguity issues in expressing transgender population, leading to difficulties or even failure of transgender population recruitment in clinical trial studies. Methods A new gender model is proposed for providing comprehensive transgender requirement specification. In addition, an automated approach is developed to extract and summarize gender requirements from unstructured text in accordance with the gender model. This approach consists of: 1) the feature extraction module, and 2) the feature summarization module. The first module identifies and extracts gender features using heuristic rules and automatically-generated patterns. The second module summarizes gender requirements by relation inference. Results Based on 100,134 clinical trials from ClinicalTrials.gov, our approach was compared with 20 commonly applied machine learning methods. It achieved a macro-averaged precision of 0.885, a macro-averaged recall of 0.871 and a macro-averaged F1-measure of 0.878. The results illustrated that our approach outperformed all baseline methods in terms of both commonly used metrics and macro-averaged metrics. Conclusions This study presented a new gender model aiming for specifying the transgender requirement more precisely. We also proposed an approach for gender information extraction and summarization from unstructured clinical text to enhance transgender-related clinical trial population recruitment. The experiment results demonstrated that the approach was effective in transgender criteria extraction and summarization.

Abstract Background Social media plays a more and more important role in the research of health and healthcare due to the fast development of internet communication and information exchange. This paper conducts a bibliometric analysis to discover the thematic change and evolution of utilizing social media for healthcare research field. Methods With the basis of 4361 publications from both Web of Science and PubMed during the year 2008–2017, the analysis utilizes methods including topic modelling and science mapping analysis. Results Utilizing social media for healthcare research has attracted increasing attention from scientific communities. Journal of Medical Internet Research is the most prolific journal with the USA dominating in the research. Overly, major research themes such as YouTube analysis and Sex event are revealed. Themes in each time period and how they evolve across time span are also detected. Conclusions This systematic mapping of the research themes and research areas helps identify research interests and how they evolve across time, as well as providing insight into future research direction.

Abstract Background The application of artificial intelligence techniques for processing electronic health records data plays increasingly significant role in advancing clinical decision support. This study conducts a quantitative comparison on the research of utilizing artificial intelligence on electronic health records between the USA and China to discovery their research similarities and differences. Methods Publications from both Web of Science and PubMed are retrieved to explore the research status and academic performances of the two countries quantitatively. Bibliometrics, geographic visualization, collaboration degree calculation, social network analysis, latent dirichlet allocation, and affinity propagation clustering are applied to analyze research quantity, collaboration relations, and hot research topics. Results There are 1031 publications from the USA and 173 publications from China during 2008–2017 period. The annual numbers of publications from the USA and China increase polynomially. JAMIA with 135 publications and JBI with 13 publications are the top prolific journals for the USA and China, respectively. Harvard University with 101 publications and Zhejiang University with 12 publications are the top prolific affiliations for the USA and China, respectively. Massachusetts is the most prolific region with 211 publications for the USA, while for China, Taiwan is the top 1 with 47 publications. China has relatively higher institutional and international collaborations. Nine main research areas for the USA are identified, differentiating 7 for China. Conclusions There is a steadily growing presence and increasing visibility of utilizing artificial intelligence on electronic health records for the USA and China over the years. The results of the study demonstrate the research similarities and differences, as well as strengths and weaknesses of the two countries.

Abstract Background Disease named entity recognition (NER) is a fundamental step in information processing of medical texts. However, disease NER involves complex issues such as descriptive modifiers in actual practice. The accurate identification of disease NER is a still an open and essential research problem in medical information extraction and text mining tasks. Methods A hybrid model named Semantics Bidirectional LSTM and CRF (SBLC) for disease named entity recognition task is proposed. The model leverages word embeddings, Bidirectional Long Short Term Memory networks and Conditional Random Fields. A publically available NCBI disease dataset is applied to evaluate the model through comparing with nine state-of-the-art baseline methods including cTAKES, MetaMap, DNorm, C-Bi-LSTM-CRF, TaggerOne and DNER. Results The results show that the SBLC model achieves an F1 score of 0.862 and outperforms the other methods. In addition, the model does not rely on external domain dictionaries, thus it can be more conveniently applied in many aspects of medical text processing. Conclusions According to performance comparison, the proposed SBLC model achieved the best performance, demonstrating its effectiveness in disease named entity recognition.

This work applies a data-driven coding method for prediction of the COVID-19 spreading profile in any given population that shows an initial phase of epidemic progression. Based on the historical data collected for COVID-19 spreading in 367 cities in China and the set of parameters of the augmented Susceptible-Exposed-Infected-Removed (SEIR) model obtained for each city, a set of profile codes representing a variety of transmission mechanisms and contact topologies is formed. By comparing the data of an early outbreak of a given population with the complete set of historical profiles, the best fit profiles are selected and the corresponding sets of profile codes are used for prediction of the future progression of the epidemic in that population. Application of the method to the data collected for South Korea, Italy and Iran shows that peaks of infection cases are expected to occur before mid April, the end of March and the end of May 2020, and that the percentage of population infected in each city or region will be less than 0.01%, 0.5% and 0.5%, for South Korea, Italy and Iran, respectively.

User intent classification is a vital component of a question-answering system or a task-based dialogue system. In order to understand the goals of users’ questions or discourses, the system categorizes user text into a set of pre-defined user intent categories. User questions or discourses are usually short in length and lack sufficient context; thus, it is difficult to extract deep semantic information from these types of text and the accuracy of user intent classification may be affected. To better identify user intents, this paper proposes a BERT-Cap hybrid neural network model with focal loss for user intent classification to capture user intents in dialogue. The model uses multiple transformer encoder blocks to encode user utterances and initializes encoder parameters with a pre-trained BERT. Then, it extracts essential features using a capsule network with dynamic routing after utterances encoding. Experiment results on four publicly available datasets show that our model BERT-Cap achieves a F1 score of 0.967 and an accuracy of 0.967, outperforming a number of baseline methods, indicating its effectiveness in user intent classification.

Abstract Background Temporal expression extraction and normalization is a fundamental and essential step in clinical text processing and analyzing. Though a variety of commonly used NLP tools are available for medical temporal information extraction, few work is satisfactory for multi-lingual heterogeneous clinical texts. Methods A novel method called TEER is proposed for both multi-lingual temporal expression extraction and normalization from various types of narrative clinical texts including clinical data requests, clinical notes, and clinical trial summaries. TEER is characterized as temporal feature summarization, heuristic rule generation, and automatic pattern learning. By representing a temporal expression as a triple , TEER identifies temporal mentions M, assigns type attributes A to M, and normalizes the values of M into formal representations N. Results Based on two heterogeneous clinical text datasets: 400 actual clinical requests in English and 1459 clinical discharge summaries in Chinese. TEER was compared with six state-of-the-art baselines. The results showed that TEER achieved a precision of 0.948 and a recall of 0.877 on the English clinical requests, while a precision of 0.941 and a recall of 0.932 on the Chinese discharge summaries. Conclusions An automated method TEER for multi-lingual temporal expression extraction was presented. Based on the two datasets containing heterogeneous clinical texts, the comparison results demonstrated the effectiveness of the TEER method in multi-lingual temporal expression extraction from heterogeneous narrative clinical texts.

Abstract Background Natural language processing (NLP) has become an increasingly significant role in advancing medicine. Rich research achievements of NLP methods and applications for medical information processing are available. It is of great significance to conduct a deep analysis to understand the recent development of NLP-empowered medical research field. However, limited study examining the research status of this field could be found. Therefore, this study aims to quantitatively assess the academic output of NLP in medical research field. Methods We conducted a bibliometric analysis on NLP-empowered medical research publications retrieved from PubMed in the period 2007–2016. The analysis focused on three aspects. Firstly, the literature distribution characteristics were obtained with a statistics analysis method. Secondly, a network analysis method was used to reveal scientific collaboration relations. Finally, thematic discovery and evolution was reflected using an affinity propagation clustering method. Results There were 1405 NLP-empowered medical research publications published during the 10 years with an average annual growth rate of 18.39%. 10 most productive publication sources together contributed more than 50% of the total publications. The USA had the highest number of publications. A moderately significant correlation between country’s publications and GDP per capita was revealed. Denny, Joshua C was the most productive author. Mayo Clinic was the most productive affiliation. The annual co-affiliation and co-country rates reached 64.04% and 15.79% in 2016, respectively. 10 main great thematic areas were identified including Computational biology, Terminology mining, Information extraction, Text classification, Social medium as data source, Information retrieval, etc. Conclusions A bibliometric analysis of NLP-empowered medical research publications for uncovering the recent research status is presented. The results can assist relevant researchers, especially newcomers in understanding the research development systematically, seeking scientific cooperation partners, optimizing research topic choices and monitoring new scientific or technological activities.

Abstract After publication of the original article [1] it was noted that the captions relating to Figs. 2 and 3 had been interchanged.

An automatic method for building a semantic dictionary from existing questions in a pattern-based question answering system is proposed for question categorization. This dictionary consists of two main parts: Semantic Domain Terms (SDT), which is a domain specific term list, and Semantic Labeled Terms (SLT), which contain common terms tagged with semantic labels. The semantic dictionary is built using the proposed method on a set of 2509 questions with semantic patterns in our system. 3390 questions without semantic patterns are used as ground truth to test its performance. Experimental results show that the precision of question classification is improved by 7.5% in average after using the constructed semantic dictionary compared with the baseline method.