A Bi-level representation learning model for medical visual question answering.

Medical Visual Question Answering (VQA) targets at answering questions related to given medical images and it contains tremendous potential in healthcare services. However, researches on medical VQA are still facing challenges, particularly on how to learn a fine-grained multimodal semantic representation from relatively small volume of data resources for answer prediction. Moreover, the long-tailed distribution labels of medical VQA data frequently result in poor performance of models. To this end, we propose a novel bi-level representation learning model with two reasoning modules to learn bi-level representations for the medical VQA task. One is sentence-level reasoning to learn sentence-level semantic representations from multimodal input. The other is token-level reasoning that employs an attention mechanism to generate a multimodal contextual vector by fusing image features and word embeddings. The contextual vector is used to filter irrelevant semantic representations from sentence-level reasoning to generate a fine-grained multimodal representation. Furthermore, a label-distribution-smooth margin loss is proposed to minimize generalization error bound of long-tailed distribution datasets by modifying margin bound of different labels in training set. Based on standard VQA-Rad dataset and PathVQA dataset, the proposed model achieves 0.7605 and 0.5434 on accuracy, 0.7741 and 0.5288 on F1-score, respectively, outperforming a set of state-of-the-art baseline models.

Language Use in Conversational Agent-Based Health Communication: Systematic Review.

BACKGROUND: Given 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. OBJECTIVE: This 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. METHODS: This 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. RESULTS: Among 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. CONCLUSIONS: This 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.

Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning.

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.

[Artificial intelligence based Chinese clinical trials eligibility criteria classification].

Subject recruitment is a key component that affects the progress and results of clinical trials, and generally conducted with eligibility criteria (includes inclusion criteria and exclusion criteria). The semantic category analysis of eligibility criteria can help optimizing clinical trials design and building automated patient recruitment system. This study explored the automatic semantic categories classification of Chinese eligibility criteria based on artificial intelligence by academic shared task. We totally collected 38 341 annotated eligibility criteria sentences and predefined 44 semantic categories. A total of 75 teams participated in competition, with 27 teams having submitted system outputs. Based on the results, we found out that most teams adopted mixed models. The mainstream resolution was applying pre-trained language models capable of providing rich semantic representation, which were combined with neural network models and used to fine-tune the models with reference to classifier tasks, and finally improved classification performance could be obtained by ensemble modeling. The best-performing system achieved a macro F1 score of 0.81 by using a pre-trained language model, i.e. bidirectional encoder representations from transformers (BERT) and ensemble modeling. With the error analysis we found out that from the point of data processing steps the data pre-processing and post-processing were very important for classification, while from the point of data volume these categories with less data volume showed lower classification performance. Finally, we hope that this study could provide a valuable dataset and state-of-the-art result for the research of Chinese medical short text classification.

The psychosis analysis in real-world on a cohort of large-scale patients with schizophrenia.

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.

Discovering thematic change and evolution of utilizing social media for healthcare research.

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.

An approach for transgender population information extraction and summarization from clinical trial text.

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.

SBLC: a hybrid model for disease named entity recognition based on semantic bidirectional LSTMs and conditional random fields.

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.

A pattern learning-based method for temporal expression extraction and normalization from multi-lingual heterogeneous clinical texts.

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.

Correction to: A pattern learning-based method for temporal expression extraction and normalization from multi-lingual heterogeneous clinical texts.

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

A comparative quantitative study of utilizing artificial intelligence on electronic health records in the USA and China during 2008-2017.

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.

A bibliometric analysis of natural language processing in medical research.

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.

Clustering clinical trials with similar eligibility criteria features.

OBJECTIVES: To automatically identify and cluster clinical trials with similar eligibility features. METHODS: Using the public repository ClinicalTrials.gov as the data source, we extracted semantic features from the eligibility criteria text of all clinical trials and constructed a trial-feature matrix. We calculated the pairwise similarities for all clinical trials based on their eligibility features. For all trials, by selecting one trial as the center each time, we identified trials whose similarities to the central trial were greater than or equal to a predefined threshold and constructed center-based clusters. Then we identified unique trial sets with distinctive trial membership compositions from center-based clusters by disregarding their structural information. RESULTS: From the 145,745 clinical trials on ClinicalTrials.gov, we extracted 5,508,491 semantic features. Of these, 459,936 were unique and 160,951 were shared by at least one pair of trials. Crowdsourcing the cluster evaluation using Amazon Mechanical Turk (MTurk), we identified the optimal similarity threshold, 0.9. Using this threshold, we generated 8806 center-based clusters. Evaluation of a sample of the clusters by MTurk resulted in a mean score 4.331±0.796 on a scale of 1-5 (5 indicating "strongly agree that the trials in the cluster are similar"). CONCLUSIONS: We contribute an automated approach to clustering clinical trials with similar eligibility features. This approach can be potentially useful for investigating knowledge reuse patterns in clinical trial eligibility criteria designs and for improving clinical trial recruitment. We also contribute an effective crowdsourcing method for evaluating informatics interventions.

A bibliometric analysis of worldwide cancer research using machine learning methods.

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.

Asymmetric cross-modal attention network with multimodal augmented mixup for medical visual question answering.

Insufficient training data is a common barrier to effectively learn multimodal information interactions and question semantics in existing medical Visual Question Answering (VQA) models. This paper proposes a new Asymmetric Cross Modal Attention network called ACMA, which constructs an image-guided attention and a question-guided attention to improve multimodal interactions from insufficient data. In addition, a Semantic Understanding Auxiliary (SUA) in the question-guided attention is newly designed to learn rich semantic embeddings for improving model performance on question understanding by integrating word-level and sentence-level information. Moreover, we propose a new data augmentation method called Multimodal Augmented Mixup (MAM) to train the ACMA, denoted as ACMA-MAM. The MAM incorporates various data augmentations and a vanilla mixup strategy to generate more non-repetitive data, which avoids time-consuming artificial data annotations and improves model generalization capability. Our ACMA-MAM outperforms state-of-the-art models on three publicly accessible medical VQA datasets (VQA-Rad, VQA-Slake, and PathVQA) with accuracies of 76.14 %, 83.13 %, and 53.83 % respectively, achieving improvements of 2.00 %, 1.32 %, and 1.59 % accordingly. Moreover, our model achieves F1 scores of 78.33 %, 82.83 %, and 51.86 %, surpassing the state-of-the-art models by 2.80 %, 1.15 %, and 1.37 % respectively.

Use of Health Care Chatbots Among Young People in China During the Omicron Wave of COVID-19: Evaluation of the User Experience of and Satisfaction With the Technology.

BACKGROUND: Long 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. OBJECTIVE: The 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. METHODS: First, 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. RESULTS: The 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<.001). The findings of this study suggest a considerable positive impact of functional, epistemic, emotional, social, and conditional values on the participants' overall user experience and satisfaction and a positive correlation between these values and user experience and satisfaction (Pearson correlation P<.001). The functional values (mean 1.762, SD 0.630) and epistemic values (mean 1.834, SD 0.654) of the selected chatbots were relatively more important contributors to the students' positive experience and overall satisfaction than the emotional values (mean 1.993, SD 0.683), conditional values (mean 1.995, SD 0.718), and social values (mean 1.998, SD 0.696). All the participants (n=413, 100%) had a positive experience and were thus satisfied with the selected health care chatbots. The 5 grade categories of participants showed different degrees of user experience and satisfaction: Seniors (mean 1.853, SD 0.108) were the most receptive to health care chatbots for COVID-19 self-diagnosis and information, and second-year graduate candidates (mean 2.069, SD 0.133) were the least receptive; freshmen (mean 1.883, SD 0.114) and juniors (mean 1.925, SD 0.087) felt slightly more positive than sophomores (mean 1.989, SD 0.092) and first-year graduate candidates (mean 1.992, SD 0.116) when engaged in conversations with the chatbots. In addition, female informants (mean 1.931, SD 0.098) showed a relatively more receptive attitude toward the selected chatbots than male respondents (mean 1.999, SD 0.051). CONCLUSIONS: This study investigated the use of health care chatbots among young people (aged 17-35 years) in China, focusing on their user experience and satisfaction examined through an assessment framework. The findings show that the 5 domains in the new assessment model all have a positive impact on the participants' user experience and satisfaction. In this paper, we examined the usability of health care chatbots as well as actual chatbots used for other purposes, enriching the literature on the subject. This study also provides practical implication for designers and developers as well as for governments of all countries, especially in the critical period of the omicron waves of COVID-19 and other future public health crises.

Chinese Version of the Mobile Health App Usability Questionnaire: Translation, Adaptation, and Validation Study.

BACKGROUND: The 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. OBJECTIVE: This 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. METHODS: The 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. RESULTS: The 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<.01), reliability (Cronbach α=.988), and validity (Kaiser-Meyer-Olkin=0.973), compared with the C-MAUQ. It was effectively used to test the usability of Left-handed Doctor, eliciting over 80% of informants' positive attitudes toward this mHealth app. CONCLUSIONS: The I-C-MAUQ is highly reliable and valid for Left-handed Doctor, and suitable for testing the usability of interactive mHealth apps used by patients in China. This finding further confirms the cross-cultural validity, reliability, and adaptability of the MAUQ. We identified certain factors influencing the perceived usability of mHealth apps, including users' age, gender, education, profession, and possibly previous experience with mHealth apps and the chatbot function of such apps. Most notably, we found a wider acceptance of this new technology among young Chinese female college students who were more engaged in the interaction with health care chatbots. The age-, gender-, and profession-induced preference for new digital health interventions in China aligns with the findings in other similar studies in America and Malaysia. This preference identifies areas for further research on the social, cultural, and gender adaptation of health technologies.

Interventions in Chinese Undergraduate Students' Mental Health: Systematic Review.

BACKGROUND: Over 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. OBJECTIVE: The 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. METHODS: We 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. RESULTS: We 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. CONCLUSIONS: This 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.

Probabilistic Prediction of Nonadherence to Psychiatric Disorder Medication from Mental Health Forum Data: Developing and Validating Bayesian Machine Learning Classifiers.

Background: Medication nonadherence represents a major burden on national health systems. According to the World Health Organization, increasing medication adherence may have a greater impact on public health than any improvement in specific medical treatments. More research is needed to better predict populations at risk of medication nonadherence. Objective: To develop clinically informative, easy-to-interpret machine learning classifiers to predict people with psychiatric disorders at risk of medication nonadherence based on the syntactic and structural features of written posts on health forums. Methods: All data were collected from posts between 2016 and 2021 on mental health forum, administered by Together 4 Change, a long-running not-for-profit organisation based in Oxford, UK. The original social media data were annotated using the Tool for the Automatic Analysis of Syntactic Sophistication and Complexity (TAASSC) system. Through applying multiple feature optimisation techniques, we developed a best-performing model using relevance vector machine (RVM) for the probabilistic prediction of medication nonadherence among online mental health forum discussants. Results: The best-performing RVM model reached a mean AUC of 0.762, accuracy of 0.763, sensitivity of 0.779, and specificity of 0.742 on the testing dataset. It outperformed competing classifiers with more complex feature sets with statistically significant improvement in sensitivity and specificity, after adjusting the alpha levels with Benjamini-Hochberg correction procedure. Discussion. We used the forest plot of multiple logistic regression to explore the association between written post features in the best-performing RVM model and the binary outcome of medication adherence among online post contributors with psychiatric disorders. We found that increased quantities of 3 syntactic complexity features were negatively associated with psychiatric medication adherence: "dobj_stdev" (standard deviation of dependents per direct object of nonpronouns) (OR, 1.486, 95% CI, 1.202-1.838, P < 0.001), "cl_av_deps" (dependents per clause) (OR, 1.597, 95% CI, 1.202-2.122, P, 0.001), and "VP_T" (verb phrases per T-unit) (OR, 2.23, 95% CI, 1.211-4.104, P, 0.010). Finally, we illustrated the clinical use of the classifier with Bayes' monograph which gives the posterior odds and their 95% CI of positive (nonadherence) versus negative (adherence) cases as predicted by the best-performing classifier. The odds ratio of the posterior probability of positive cases was 3.9, which means that around 10 in every 13 psychiatric patients with a positive result as predicted by our model were following their medication regime. The odds ratio of the posterior probability of true negative cases was 0.4, meaning that around 10 in every 14 psychiatric patients with a negative test result after screening by our classifier were not adhering to their medications. Conclusion: Psychiatric medication nonadherence is a large and increasing burden on national health systems. Using Bayesian machine learning techniques and publicly accessible online health forum data, our study illustrates the viability of developing cost-effective, informative decision aids to support the monitoring and prediction of patients at risk of medication nonadherence.

Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources.

With the rapid development of artificial intelligence (AI) technologies, and the large amount of pharmacovigilance-related data stored in an electronic manner, data-driven automatic methods need to be urgently applied to all aspects of pharmacovigilance to assist healthcare professionals. However, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings. Analyzing challenges and solutions for AI-based pharmacovigilance in resource-limited settings can improve pharmacovigilance frameworks and capabilities in these settings. In this review, we summarize the challenges into four categories: establishing a database for an AI-based pharmacovigilance system, lack of human resources, weak AI technology and insufficient government support. This study also discusses possible solutions and future perspectives on AI-based pharmacovigilance in resource-limited settings.