RESUMO
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.
RESUMO
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.
Assuntos
Aprendizagem , SemânticaRESUMO
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.
RESUMO
Background: COVID-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. Objective: This 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. Methods: A 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. Results: Of 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. Conclusions: This 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.
RESUMO
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.
Assuntos
Aprendizado de Máquina , Semântica , Atenção à Saúde , Idioma , AprendizagemRESUMO
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.
Assuntos
Comunicação em Saúde , Comunicação , Atenção à Saúde , Humanos , Idioma , Estilo de VidaRESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
Assuntos
Inteligência Artificial , Farmacovigilância , Bases de Dados Factuais , Pessoal de Saúde , Humanos , TecnologiaRESUMO
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.
Assuntos
Transtornos Mentais , Saúde Mental , Teorema de Bayes , Humanos , Modelos Logísticos , Aprendizado de Máquina , Transtornos Mentais/tratamento farmacológicoRESUMO
BACKGROUND: From Ebola, Zika, to the latest COVID-19 pandemic, outbreaks of highly infectious diseases continue to reveal severe consequences of social and health inequalities. People from low socioeconomic and educational backgrounds as well as low health literacy tend to be affected by the uncertainty, complexity, volatility, and progressiveness of public health crises and emergencies. A key lesson that governments have taken from the ongoing coronavirus pandemic is the importance of developing and disseminating highly accessible, actionable, inclusive, coherent public health advice, which represent a critical tool to help people with diverse cultural, educational backgrounds and varying abilities to effectively implement health policies at the grassroots level. OBJECTIVE: We aimed to translate the best practices of accessible, inclusive public health advice (purposefully designed for people with low socioeconomic and educational background, health literacy levels, limited English proficiency, and cognitive/functional impairments) on COVID-19 from health authorities in English-speaking multicultural countries (USA, Australia, and UK) to adaptive tools for the evaluation of the accessibility of public health advice in other languages. METHODS: We developed an optimised Bayesian classifier to produce probabilistic prediction of the accessibility of official health advice among vulnerable people including migrants and foreigners living in China. We developed an adaptive statistical formula for the rapid evaluation of the accessibility of health advice among vulnerable people in China. RESULTS: Our study provides needed research tools to fill in a persistent gap in Chinese public health research on accessible, inclusive communication of infectious diseases' prevention and management. For the probabilistic prediction, using the optimised Bayesian machine learning classifier (GNB), the largest positive likelihood ratio (LR+) 16.685 (95% confidence interval: 4.35, 64.04) was identified when the probability threshold was set at 0.2 (sensitivity: 0.98; specificity: 0.94). CONCLUSION: Effective communication of health risks through accessible, inclusive, actionable public advice represents a powerful tool to reduce health inequalities amidst health crises and emergencies. Our study translated the best-practice public health advice developed during the pandemic into intuitive machine learning classifiers for health authorities to develop evidence-based guidelines of accessible health advice. In addition, we developed adaptive statistical tools for frontline health professionals to assess accessibility of public health advice for people from non-English speaking backgrounds.
Assuntos
COVID-19 , Doenças Transmissíveis , Infecção por Zika virus , Zika virus , Teorema de Bayes , Doenças Transmissíveis/epidemiologia , Humanos , Aprendizado de Máquina , Pandemias , Saúde Pública , SARS-CoV-2RESUMO
Neural machine translation technologies are having increasing applications in clinical and healthcare settings. In multicultural countries, automatic translation tools provide critical support to medical and health professionals in their interaction and exchange of health messages with migrant patients with limited or non-English proficiency. While research has mainly explored the usability and limitations of state-of-the-art machine translation tools in the detection and diagnosis of physical diseases and conditions, there is a persistent lack of evidence-based studies on the applicability of machine translation tools in the delivery of mental healthcare services for vulnerable populations. Our study developed Bayesian machine learning algorithms using relevance vector machine to support frontline health workers and medical professionals to make better informed decisions between risks and convenience of using online translation tools when delivering mental healthcare services to Spanish-speaking minority populations living in English-speaking countries. Major strengths of the machine learning classifier that we developed include scalability, interpretability, and adaptability of the classifier for diverse mental healthcare settings. In this paper, we report on the process of the Bayesian machine learning classifier development through automatic feature optimisation and the interpretation of the classifier-enabled assessment of the suitability of original English mental health information for automatic online translation. We elaborate on the interpretation of the assessment results in clinical settings using statistical tools such as positive likelihood ratios and negative likelihood ratios.
Assuntos
Serviços de Saúde Mental , Teorema de Bayes , Humanos , Aprendizado de Máquina , Saúde Mental , TraduçõesRESUMO
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.
RESUMO
BACKGROUND: There 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. OBJECTIVE: Our 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. METHODS: Logistic 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). RESULTS: We 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. CONCLUSIONS: The 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.
RESUMO
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".
RESUMO
BACKGROUND: Current 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. OBJECTIVE: Our 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. METHODS: We 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 10-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. RESULTS: We developed and compared 4 machine learning algorithms using multidimensional semantic features as predictors. The results showed that ensemble tree (LogitBoost) outperformed in terms of AUC (0.97), sensitivity (0.966), specificity (0.972), and accuracy (0.969). Decision tree (AUC 0.924, sensitivity 0.912, specificity 0.9358, and accuracy 0.924) and SVM (AUC 0.8946, sensitivity 0.8952, specificity 0.894, and accuracy 0.8946) followed closely. Decision tree, ensemble tree, and SVM achieved statistically significant improvement over logistic regression in AUC, specificity, and accuracy. As the best performing algorithm, ensemble tree reached statistically significant improvement over SVM in AUC, specificity, and accuracy, and statistically significant improvement over decision tree in sensitivity. CONCLUSIONS: Our 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.
RESUMO
[This corrects the article DOI: 10.2196/29175.].
RESUMO
We aimed to develop machine learning classifiers as a risk-prevention mechanism to help medical professionals with little or no knowledge of the patient's languages in order to predict the likelihood of clinically significant mistakes or incomprehensible MT outputs based on the features of English source information as input to the MT systems. A MNB classifier was developed to provide intuitive probabilistic predictions of erroneous health translation outputs based on the computational modelling of a small number of optimised features of the original English source texts. The best performing multinominal Naïve Bayes classifier (MNB) using a small number of optimised features (8) achieved statistically higher AUC (M = 0.760, SD = 0.03) than the classifier using high-dimension natural features (135) (M = 0.631, SD = 0.006, p < 0.0001, SE = 0.004) and the automatically optimised classifier (22) (M = 0.7231, SD = 0.0084, p < 0.0001, SE = 0.004). Furthermore, MNB (8) had statistically higher sensitivity (M = 0.885, SD = 0.100) compared with the full-feature classifier (135) (M = 0.577, SD = 0.155, p < 0.0001, SE = 0.005) and the automatically optimised classifier (22) (M = 0.731, SD = 0.139, p < 0.0001, SE = 0.0023). Finally, MNB (8) reached statistically higher specificity (M = 0.667, SD = 0.138) compared to the full-feature classifier (135) (M = 0.567, SD = 0.139, p = 0.0002, SE = 0.026) and the automatically optimised classifier (22) (M = 0.633, SD = 0.141, p = 0.0133, SE = 0.026).
Assuntos
Recursos em Saúde , Aprendizado de Máquina , Teorema de Bayes , HumanosRESUMO
BACKGROUND: Medical 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. OBJECTIVE: Using 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. METHODS: The 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. RESULTS: Using 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. CONCLUSIONS: We 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.