JMIR Medical Informatics最新文献

{"title":"Advancing Accuracy in Multimodal Medical Tasks Through Bootstrapped Language-Image Pretraining (BioMedBLIP): Performance Evaluation Study.","authors":"Usman Naseem, Surendrabikram Thapa, Anum Masood","doi":"10.2196/56627","DOIUrl":"10.2196/56627","url":null,"abstract":"<p><strong>Background: </strong>Medical image analysis, particularly in the context of visual question answering (VQA) and image captioning, is crucial for accurate diagnosis and educational purposes.</p><p><strong>Objective: </strong>Our study aims to introduce BioMedBLIP models, fine-tuned for VQA tasks using specialized medical data sets such as Radiology Objects in Context and Medical Information Mart for Intensive Care-Chest X-ray, and evaluate their performance in comparison to the state of the art (SOTA) original Bootstrapping Language-Image Pretraining (BLIP) model.</p><p><strong>Methods: </strong>We present 9 versions of BioMedBLIP across 3 downstream tasks in various data sets. The models are trained on a varying number of epochs. The findings indicate the strong overall performance of our models. We proposed BioMedBLIP for the VQA generation model, VQA classification model, and BioMedBLIP image caption model. We conducted pretraining in BLIP using medical data sets, producing an adapted BLIP model tailored for medical applications.</p><p><strong>Results: </strong>In VQA generation tasks, BioMedBLIP models outperformed the SOTA on the Semantically-Labeled Knowledge-Enhanced (SLAKE) data set, VQA in Radiology (VQA-RAD), and Image Cross-Language Evaluation Forum data sets. In VQA classification, our models consistently surpassed the SOTA on the SLAKE data set. Our models also showed competitive performance on the VQA-RAD and PathVQA data sets. Similarly, in image captioning tasks, our model beat the SOTA, suggesting the importance of pretraining with medical data sets. Overall, in 20 different data sets and task combinations, our BioMedBLIP excelled in 15 (75%) out of 20 tasks. BioMedBLIP represents a new SOTA in 15 (75%) out of 20 tasks, and our responses were rated higher in all 20 tasks (P<.005) in comparison to SOTA models.</p><p><strong>Conclusions: </strong>Our BioMedBLIP models show promising performance and suggest that incorporating medical knowledge through pretraining with domain-specific medical data sets helps models achieve higher performance. Our models thus demonstrate their potential to advance medical image analysis, impacting diagnosis, medical education, and research. However, data quality, task-specific variability, computational resources, and ethical considerations should be carefully addressed. In conclusion, our models represent a contribution toward the synergy of artificial intelligence and medicine. We have made BioMedBLIP freely available, which will help in further advancing research in multimodal medical tasks.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e56627"},"PeriodicalIF":3.1,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11333867/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141891171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation.","authors":"Chang Liu, Zhan Li, Jianmin Li, Yiqian Qu, Ying Chang, Qing Han, Lingyong Cao, Shuyuan Lin","doi":"10.2196/55090","DOIUrl":"10.2196/55090","url":null,"abstract":"<p><strong>Background: </strong>Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods.</p><p><strong>Objective: </strong>This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge.</p><p><strong>Methods: </strong>In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step \"entity-ontology-path\" completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability.</p><p><strong>Results: </strong>In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation.</p><p><strong>Conclusions: </strong>The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e55090"},"PeriodicalIF":3.1,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11329848/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141879923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reference Hallucination Score for Medical Artificial Intelligence Chatbots: Development and Usability Study.","authors":"Fadi Aljamaan, Mohamad-Hani Temsah, Ibraheem Altamimi, Ayman Al-Eyadhy, Amr Jamal, Khalid Alhasan, Tamer A Mesallam, Mohamed Farahat, Khalid H Malki","doi":"10.2196/54345","DOIUrl":"10.2196/54345","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI) chatbots have recently gained use in medical practice by health care practitioners. Interestingly, the output of these AI chatbots was found to have varying degrees of hallucination in content and references. Such hallucinations generate doubts about their output and their implementation.</p><p><strong>Objective: </strong>The aim of our study was to propose a reference hallucination score (RHS) to evaluate the authenticity of AI chatbots' citations.</p><p><strong>Methods: </strong>Six AI chatbots were challenged with the same 10 medical prompts, requesting 10 references per prompt. The RHS is composed of 6 bibliographic items and the reference's relevance to prompts' keywords. RHS was calculated for each reference, prompt, and type of prompt (basic vs complex). The average RHS was calculated for each AI chatbot and compared across the different types of prompts and AI chatbots.</p><p><strong>Results: </strong>Bard failed to generate any references. ChatGPT 3.5 and Bing generated the highest RHS (score=11), while Elicit and SciSpace generated the lowest RHS (score=1), and Perplexity generated a middle RHS (score=7). The highest degree of hallucination was observed for reference relevancy to the prompt keywords (308/500, 61.6%), while the lowest was for reference titles (169/500, 33.8%). ChatGPT and Bing had comparable RHS (β coefficient=-0.069; P=.32), while Perplexity had significantly lower RHS than ChatGPT (β coefficient=-0.345; P<.001). AI chatbots generally had significantly higher RHS when prompted with scenarios or complex format prompts (β coefficient=0.486; P<.001).</p><p><strong>Conclusions: </strong>The variation in RHS underscores the necessity for a robust reference evaluation tool to improve the authenticity of AI chatbots. Further, the variations highlight the importance of verifying their output and citations. Elicit and SciSpace had negligible hallucination, while ChatGPT and Bing had critical hallucination levels. The proposed AI chatbots' RHS could contribute to ongoing efforts to enhance AI's general reliability in medical research.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e54345"},"PeriodicalIF":3.1,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11325115/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141861823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study","authors":"Peyman Ghasemi, Joon Lee","doi":"10.2196/52896","DOIUrl":"https://doi.org/10.2196/52896","url":null,"abstract":"Background: The application of machine learning in healthcare often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the \"curse of dimensionality\" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD/ATC codes and the hierarchical structures of these systems. Objective: The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of coronary artery disease patients in different aspects of performance and complexity and select the best set of features representing these patients. Methods: We compared several unsupervised feature selection methods for two ICD and one ATC code databases of 51,506 coronary artery disease patients in Alberta, Canada. Specifically, we employed Laplacian Score, Unsupervised Feature Selection for Multi-Cluster Data, Autoencoder Inspired Unsupervised Feature Selection, Principal Feature Analysis, and Concrete Autoencoders with and without ICD/ATC tree weight adjustment to select the 100 best features from over 9,000 ICD and 2,000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of selected features by mean code level in ICD/ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis. Results: In feature space reconstruction and mortality prediction, the Concrete Autoencoder-based methods outperformed other techniques. A weight-adjusted Concrete Autoencoder variant, particularly, demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong's and McNemar's tests (P&lt;.05). Concrete Autoencoders preferred more general codes and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted Concrete Autoencoders yielded higher Shapley values in mortality prediction compared to most alternatives. Conclusions: This study scrutinized five feature selection methods in ICD/ATC code datasets in an unsupervised context. Our findings underscore the superiority of the Concrete Autoencoder method in selecting salient features that represent the entire dataset, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the Concrete Autoenc","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"61 1","pages":""},"PeriodicalIF":3.2,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141770157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maturity Assessment of District Health Information System Version 2 Implementation in Ethiopia: Current Status and Improvement Pathways.","authors":"Tesfahun Melese Yilma, Asefa Taddese, Adane Mamuye, Berhanu Fikadie Endehabtu, Yibeltal Alemayehu, Asaye Senay, Dawit Daka, Loko Abraham, Rabeal Tadesse, Gemechis Melkamu, Naod Wendrad, Oli Kaba, Mesoud Mohammed, Wubshet Denboba, Dawit Birhan, Amanuel Biru, Binyam Tilahun","doi":"10.2196/50375","DOIUrl":"10.2196/50375","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Although Ethiopia has made remarkable progress in the uptake of the District Health Information System version 2 (DHIS2) for national aggregate data reporting, there has been no comprehensive assessment of the maturity level of the system.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to assess the maturity level of DHIS2 implementation in Ethiopia and propose a road map that could guide the progress toward a higher level of maturity. We also aim to assess the current maturity status, implementation gaps, and future directions of DHIS2 implementation in Ethiopia. The assessment focused on digital health system governance, skilled human resources, information and communication technology (ICT) infrastructure, interoperability, and data quality and use.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A collaborative assessment was conducted with the engagement of key stakeholders through consultative workshops using the Stages of Continuous Improvement tool to measure maturity levels in 5 core domains, 13 components, and 39 subcomponents. A 5-point scale (1=emerging, 2=repeatable, 3=defined, 4=managed, and 5=optimized) was used to measure the DHIS2 implementation maturity level.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The national DHIS2 implementation's maturity level is currently at the defined stage (score=2.81) and planned to move to the manageable stage (score=4.09) by 2025. The domain-wise maturity score indicated that except for ICT infrastructure, which is at the repeatable stage (score=2.14), the remaining 4 domains are at the defined stage (score=3). The development of a standardized and basic DHIS2 process at the national level, the development of a 10-year strategic plan to guide the implementation of digital health systems including DHIS2, and the presence of the required competencies at the facility level to accomplish specific DHIS2-related tasks are the major strength of the Ministry of Health of Ethiopia so far. The lack of workforce competency guidelines to support the implementation of DHIS2; the unavailability of core competencies (knowledge, skills, and abilities) required to accomplish DHIS2 tasks at all levels of the health system; and ICT infrastructures such as communication network and internet connectivity at the district, zonal, and regional levels are the major hindrances to effective DHIS2 implementation in the country.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;On the basis of the Stages of Continuous Improvement maturity model toolkit, the implementation status of DHIS2 in Ethiopia is at the defined stage, with the ICT infrastructure domain being at the lowest stage as compared to the other 4 domains. By 2025, the maturity status is planned to move from the defined stage to the managed stage by improving the identified gaps. Various action points are suggested to address the identified gaps and reach the stated maturity level. The responsible body, necessary resources, and methods of verification required to reac","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e50375"},"PeriodicalIF":3.1,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316158/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Large Language Models on Medical Education and Teaching Adaptations","authors":"Li Zhui, Nina Yhap, Liu Liping, Wang Zhengjie, Xiong Zhonghao, Yuan Xiaoshu, Cui Hong, Liu Xuexiu, Ren Wei","doi":"10.2196/55933","DOIUrl":"https://doi.org/10.2196/55933","url":null,"abstract":"This viewpoint article explores the transformative impact of Chat Generative Pre-trained Transformer (ChatGPT) on medical education, highlighting its opportunities and challenges. ChatGPT, a product of OpenAI, leverages advanced deep learning models to offer diverse applications, including enhancing teaching efficiency, facilitating personalized learning, reinforcing clinical skills training, improving medical teaching assessment, enhancing efficiency in medical research, and supporting continuing medical education. While presenting promising opportunities, the integration of ChatGPT in medical education raises concerns about response accuracy, overreliance, lack of emotional intelligence, and privacy and data security risks. The article underscores the imperative need to carefully address these challenges, outlining future pathways to bolster medical information accuracy, fortify privacy and data security, and promote synergy between ChatGPT and other artificial intelligence technologies in medical education. It highlights the adaptability and transformative significance of educators amid the widespread integration of ChatGPT in medical education. Educators must consistently uphold a leadership role, guiding students in the ethical and effective use of ChatGPT, nurturing independent thinking, and honing critical reasoning skills. Safeguarding the quality and integrity of medical education in this dynamic technological era remains paramount.","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"66 1","pages":""},"PeriodicalIF":3.2,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141770158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hjernetegn.dk-The Danish Central Nervous System Tumor Awareness Initiative Digital Decision Support Tool: Design and Implementation Report.","authors":"Kathrine Synne Weile, René Mathiasen, Jeanette Falck Winther, Henrik Hasle, Louise Tram Henriksen","doi":"10.2196/58886","DOIUrl":"10.2196/58886","url":null,"abstract":"<p><strong>Background: </strong>Childhood tumors in the central nervous system (CNS) have longer diagnostic delays than other pediatric tumors. Vague presenting symptoms pose a challenge in the diagnostic process; it has been indicated that patients and parents may be hesitant to seek help, and health care professionals (HCPs) may lack awareness and knowledge about clinical presentation. To raise awareness among HCPs, the Danish CNS tumor awareness initiative hjernetegn.dk was launched.</p><p><strong>Objective: </strong>This study aims to present the learnings from designing and implementing a decision support tool for HCPs to reduce diagnostic delay in childhood CNS tumors. The aims also include decisions regarding strategies for dissemination and use of social media, and an evaluation of the digital impact 6 months after launch.</p><p><strong>Methods: </strong>The phases of developing and implementing the tool include participatory co-creation workshops, designing the website and digital platforms, and implementing a press and media strategy. The digital impact of hjernetegn.dk was evaluated through website analytics and social media engagement.</p><p><strong>Implementation (results): </strong>hjernetegn.dk was launched in August 2023. The results after 6 months exceeded key performance indicators. The analysis showed a high number of website visitors and engagement, with a plateau reached 3 months after the initial launch. The LinkedIn campaign and Google Search strategy also generated a high number of impressions and clicks.</p><p><strong>Conclusions: </strong>The findings suggest that the initiative has been successfully integrated, raising awareness and providing a valuable tool for HCPs in diagnosing childhood CNS tumors. The study highlights the importance of interdisciplinary collaboration, co-creation, and ongoing community management, as well as broad dissemination strategies when introducing a digital support tool.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e58886"},"PeriodicalIF":3.1,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11310640/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introducing Attribute Association Graphs to Facilitate Medical Data Exploration: Development and Evaluation Using Epidemiological Study Data.","authors":"Louis Bellmann, Alexander Johannes Wiederhold, Leona Trübe, Raphael Twerenbold, Frank Ückert, Karl Gottfried","doi":"10.2196/49865","DOIUrl":"10.2196/49865","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Interpretability and intuitive visualization facilitate medical knowledge generation through big data. In addition, robustness to high-dimensional and missing data is a requirement for statistical approaches in the medical domain. A method tailored to the needs of physicians must meet all the abovementioned criteria.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to develop an accessible tool for visual data exploration without the need for programming knowledge, adjusting complex parameterizations, or handling missing data. We sought to use statistical analysis using the setting of disease and control cohorts familiar to clinical researchers. We aimed to guide the user by identifying and highlighting data patterns associated with disease and reveal relations between attributes within the data set.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We introduce the attribute association graph, a novel graph structure designed for visual data exploration using robust statistical metrics. The nodes capture frequencies of participant attributes in disease and control cohorts as well as deviations between groups. The edges represent conditional relations between attributes. The graph is visualized using the Neo4j (Neo4j, Inc) data platform and can be interactively explored without the need for technical knowledge. Nodes with high deviations between cohorts and edges of noticeable conditional relationship are highlighted to guide the user during the exploration. The graph is accompanied by a dashboard visualizing variable distributions. For evaluation, we applied the graph and dashboard to the Hamburg City Health Study data set, a large cohort study conducted in the city of Hamburg, Germany. All data structures can be accessed freely by researchers, physicians, and patients. In addition, we developed a user test conducted with physicians incorporating the System Usability Scale, individual questions, and user tasks.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We evaluated the attribute association graph and dashboard through an exemplary data analysis of participants with a general cardiovascular disease in the Hamburg City Health Study data set. All results extracted from the graph structure and dashboard are in accordance with findings from the literature, except for unusually low cholesterol levels in participants with cardiovascular disease, which could be induced by medication. In addition, 95% CIs of Pearson correlation coefficients were calculated for all associations identified during the data analysis, confirming the results. In addition, a user test with 10 physicians assessing the usability of the proposed methods was conducted. A System Usability Scale score of 70.5% and average successful task completion of 81.4% were reported.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The proposed attribute association graph and dashboard enable intuitive visual data exploration. They are robust to high-dimensional as well as missing data and require no pa","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e49865"},"PeriodicalIF":3.1,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11306949/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141753505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Telehealth Uptake Among Hispanic People During COVID-19: Retrospective Observational Study.","authors":"Di Shang, Cynthia Williams, Hera Culiqi","doi":"10.2196/57717","DOIUrl":"10.2196/57717","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The Hispanic community represents a sizeable community that experiences inequities in the US health care system. As the system has moved toward digital health platforms, evaluating the potential impact on Hispanic communities is critical.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The study aimed to investigate demographic, socioeconomic, and behavioral factors contributing to low telehealth use in Hispanic communities.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We used a retrospective observation study design to examine the study objectives. The COVID-19 Research Database Consortium provided the Analytics IQ PeopleCore consumer data and Office Alley claims data. The study period was from March 2020 to April 2021. Multiple logistic regression was used to determine the odds of using telehealth services.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We examined 3,478,287 unique Hispanic patients, 16.6% (577,396) of whom used telehealth. Results suggested that patients aged between 18 and 44 years were more likely to use telehealth (odds ratio [OR] 1.07, 95% CI 1.05-1.1; P&lt;.001) than patients aged older than 65 years. Across all age groups, patients with high incomes were at least 20% more likely to use telehealth than patients with lower incomes (P&lt;.001); patients who had a primary care physician (P=.01), exhibited high medical usage (P&lt;.001), or were interested in exercise (P=.03) were more likely to use telehealth; patients who had unhealthy behaviors such as smoking and alcohol consumption were less likely to use telehealth (P&lt;.001). Male patients were less likely than female patients to use telehealth among patients aged 65 years and older (OR 0.94, 95% CI 0.93-0.95; P&lt;.001), while male patients aged between 18 and 44 years were more likely to use telehealth (OR 1.05, 95% CI 1.03-1.07; P&lt;.001). Among patients younger than 65 years, full-time employment was positively associated with telehealth use (P&lt;.001). Patients aged between 18 and 44 years with high school or less education were 2% less likely to use telehealth (OR 0.98, 95% CI 0.97-0.99; P=.005). Results also revealed a positive association with using WebMD (WebMD LLC) among patients aged older than 44 years (P&lt;.001), while there was a negative association with electronic prescriptions among those who were aged between 18 and 44 years (P=.009) and aged between 45 and 64 years (P=.004).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study demonstrates that telehealth use among Hispanic communities is dependent upon factors such as age, gender, education, socioeconomic status, current health care engagement, and health behaviors. To address these challenges, we advocate for interdisciplinary approaches that involve medical professionals, insurance providers, and community-based services actively engaging with Hispanic communities and promoting telehealth use. We propose the following recommendations: enhance access to health insurance, improve access to primary care providers, and allocate fiscal a","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e57717"},"PeriodicalIF":3.1,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11289584/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncovering Harmonization Potential in Health Care Data Through Iterative Refinement of Fast Healthcare Interoperability Resources Profiles Based on Retrospective Discrepancy Analysis: Case Study.","authors":"Lorenz Rosenau, Paul Behrend, Joshua Wiedekopf, Julian Gruendner, Josef Ingenerf","doi":"10.2196/57005","DOIUrl":"10.2196/57005","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Cross-institutional interoperability between health care providers remains a recurring challenge worldwide. The German Medical Informatics Initiative, a collaboration of 37 university hospitals in Germany, aims to enable interoperability between partner sites by defining Fast Healthcare Interoperability Resources (FHIR) profiles for the cross-institutional exchange of health care data, the Core Data Set (CDS). The current CDS and its extension modules define elements representing patients' health care records. All university hospitals in Germany have made significant progress in providing routine data in a standardized format based on the CDS. In addition, the central research platform for health, the German Portal for Medical Research Data feasibility tool, allows medical researchers to query the available CDS data items across many participating hospitals.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;In this study, we aimed to evaluate a novel approach of combining the current top-down generated FHIR profiles with the bottom-up generated knowledge gained by the analysis of respective instance data. This allowed us to derive options for iteratively refining FHIR profiles using the information obtained from a discrepancy analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We developed an FHIR validation pipeline and opted to derive more restrictive profiles from the original CDS profiles. This decision was driven by the need to align more closely with the specific assumptions and requirements of the central feasibility platform's search ontology. While the original CDS profiles offer a generic framework adaptable for a broad spectrum of medical informatics use cases, they lack the specificity to model the nuanced criteria essential for medical researchers. A key example of this is the necessity to represent specific laboratory codings and values interdependencies accurately. The validation results allow us to identify discrepancies between the instance data at the clinical sites and the profiles specified by the feasibility platform and addressed in the future.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 20 university hospitals participated in this study. Historical factors, lack of harmonization, a wide range of source systems, and case sensitivity of coding are some of the causes for the discrepancies identified. While in our case study, Conditions, Procedures, and Medications have a high degree of uniformity in the coding of instance data due to legislative requirements for billing in Germany, we found that laboratory values pose a significant data harmonization challenge due to their interdependency between coding and value.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;While the CDS achieves interoperability, different challenges for federated data access arise, requiring more specificity in the profiles to make assumptions on the instance data. We further argue that further harmonization of the instance data can significantly lower required","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e57005"},"PeriodicalIF":3.1,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11303887/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141749840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}