JMIR Medical Informatics最新文献

{"title":"Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for \"Complete Data\": Observational Clinical Data Analysis.","authors":"Jose Miguel Acitores Cortina, Yasaman Fatapour, Kathleen LaRow Brown, Undina Gisladottir, Michael Zietz, Oliver John Bear Don't Walk Iv, Danner Peter, Jacob S Berkowitz, Nadine A Friedrich, Sophia Kivelson, Aditi Kuchi, Hongyu Liu, Apoorva Srinivasan, Kevin K Tsang, Nicholas P Tatonetti","doi":"10.2196/67591","DOIUrl":"10.2196/67591","url":null,"abstract":"<p><strong>Background: </strong>Integrated clinical databases from national biobanks have advanced the capacity for disease research. Data quality and completeness filters are used when building clinical cohorts to address limitations of data missingness. However, these filters may unintentionally introduce systemic biases when they are correlated with race and ethnicity.</p><p><strong>Objective: </strong>In this study, we examined the race and ethnicity biases introduced by applying common filters to 4 clinical records databases. Specifically, we evaluated whether these filters introduce biases that disproportionately exclude minoritized groups.</p><p><strong>Methods: </strong>We applied 19 commonly used data filters to electronic health record datasets from 4 geographically varied locations comprising close to 12 million patients to understand how using these filters introduces sample bias along racial and ethnic groupings. These filters covered a range of information, including demographics, medication records, visit details, and observation periods. We observed the variation in sample drop-off between self-reported ethnic and racial groups for each site as we applied each filter individually.</p><p><strong>Results: </strong>Applying the observation period filter substantially reduced data availability across all races and ethnicities in all 4 datasets. However, among those examined, the availability of data in the white group remained consistently higher compared to other racial groups after applying each filter. Conversely, the Black or African American group was the most impacted by each filter on these 3 datasets: Cedars-Sinai dataset, UK Biobank, and Columbia University dataset. Among the 4 distinct datasets, only applying the filters to the All of Us dataset resulted in minimal deviation from the baseline, with most racial and ethnic groups following a similar pattern.</p><p><strong>Conclusions: </strong>Our findings underscore the importance of using only necessary filters, as they might disproportionally affect data availability of minoritized racial and ethnic populations. Researchers must consider these unintentional biases when performing data-driven research and explore techniques to minimize the impact of these filters, such as probabilistic methods or adjusted cohort selection methods. Additionally, we recommend disclosing sample sizes for racial and ethnic groups both before and after data filters are applied to aid the reader in understanding the generalizability of the results. Future work should focus on exploring the effects of filters on downstream analyses.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e67591"},"PeriodicalIF":3.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11967746/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733281","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":"Correction: Patients' Experienced Usability and Satisfaction With Digital Health Solutions in a Home Setting: Instrument Validation Study.","authors":"Susan J Oudbier, Ellen M A Smets, Pythia T Nieuwkerk, David P Neal, S Azam Nurmohamed, Hans J Meij, Linda W Dusseljee-Peute","doi":"10.2196/73416","DOIUrl":"10.2196/73416","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e73416"},"PeriodicalIF":3.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11968001/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733282","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":"Improving Systematic Review Updates With Natural Language Processing Through Abstract Component Classification and Selection: Algorithm Development and Validation.","authors":"Tatsuki Hasegawa, Hayato Kizaki, Keisho Ikegami, Shungo Imai, Yuki Yanagisawa, Shuntaro Yada, Eiji Aramaki, Satoko Hori","doi":"10.2196/65371","DOIUrl":"10.2196/65371","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;A challenge in updating systematic reviews is the workload in screening the articles. Many screening models using natural language processing technology have been implemented to scrutinize articles based on titles and abstracts. While these approaches show promise, traditional models typically treat abstracts as uniform text. We hypothesize that selective training on specific abstract components could enhance model performance for systematic review screening.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We evaluated the efficacy of a novel screening model that selects specific components from abstracts to improve performance and developed an automatic systematic review update model using an abstract component classifier to categorize abstracts based on their components.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A screening model was created based on the included and excluded articles in the existing systematic review and used as the scheme for the automatic update of the systematic review. A prior publication was selected for the systematic review, and articles included or excluded in the articles screening process were used as training data. The titles and abstracts were classified into 5 categories (Title, Introduction, Methods, Results, and Conclusion). Thirty-one component-composition datasets were created by combining 5 component datasets. We implemented 31 screening models using the component-composition datasets and compared their performances. Comparisons were conducted using 3 pretrained models: Bidirectional Encoder Representations from Transformer (BERT), BioLinkBERT, and BioM- Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA). Moreover, to automate the component selection of abstracts, we developed the Abstract Component Classifier Model and created component datasets using this classifier model classification. Using the component datasets classified using the Abstract Component Classifier Model, we created 10 component-composition datasets used by the top 10 screening models with the highest performance when implementing screening models using the component datasets that were classified manually. Ten screening models were implemented using these datasets, and their performances were compared with those of models developed using manually classified component-composition datasets. The primary evaluation metric was the F10-Score weighted by the recall.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 256 included articles and 1261 excluded articles were extracted from the selected systematic review. In the screening models implemented using manually classified datasets, the performance of some surpassed that of models trained on all components (BERT: 9 models, BioLinkBERT: 6 models, and BioM-ELECTRA: 21 models). In models implemented using datasets classified by the Abstract Component Classifier Model, the performances of some models (BERT: 7 models and BioM-ELECTRA: 9 models) surpassed that of","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e65371"},"PeriodicalIF":3.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11986382/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733283","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":"An Interpretable Model With Probabilistic Integrated Scoring for Mental Health Treatment Prediction: Design Study.","authors":"Anthony Kelly, Esben Kjems Jensen, Eoin Martino Grua, Kim Mathiasen, Pepijn Van de Ven","doi":"10.2196/64617","DOIUrl":"10.2196/64617","url":null,"abstract":"<p><strong>Background: </strong>Machine learning (ML) systems in health care have the potential to enhance decision-making but often fail to address critical issues such as prediction explainability, confidence, and robustness in a context-based and easily interpretable manner.</p><p><strong>Objective: </strong>This study aimed to design and evaluate an ML model for a future decision support system for clinical psychopathological treatment assessments. The novel ML model is inherently interpretable and transparent. It aims to enhance clinical explainability and trust through a transparent, hierarchical model structure that progresses from questions to scores to classification predictions. The model confidence and robustness were addressed by applying Monte Carlo dropout, a probabilistic method that reveals model uncertainty and confidence.</p><p><strong>Methods: </strong>A model for clinical psychopathological treatment assessments was developed, incorporating a novel ML model structure. The model aimed at enhancing the graphical interpretation of the model outputs and addressing issues of prediction explainability, confidence, and robustness. The proposed ML model was trained and validated using patient questionnaire answers and demographics from a web-based treatment service in Denmark (N=1088).</p><p><strong>Results: </strong>The balanced accuracy score on the test set was 0.79. The precision was ≥0.71 for all 4 prediction classes (depression, panic, social phobia, and specific phobia). The area under the curve for the 4 classes was 0.93, 0.92, 0.91, and 0.98, respectively.</p><p><strong>Conclusions: </strong>We have demonstrated a mental health treatment ML model that supported a graphical interpretation of prediction class probability distributions. Their spread and overlap can inform clinicians of competing treatment possibilities for patients and uncertainty in treatment predictions. With the ML model achieving 79% balanced accuracy, we expect that the model will be clinically useful in both screening new patients and informing clinical interviews.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64617"},"PeriodicalIF":3.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11982765/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733280","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":"Convolutional Neural Network Models for Visual Classification of Pressure Ulcer Stages: Cross-Sectional Study.","authors":"Changbin Lei, Yan Jiang, Ke Xu, Shanshan Liu, Hua Cao, Cong Wang","doi":"10.2196/62774","DOIUrl":"10.2196/62774","url":null,"abstract":"<p><strong>Background: </strong>Pressure injuries (PIs) pose a negative health impact and a substantial economic burden on patients and society. Accurate staging is crucial for treating PIs. Owing to the diversity in the clinical manifestations of PIs and the lack of objective biochemical and pathological examinations, accurate staging of PIs is a major challenge. The deep learning algorithm, which uses convolutional neural networks (CNNs), has demonstrated exceptional classification performance in the intricate domain of skin diseases and wounds and has the potential to improve the staging accuracy of PIs.</p><p><strong>Objective: </strong>We explored the potential of applying AlexNet, VGGNet16, ResNet18, and DenseNet121 to PI staging, aiming to provide an effective tool to assist in staging.</p><p><strong>Methods: </strong>PI images from patients-including those with stage I, stage II, stage III, stage IV, unstageable, and suspected deep tissue injury (SDTI)-were collected at a tertiary hospital in China. Additionally, we augmented the PI data by cropping and flipping the PI images 9 times. The collected images were then divided into training, validation, and test sets at a ratio of 8:1:1. We subsequently trained them via AlexNet, VGGNet16, ResNet18, and DenseNet121 to develop staging models.</p><p><strong>Results: </strong>We collected 853 raw PI images with the following distributions across stages: stage I (n=148), stage II (n=121), stage III (n=216), stage IV (n=110), unstageable (n=128), and SDTI (n=130). A total of 7677 images were obtained after data augmentation. Among all the CNN models, DenseNet121 demonstrated the highest overall accuracy of 93.71%. The classification performances of AlexNet, VGGNet16, and ResNet18 exhibited overall accuracies of 87.74%, 82.42%, and 92.42%, respectively.</p><p><strong>Conclusions: </strong>The CNN-based models demonstrated strong classification ability for PI images, which might promote highly efficient, intelligent PI staging methods. In the future, the models can be compared with nurses with different levels of experience to further verify the clinical application effect.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e62774"},"PeriodicalIF":3.1,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11962570/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712247","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":"Public Attitudes Toward Violence Against Doctors: Sentiment Analysis of Chinese Users.","authors":"Yuwen Zheng, Meirong Tian, Jingjing Chen, Lei Zhang, Jia Gao, Xiang Li, Jin Wen, Xing Qu","doi":"10.2196/63772","DOIUrl":"10.2196/63772","url":null,"abstract":"<p><strong>Background: </strong>Violence against doctors attracts the public's attention both online and in the real world. Understanding how public sentiment evolves during such crises is essential for developing strategies to manage emotions and rebuild trust.</p><p><strong>Objective: </strong>This study aims to quantify the difference in public sentiment based on the public opinion life cycle theory and describe how public sentiment evolved during a high-profile crisis involving violence against doctors in China.</p><p><strong>Methods: </strong>This study used the term frequency-inverse document frequency (TF-IDF) algorithm to extract key terms and create keyword clouds from textual comments. The latent Dirichlet allocation (LDA) topic model was used to analyze the thematic trends and shifts within public sentiment. The integrated Chinese Sentiment Lexicon was used to analyze sentiment trajectories in the collected data.</p><p><strong>Results: </strong>A total of 12,775 valid comments were collected on Sina Weibo about public opinion related to a doctor-patient conflict. Thematic and sentiment analyses showed that the public's sentiments were highly negative during the outbreak period (disgust: 10,201/30,433, 33.52%; anger: 6792/30,433, 22.32%) then smoothly changed to positive and negative during the spread period (sorrow: 2952/8569, 34.45%; joy: 2782/8569, 32.47%) and tended to be rational and peaceful during the decline period (joy: 4757/14,543, 32.71%; sorrow: 4070/14,543, 27.99%). However, no matter how emotions changed, each period's leading tone contained many negative sentiments.</p><p><strong>Conclusions: </strong>This study simultaneously examined the dynamics of theme change and sentiment evolution in crises involving violence against doctors. It discovered that public sentiment evolved alongside thematic changes, with the dominant negative tone from the initial stage persisting throughout. This finding, distinguished from prior research, underscores the lasting influence of early public sentiment. The results offer valuable insights for medical institutions and authorities, suggesting the need for tailored risk communication strategies responsive to the evolving themes and sentiments at different stages of a crisis.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e63772"},"PeriodicalIF":3.1,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11969123/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143665520","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":"Imputation and Missing Indicators for Handling Missing Longitudinal Data: Data Simulation Analysis Based on Electronic Health Record Data.","authors":"Molly Ehrig, Garrett S Bullock, Xiaoyan Iris Leng, Nicholas M Pajewski, Jaime Lynn Speiser","doi":"10.2196/64354","DOIUrl":"10.2196/64354","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Missing data in electronic health records are highly prevalent and result in analytical concerns such as heterogeneous sources of bias and loss of statistical power. One simple analytic method for addressing missing or unknown covariate values is to treat missingness for a particular variable as a category onto itself, which we refer to as the missing indicator method. For cross-sectional analyses, recent work suggested that there was minimal benefit to the missing indicator method; however, it is unclear how this approach performs in the setting of longitudinal data, in which correlation among clustered repeated measures may be leveraged for potentially improved model performance.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objectives: &lt;/strong&gt;This study aims to conduct a simulation study to evaluate whether the missing indicator method improved model performance and imputation accuracy for longitudinal data mimicking an application of developing a clinical prediction model for falls in older adults based on electronic health record data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We simulated a longitudinal binary outcome using mixed effects logistic regression that emulated a falls assessment at annual follow-up visits. Using multivariate imputation by chained equations, we simulated time-invariant predictors such as sex and medical history, as well as dynamic predictors such as physical function, BMI, and medication use. We induced missing data in predictors under scenarios that had both random (missing at random) and dependent missingness (missing not at random). We evaluated aggregate performance using the area under the receiver operating characteristic curve (AUROC) for models with and with no missing indicators as predictors, as well as complete case analysis, across simulation replicates. We evaluated imputation quality using normalized root-mean-square error for continuous variables and percent falsely classified for categorical variables.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Independent of the mechanism used to simulate missing data (missing at random or missing not at random), overall model performance via AUROC was similar regardless of whether missing indicators were included in the model. The root-mean-square error and percent falsely classified measures were similar for models including missing indicators versus those with no missing indicators. Model performance and imputation quality were similar regardless of whether the outcome was related to missingness. Imputation with or with no missing indicators had similar mean values of AUROC compared with complete case analysis, although complete case analysis had the largest range of values.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The results of this study suggest that the inclusion of missing indicators in longitudinal data modeling neither improves nor worsens overall performance or imputation accuracy. Future research is needed to address whether the inclusion of missing indicators is useful in pr","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64354"},"PeriodicalIF":3.1,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924964/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143626899","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":"Assessing Total Hip Arthroplasty Outcomes and Generating an Orthopedic Research Outcome Database via a Natural Language Processing Pipeline: Development and Validation Study.","authors":"Nicholas H Mast, Clara L Oeste, Dries Hens","doi":"10.2196/64705","DOIUrl":"10.2196/64705","url":null,"abstract":"<p><strong>Background: </strong>Processing data from electronic health records (EHRs) to build research-grade databases is a lengthy and expensive process. Modern arthroplasty practice commonly uses multiple sites of care, including clinics and ambulatory care centers. However, most private data systems prevent obtaining usable insights for clinical practice.</p><p><strong>Objective: </strong>This study aims to create an automated natural language processing (NLP) pipeline for extracting clinical concepts from EHRs related to orthopedic outpatient visits, hospitalizations, and surgeries in a multicenter, single-surgeon practice. The pipeline was also used to assess therapies and complications after total hip arthroplasty (THA).</p><p><strong>Methods: </strong>EHRs of 1290 patients undergoing primary THA from January 1, 2012 to December 31, 2019 (operated and followed by the same surgeon) were processed using artificial intelligence (AI)-based models (NLP and machine learning). In addition, 3 independent medical reviewers generated a gold standard using 100 randomly selected EHRs. The algorithm processed the entire database from different EHR systems, generating an aggregated clinical data warehouse. An additional manual control arm was used for data quality control.</p><p><strong>Results: </strong>The algorithm was as accurate as human reviewers (0.95 vs 0.94; P=.01), achieving a database-wide average F1-score of 0.92 (SD 0.09; range 0.67-0.99), validating its use as an automated data extraction tool. During the first year after direct anterior THA, 92.1% (1188/1290) of our population had a complication-free recovery. In 7.9% (102/1290) of cases where surgery or recovery was not uneventful, lateral femoral cutaneous nerve sensitivity (47/1290, 3.6%), intraoperative fractures (13/1290, 1%), and hematoma (9/1290, 0.7%) were the most common complications.</p><p><strong>Conclusions: </strong>Algorithm evaluation of this dataset accurately represented key clinical information swiftly, compared with human reviewers. This technology may provide substantial value for future surgeon practice and patient counseling. Furthermore, the low early complication rate of direct anterior THA in this surgeon's hands was supported by the dataset, which included data from all treated patients in a multicenter practice.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64705"},"PeriodicalIF":3.1,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11922490/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617991","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":"Large Language Model-Based Critical Care Big Data Deployment and Extraction: Descriptive Analysis.","authors":"Zhongbao Yang, Shan-Shan Xu, Xiaozhu Liu, Ningyuan Xu, Yuqing Chen, Shuya Wang, Ming-Yue Miao, Mengxue Hou, Shuai Liu, Yi-Min Zhou, Jian-Xin Zhou, Linlin Zhang","doi":"10.2196/63216","DOIUrl":"10.2196/63216","url":null,"abstract":"<p><strong>Background: </strong>Publicly accessible critical care-related databases contain enormous clinical data, but their utilization often requires advanced programming skills. The growing complexity of large databases and unstructured data presents challenges for clinicians who need programming or data analysis expertise to utilize these systems directly.</p><p><strong>Objective: </strong>This study aims to simplify critical care-related database deployment and extraction via large language models.</p><p><strong>Methods: </strong>The development of this platform was a 2-step process. First, we enabled automated database deployment using Docker container technology, with incorporated web-based analytics interfaces Metabase and Superset. Second, we developed the intensive care unit-generative pretrained transformer (ICU-GPT), a large language model fine-tuned on intensive care unit (ICU) data that integrated LangChain and Microsoft AutoGen.</p><p><strong>Results: </strong>The automated deployment platform was designed with user-friendliness in mind, enabling clinicians to deploy 1 or multiple databases in local, cloud, or remote environments without the need for manual setup. After successfully overcoming GPT's token limit and supporting multischema data, ICU-GPT could generate Structured Query Language (SQL) queries and extract insights from ICU datasets based on request input. A front-end user interface was developed for clinicians to achieve code-free SQL generation on the web-based client.</p><p><strong>Conclusions: </strong>By harnessing the power of our automated deployment platform and ICU-GPT model, clinicians are empowered to easily visualize, extract, and arrange critical care-related databases more efficiently and flexibly than manual methods. Our research could decrease the time and effort spent on complex bioinformatics methods and advance clinical research.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e63216"},"PeriodicalIF":3.1,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11922493/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617995","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":"GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews.","authors":"Takehiko Oami, Yohei Okada, Taka-Aki Nakada","doi":"10.2196/64682","DOIUrl":"10.2196/64682","url":null,"abstract":"<p><strong>Unlabelled: </strong>This study demonstrated that while GPT-4 Turbo had superior specificity when compared to GPT-3.5 Turbo (0.98 vs 0.51), as well as comparable sensitivity (0.85 vs 0.83), GPT-3.5 Turbo processed 100 studies faster (0.9 min vs 1.6 min) in citation screening for systematic reviews, suggesting that GPT-4 Turbo may be more suitable due to its higher specificity and highlighting the potential of large language models in optimizing literature selection.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64682"},"PeriodicalIF":3.1,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11922487/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617994","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}