Journal of the American Medical Informatics Association最新文献

{"title":"Reply to Layne et al.'s Letter to the Editor.","authors":"Cathy Shyr, Paul A Harris","doi":"10.1093/jamia/ocaf026","DOIUrl":"10.1093/jamia/ocaf026","url":null,"abstract":"","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1089"},"PeriodicalIF":4.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12089780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143416026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of the provider documentation summarization quality instrument for large language models.","authors":"Emma Croxford, Yanjun Gao, Nicholas Pellegrino, Karen Wong, Graham Wills, Elliot First, Miranda Schnier, Kyle Burton, Cris Ebby, Jillian Gorski, Matthew Kalscheur, Samy Khalil, Marie Pisani, Tyler Rubeor, Peter Stetson, Frank Liao, Cherodeep Goswami, Brian Patterson, Majid Afshar","doi":"10.1093/jamia/ocaf068","DOIUrl":"10.1093/jamia/ocaf068","url":null,"abstract":"<p><strong>Objectives: </strong>As large language models (LLMs) are integrated into electronic health record (EHR) workflows, validated instruments are essential to evaluate their performance before implementation and as models and documentation practices evolve. Existing instruments for provider documentation quality are often unsuitable for the complexities of LLM-generated text and lack validation on real-world data. The Provider Documentation Summarization Quality Instrument (PDSQI-9) was developed to evaluate LLM-generated clinical summaries. This study aimed to validate the PDSQI-9 across key aspects of construct validity.</p><p><strong>Materials and methods: </strong>Multi-document summaries were generated from real-world EHR data across multiple specialties using several LLMs (GPT-4o, Mixtral 8x7b, and Llama 3-8b). Validation included Pearson correlation analyses for substantive validity, factor analysis and Cronbach's α for structural validity, inter-rater reliability (ICC and Krippendorff's α) for generalizability, a semi-Delphi process for content validity, and comparisons of high- versus low-quality summaries for discriminant validity. Raters underwent standardized training to ensure consistent application of the instrument.</p><p><strong>Results: </strong>Seven physician raters evaluated 779 summaries and answered 8329 questions, achieving over 80% power for inter-rater reliability. The PDSQI-9 demonstrated strong internal consistency (Cronbach's α = 0.879; 95% CI, 0.867-0.891) and high inter-rater reliability (ICC = 0.867; 95% CI, 0.867-0.868), supporting structural validity and generalizability. Factor analysis identified a 4-factor model explaining 58% of the variance, representing organization, clarity, accuracy, and utility. Substantive validity was supported by correlations between note length and scores for Succinct (ρ = -0.200, P = .029) and Organized (ρ = -0.190, P = .037). The semi-Delphi process ensured clinically relevant attributes, and discriminant validity distinguished high- from low-quality summaries (P<.001).</p><p><strong>Discussion: </strong>The PDSQI-9 showed high inter-rater reliability, internal consistency, and a meaningful factor structure that reliably captured key dimensions of documentation quality. It distinguished between high- and low-quality summaries, supporting its practical utility for health systems needing an evaluation instrument for LLMs.</p><p><strong>Conclusions: </strong>The PDSQI-9 demonstrates robust construct validity, supporting its use in clinical practice to evaluate LLM-generated summaries and facilitate safer, more effective integration of LLMs into healthcare workflows.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1050-1060"},"PeriodicalIF":4.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12089781/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144025188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Factors impacting electronic patient-generated data use in safety-net systems: a qualitative study.","authors":"Elaine C Khoong, Jeanette Wong, Faviola Garcia, Kristan Olazo, Mahal Miles, Billy Zeng, Courtney R Lyles, Urmimala Sarkar","doi":"10.1093/jamia/ocaf079","DOIUrl":"https://doi.org/10.1093/jamia/ocaf079","url":null,"abstract":"<p><strong>Objective: </strong>To characterize patient and clinician perceived barriers and facilitators to using electronic patient-generated data (PGD) in safety-net systems.</p><p><strong>Materials and methods: </strong>We conducted 43 semi-structured interviews (18 clinicians and 25 patients) and observed 15 patient-clinician interactions. Clinical observations were conducted in an integrated urban safety-net system. Patients who spoke English, Spanish, or Cantonese were recruited from this system. Pharmacists, nurses, and clinicians treating chronic diseases were sampled from multiple California safety-net systems. Interview guides were developed based on the Consolidated Framework for Implementation Research (CFIR) and the Behavior Change Wheel (BCW). We conducted thematic analysis through a combination of inductive and deductive coding.</p><p><strong>Results: </strong>Themes most frequently identified by both clinicians and patients as impacting electronic PGD use were capability-related (knowledge about collecting and using PGD), motivation-related (preference for data sharing; attitude toward digital tools and learning how to use them; the importance of measuring the outcome for health; privacy; and patient-clinician relationship), and opportunity-related (social support). Non-English speakers expressed concerns about inconveniencing others. Clinicians also identified additional opportunity-related themes (resource availability; implementation process; external incentives).</p><p><strong>Discussion: </strong>Despite the growth in electronic PGD and its potential to improve chronic disease care and outcomes, implementation in safety-net systems would benefit from consideration of capability, motivation, and opportunity-related barriers.</p><p><strong>Conclusion: </strong>PGD is an increasingly vital part of clinical care. If implementation is pursued without concurrently addressing factors at the patient, clinician, health system, and policy levels, barriers to adoption will persist, especially in under-resourced settings.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144163470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of inpatient medication administration technologies on nursing autonomy and practice: a meta-ethnographic synthesis of the qualitative literature.","authors":"Sadaf Kazi, Zoe Pruitt, Ella Franklin, Aaron Z Hettinger, Raj M Ratwani, Charlene Weir","doi":"10.1093/jamia/ocaf080","DOIUrl":"https://doi.org/10.1093/jamia/ocaf080","url":null,"abstract":"<p><strong>Objective: </strong>To conduct a meta-ethnographic synthesis summarizing the overarching themes of the qualitative literature on nurse interaction with medication administration technologies (MAT) comprising electronic medication administration record (eMAR) and bar-coded medication administration (BCMA).</p><p><strong>Materials and methods: </strong>We searched scientific databases from their inception until September 23, 2024, resulting in 2270 unique articles, and extracted data from 27 articles. Scientific rigor was assessed by the Standards for Reporting Qualitative Research (SRQR) checklist. Noblit and Hare's methodology was used to conduct a meta-ethnography to identify and interpret emergent themes.</p><p><strong>Results: </strong>SRQR revealed low-to-medium methodological quality and theoretical framing of the literature. We found 6 overarching themes connecting MAT with nursing work: (1) View of the MAT system as mechanistic and invariant vs living and co-evolving with its users drives the research approach; (2) MAT limits nurse autonomy; (3) MAT unnaturally splits the medication administration workflow; (4) Nurses must manage MAT challenges at the sharp end; (5) MAT does not align with social dependencies of nursing work; and (6) MAT increases perceived safety but can also result in new types of errors.</p><p><strong>Discussion: </strong>MAT does not support key cognitive work that nurses must perform to maintain safety. Additionally, MAT can impede problem solving during medication management and limit nursing autonomy that is essential for safe medication administration.</p><p><strong>Conclusion: </strong>Recommendations based in human factors engineering recognizing how MAT design impacts nursing work and workload are essential in improving the fit of MAT to nurse cognitive workflows.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144163475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal integration of longitudinal noninvasive diagnostics for survival prediction in immunotherapy using deep learning.","authors":"Melda Yeghaian, Zuhir Bodalal, Daan van den Broek, John B A G Haanen, Regina G H Beets-Tan, Stefano Trebeschi, Marcel A J van Gerven","doi":"10.1093/jamia/ocaf074","DOIUrl":"https://doi.org/10.1093/jamia/ocaf074","url":null,"abstract":"<p><strong>Objectives: </strong>Immunotherapies have revolutionized the landscape of cancer treatments. However, our understanding of response patterns in advanced cancers treated with immunotherapy remains limited. By leveraging routinely collected noninvasive longitudinal and multimodal data with artificial intelligence, we could unlock the potential to transform immunotherapy for cancer patients, paving the way for personalized treatment approaches.</p><p><strong>Materials and methods: </strong>In this study, we developed a novel artificial neural network architecture, multimodal transformer-based simple temporal attention (MMTSimTA) network, building upon a combination of recent successful developments. We integrated pre- and on-treatment blood measurements, prescribed medications, and CT-based volumes of organs from a large pan-cancer cohort of 694 patients treated with immunotherapy to predict mortality at 3, 6, 9, and 12 months. Different variants of our extended MMTSimTA network were implemented and compared to baseline methods, incorporating intermediate and late fusion-based integration methods.</p><p><strong>Results: </strong>The strongest prognostic performance was demonstrated using a variant of the MMTSimTA model with area under the curves of 0.84 ± 0.04, 0.83 ± 0.02, 0.82 ± 0.02, 0.81 ± 0.03 for 3-, 6-, 9-, and 12-month survival prediction, respectively.</p><p><strong>Discussion: </strong>Our findings show that integrating noninvasive longitudinal data using our novel architecture yields an improved multimodal prognostic performance, especially in short-term survival prediction.</p><p><strong>Conclusion: </strong>Our study demonstrates that multimodal longitudinal integration of noninvasive data using deep learning may offer a promising approach for personalized prognostication in immunotherapy-treated cancer patients.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144144346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Linguistic markers for identifying post-traumatic stress disorder and associated symptoms: a systematic literature review.","authors":"Robin Quillivic, Yann Auxéméry, Frédérique Gayraud, Jacques Dayan, Salma Mesmoudi","doi":"10.1093/jamia/ocaf075","DOIUrl":"https://doi.org/10.1093/jamia/ocaf075","url":null,"abstract":"<p><strong>Objectives: </strong>Diagnosing post-traumatic stress disorder (PTSD) remains a challenge due to symptom variability and comorbidities. Linguistic analysis offers an innovative approach to identify PTSD symptoms and severity. This systematic review aimed at identifying linguistic features associated with PTSD, assessing the quality and limitations of existing studies, summarizing the predictive performance of identified models, and describing the clinical utility of these models.</p><p><strong>Materials: </strong>A comprehensive search was conducted across multiple databases, resulting in the identification of 593 articles. After screening and eligibility assessment, 58 studies were included.</p><p><strong>Methods: </strong>Data extraction focused on study characteristics, methodology, and performance metrics. We assessed the risk of bias using the PROBAST and conducted both a narrative synthesis and a meta-analysis.</p><p><strong>Results: </strong>Linguistic features such as pronoun use, emotional valence, cognitive processing words, narrative length, discourse disorganization, temporal orientation, specific lexical fields (death, anxiety, sensory-perception details), and disfluencies were commonly investigated. The meta-analysis revealed a pooled area under the curve of 0.81, indicating the high performance of classification models. However, significant publication bias and heterogeneity were noted. Only 8 studies were rated with a low risk of bias, highlighting common issues such as inadequate control groups, unvalidated linguistic tools, unvalidated diagnosis tools, and low rigor in statistical analysis.</p><p><strong>Discussion and conclusions: </strong>Linguistic markers showed potential for enhancing PTSD diagnoses, but the contemporary research was limited by methodological inconsistencies and biases. Future research should focus on standardized tools, symptom-focused studies, and interdisciplinary collaboration to improve the robustness and clinical applicability of findings.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144136524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electronic patient-reported outcome measures for triaging and scheduling outpatient appointments: a systematic review and meta-analysis.","authors":"Chen He, Yuelin Xia, Ying Shan Cheung, Sze Tung Lam, Suephy C Chen, Jose M Valderas, Ellie Choi","doi":"10.1093/jamia/ocaf078","DOIUrl":"https://doi.org/10.1093/jamia/ocaf078","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to review the effectiveness of electronic patient-reported outcome measures (ePROMs) to triage and schedule appointments for adult patients with chronic medical conditions.</p><p><strong>Materials and methods: </strong>A structured search was implemented in electronic databases for randomized controlled trials that compared use of ePROMs to facilitate flexible scheduling of appointments (intervention) with conventional scheduling practices (control) in adult outpatients with chronic medical condition. The primary outcome was the difference in healthcare utilization, measured by the number of outpatient physical appointments. Secondary outcomes include disease control and implementational outcomes. A meta-analysis using random effects modeling was performed.</p><p><strong>Results: </strong>The search strategy yielded 3769 citations and 1 additional article from hand search; 17 randomized controlled trials (6469 patients) were included. Most studies focused on cancer (n = 9) or rheumatoid arthritis (n = 3). Six out of 10 studies comparing the number of physical appointments showed that ePROMs significantly reduced the mean number of physical appointments, while 1 study reported increased appointments. A meta-analysis of 6 studies with sufficient data for pooling indicated that the ePROMs group had fewer appointments, with a mean difference of -1.12 (CI, -1.87 to -0.37). Among 10 studies evaluating disease control, 2 showed improved disease control with ePROMs, 2 reported improved survival in cancer patients, while 6 found no significant differences.</p><p><strong>Discussion: </strong>Current evidence supports the feasibility and acceptability of incorporating ePROMs in outpatient visit scheduling, with a reduction in physical appointments without compromising disease outcomes.</p><p><strong>Conclusion: </strong>ePROMs can be used to support and guide decisions regarding outpatient appointment scheduling.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semi-automated pipeline to accelerate multi-site flowsheet alignment and concept mapping in electronic health records.","authors":"Hao Fan, Sarah C Rossetti, Jennifer Thate, Rosemary Mugoya, Albert M Lai, Po-Yin Yen","doi":"10.1093/jamia/ocaf076","DOIUrl":"https://doi.org/10.1093/jamia/ocaf076","url":null,"abstract":"<p><strong>Objectives: </strong>Health-care institutions customize electronic health record (EHR) configurations to reflect their unique workflows and patient care priorities. Ensuring EHR alignment across sites facilitates seamless information exchange. We developed a pipeline for EHR flowsheet alignment between health-care organizations. The pipeline is augmented by mapping flowsheet data fields to concepts in the Clinical Care Classification (CCC) nursing terminology.</p><p><strong>Materials and methods: </strong>Flowsheet templates and measures from 2 study sites were transformed into template-measure (T-M) pairs. They were aligned through exact, lexical, or semantic matching. Lexical matches were assessed using Jaccard similarity and fuzzy matching methods. Semantic alignment was determined using cosine similarity between large language model-generated embeddings of T-M pairs and CCC concepts to rank and recommend the top n concepts in CCC. Concept mappings were evaluated based on whether concepts were mapped consistently within the CCC hierarchy.</p><p><strong>Results: </strong>We totally aligned 31 255 unique T-M pairs in acute care units and 27 012 T-M pairs in intensive care units from 2 study sites. When restricted to the top-ranked CCC concept (n = 1), we achieved a 63% flowsheet alignment rate with a 53% concept mapping rate. Expanding to the top 3 concepts (n = 3) improved alignment to 96.5% and concept mapping to 96%.</p><p><strong>Discussion and conclusion: </strong>Electronic health record data field alignment with concept mapping offers opportunities to standardize data elements presented in flowsheets across health-care sites. We demonstrated the feasibility of leveraging a semi-automated pipeline to streamline the EHR flowsheet alignment and accelerate the manual concept mapping process.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Supporting rapid innovation in research data capture and management: the REDCap external module framework.","authors":"Alex C Cheng, Stephany N Duda, Kyle McGuffin, Mark McEver, Rob Taylor, Günther A Rezniczek, Andrew Martin, Eduardo Morales, Paul A Harris","doi":"10.1093/jamia/ocaf073","DOIUrl":"https://doi.org/10.1093/jamia/ocaf073","url":null,"abstract":"<p><strong>Objectives: </strong>Establishing a robust and secure framework allowing creation and sharing of custom features within the REDCap electronic data capture platform.</p><p><strong>Materials and methods: </strong>In partnership with REDCap Consortium members, we developed a framework for creating external modules enabling project-specific REDCap custom functionality (EM Framework). The EM Framework includes guidance and standard processes for developers to ensure basic functionality, compatibility, and security across REDCap instances. The EM Framework also includes an optional dissemination mechanism, the REDCap Repository of External Modules (Repo), for developers to easily share their work with other institutions in the REDCap Consortium.</p><p><strong>Results: </strong>From the EM Framework's launch in 2017 through 2024, 356 external modules have been published to the Repo by software developers at 59 institutions. These modules have been used on 29 485 projects at 2107 institutions in 67 countries. Over time, features from 22 of these external modules have been integrated into the core REDCap code serving 7700+ REDCap Consortium members in 160 countries.</p><p><strong>Discussion: </strong>The EM Framework permits developers to create, test, and deploy custom features to their local REDCap platform. It further enables a process to distribute these features to other REDCap administrators across the Consortium.</p><p><strong>Conclusion: </strong>The EM Framework has enhanced innovation in electronic data capture and dissemination of those innovations to a global research community.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144057082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dependence of premature ventricular complexes on heart rate-it's not that simple.","authors":"Adrien Osakwe, Noah Wightman, Marc W Deyell, Zachary Laksman, Alvin Shrier, Gil Bub, Leon Glass, Thomas M Bury","doi":"10.1093/jamia/ocaf069","DOIUrl":"https://doi.org/10.1093/jamia/ocaf069","url":null,"abstract":"<p><strong>Objective: </strong>Frequent premature ventricular complexes (PVCs) can lead to adverse health conditions such as cardiomyopathy. The linear correlation between PVC frequency and heart rate (as positive, negative, or neutral) on a 24-hour Holter recording has been proposed as a way to classify patients and guide treatment with beta-blockers. Our objective was to evaluate the robustness of this classification to measurement methodology, different 24-hour periods, and nonlinear dependencies of PVCs on heart rate.</p><p><strong>Materials and methods: </strong>We analyzed 82 multi-day Holter recordings (1-7 days) collected from 48 patients with frequent PVCs (burden 1%-44%). For each record, linear correlation between PVC frequency and heart rate was computed for different 24-hour periods and using different length intervals to determine PVC frequency.</p><p><strong>Results: </strong>Using a 1-hour interval, the correlation between PVC frequency and heart rate was consistently positive, negative, or neutral on different days in only 36.6% of patients. Using shorter time intervals, the correlation was consistent in 56.1% of patients. Shorter time intervals revealed nonlinear and piecewise linear relationships between PVC frequency and heart rate in many patients.</p><p><strong>Discussion: </strong>The variability of the correlation between PVC frequency and heart rate across different 24-hour periods and interval durations suggests that the relationship is neither strictly linear nor stationary. A better understanding of the mechanism driving the PVCs, combined with computational and biological models that represent these mechanisms, may provide insight into the observed nonlinear behavior and guide more robust classification strategies.</p><p><strong>Conclusion: </strong>Linear correlation as a tool to classify patients with frequent PVCs should be used with caution. It is sensitive to the specific 24-hour period analyzed and the methodology used to segment the data. More sophisticated classification approaches that can capture nonlinear and time-varying dependencies should be developed and considered in clinical practice.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144055982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}