Journal of the American Medical Informatics Association最新文献

{"title":"Application of large language models in clinical record correction: a comprehensive study on various retraining methods.","authors":"Ana M Maitin, Alberto Nogales, Sergio Fernández-Rincón, Enrique Aranguren, Emilio Cervera-Barba, Sophia Denizon-Arranz, Alonso Mateos-Rodríguez, Álvaro J García-Tejedor","doi":"10.1093/jamia/ocae302","DOIUrl":"https://doi.org/10.1093/jamia/ocae302","url":null,"abstract":"<p><strong>Objectives: </strong>We evaluate the effectiveness of large language models (LLMs), specifically GPT-based (GPT-3.5 and GPT-4) and Llama-2 models (13B and 7B architectures), in autonomously assessing clinical records (CRs) to enhance medical education and diagnostic skills.</p><p><strong>Materials and methods: </strong>Various techniques, including prompt engineering, fine-tuning (FT), and low-rank adaptation (LoRA), were implemented and compared on Llama-2 7B. These methods were assessed using prompts in both English and Spanish to determine their adaptability to different languages. Performance was benchmarked against GPT-3.5, GPT-4, and Llama-2 13B.</p><p><strong>Results: </strong>GPT-based models, particularly GPT-4, demonstrated promising performance closely aligned with specialist evaluations. Application of FT on Llama-2 7B improved text comprehension in Spanish, equating its performance to that of Llama-2 13B with English prompts. Low-rank adaptation significantly enhanced performance, surpassing GPT-3.5 results when combined with FT. This indicates LoRA's effectiveness in adapting open-source models for specific tasks.</p><p><strong>Discussion: </strong>While GPT-4 showed superior performance, FT and LoRA on Llama-2 7B proved crucial in improving language comprehension and task-specific accuracy. Identified limitations highlight the need for further research.</p><p><strong>Conclusion: </strong>This study underscores the potential of LLMs in medical education, providing an innovative, effective approach to CR correction. Low-rank adaptation emerged as the most effective technique, enabling open-source models to perform on par with proprietary models. Future research should focus on overcoming current limitations to further improve model performance.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873370","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":"An electronic health record metadata-mining approach to identifying patient-level interprofessional clinician teams in the intensive care unit.","authors":"Olga Yakusheva, Lara Khadr, Kathryn A Lee, Hannah C Ratliff, Deanna J Marriott, Deena Kelly Costa","doi":"10.1093/jamia/ocae275","DOIUrl":"https://doi.org/10.1093/jamia/ocae275","url":null,"abstract":"<p><strong>Objectives: </strong>Advances in health informatics rapidly expanded use of big-data analytics and electronic health records (EHR) by clinical researchers seeking to optimize interprofessional ICU team care. This study developed and validated a program for extracting interprofessional teams assigned to each patient each shift from EHR event logs.</p><p><strong>Materials and methods: </strong>A retrospective analysis of EHR event logs for mechanically-ventilated patients 18 and older from 5 ICUs in an academic medical center during 1/1/2018-12/31/2019. We defined interprofessional teams as all medical providers (physicians, physician assistants, and nurse practitioners), registered nurses, and respiratory therapists assigned to each patient each shift. We created an EHR event logs-mining program that extracts clinicians who interact with each patient's medical record each shift. The algorithm was validated using the Message Understanding Conference (MUC-6) method against manual chart review of a random sample of 200 patient-shifts from each ICU by two independent reviewers.</p><p><strong>Results: </strong>Our sample included 4559 ICU encounters and 72 846 patient-shifts. Our program extracted 3288 medical providers, 2702 registered nurses, and 219 respiratory therapists linked to these encounters. Eighty-three percent of patient-shift teams included medical providers, 99.3% included registered nurses, and 74.1% included respiratory therapists; 63.4% of shift-level teams included clinicians from all three professions. The program demonstrated 95.9% precision, 96.2% recall, and high face validity.</p><p><strong>Discussion: </strong>Our EHR event logs-mining program has high precision, recall, and validity for identifying patient-levelshift interprofessional teams in ICUs.</p><p><strong>Conclusions: </strong>Algorithmic and artificial intelligence approaches have a strong potential for informing research to optimize patient team assignments and improve ICU care and outcomes.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142839957","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":"Variations in digital health literacy for pediatric caregivers of hospitalized children: implications for digital health equity.","authors":"Steven Crook, Glenn Rosenbluth, David V Glidden, Alicia Fernandez, Chuan-Mei Lee, Lizette Avina, Leslie Magana, Kiana Washington, Naomi S Bardach","doi":"10.1093/jamia/ocae305","DOIUrl":"https://doi.org/10.1093/jamia/ocae305","url":null,"abstract":"<p><strong>Objectives: </strong>We sought to assess whether race, ethnicity, and preferred language were associated with digital health literacy in pediatric caregivers.</p><p><strong>Materials and methods: </strong>We used linear regression to measure associations between 3 eHealth Literacy Questionnaire (eHLQ) domains (score range: 1-4) and demographic characteristics.</p><p><strong>Results: </strong>Non-Latinx White respondents (n = 230) had highest adjusted mean eHLQ scores: 3.44 (95% confidence interval: 3.36-3.52) in \"Ability to engage,\" 3.39 (3.31 to 3.47) in \"Feel safe and in control,\" and 3.34 (3.25 to 3.41) in \"Motivated.\" By contrast, Spanish-preferring Latinx respondents (n = 246) had lower adjusted mean scores across all 3 eHLQ domains: 2.97 (P < .0001), 3.21 (P = .004), and 3.19 (P = .033), respectively.</p><p><strong>Discussion: </strong>Our study contributes insights in variations across ethnoracial and language preference groups by different eHLQ domains, with implications for addressing digital health inequities.</p><p><strong>Conclusion: </strong>Digital health literacy was lower in Spanish-preferring Latinx pediatric caregivers compared to non-Latinx White caregivers across 3 eHLQ domains. It was lower than English-preferring Latinx caregivers in \"Ability.\"</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142839964","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":"Ambient artificial intelligence scribes: utilization and impact on documentation time.","authors":"Stephen P Ma, April S Liang, Shreya J Shah, Margaret Smith, Yejin Jeong, Anna Devon-Sand, Trevor Crowell, Clarissa Delahaie, Caroline Hsia, Steven Lin, Tait Shanafelt, Michael A Pfeffer, Christopher Sharp, Patricia Garcia","doi":"10.1093/jamia/ocae304","DOIUrl":"https://doi.org/10.1093/jamia/ocae304","url":null,"abstract":"<p><strong>Objectives: </strong>To quantify utilization and impact on documentation time of a large language model-powered ambient artificial intelligence (AI) scribe.</p><p><strong>Materials and methods: </strong>This prospective quality improvement study was conducted at a large academic medical center with 45 physicians from 8 ambulatory disciplines over 3 months. Utilization and documentation times were derived from electronic health record (EHR) use measures.</p><p><strong>Results: </strong>The ambient AI scribe was utilized in 9629 of 17 428 encounters (55.25%) with significant interuser heterogeneity. Compared to baseline, median time per note reduced significantly by 0.57 minutes. Median daily documentation, afterhours, and total EHR time also decreased significantly by 6.89, 5.17, and 19.95 minutes/day, respectively.</p><p><strong>Discussion: </strong>An early pilot of an ambient AI scribe demonstrated robust utilization and reduced time spent on documentation and in the EHR. There was notable individual-level heterogeneity.</p><p><strong>Conclusion: </strong>Large language model-powered ambient AI scribes may reduce documentation burden. Further studies are needed to identify which users benefit most from current technology and how future iterations can support a broader audience.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142839833","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":"Effectiveness of electronic medical record-based strategies for death and hospital admission endpoint capture in pragmatic clinical trials.","authors":"Maryam Rahafrooz, Danne C Elbers, Jay R Gopal, Junling Ren, Nathan H Chan, Cenk Yildirim, Akshay S Desai, Abigail A Santos, Karen Murray, Thomas Havighurst, Jacob A Udell, Michael E Farkouh, Lawton Cooper, J Michael Gaziano, Orly Vardeny, Lu Mao, KyungMann Kim, David R Gagnon, Scott D Solomon, Jacob Joseph","doi":"10.1093/jamia/ocae303","DOIUrl":"https://doi.org/10.1093/jamia/ocae303","url":null,"abstract":"<p><strong>Objective: </strong>Event capture in clinical trials is resource-intensive, and electronic medical records (EMRs) offer a potential solution. This study develops algorithms for EMR-based death and hospitalization capture and compares them with traditional event capture methods.</p><p><strong>Materials and methods: </strong>We compared the effectiveness of EMR-based event capture and site-captured events adjudicated by a clinical endpoint committee in the multi-center INfluenza Vaccine to Effectively Stop cardio Thoracic Events and Decompensated heart failure (INVESTED) trial for participants from the Veterans Affairs healthcare system. Varying time windows around event dates were used to optimize events matching. The algorithms were externally validated for heart failure hospitalizations in the Medical Information Mart for Intensive Care (MIMIC)-IV database.</p><p><strong>Results: </strong>We observed 100% sensitivity for death events with a 1-day window. Sensitivity for cardiovascular, heart failure, pulmonary, and nonspecific cardiopulmonary hospitalizations using discharge diagnosis codes varied between 75% and 95%. Including Centers for Medicare & Medicaid Services data improved sensitivity with no meaningful decrease in specificity. The MIMIC-IV analysis showed 82% sensitivity and 99% specificity for heart failure hospitalizations.</p><p><strong>Discussion: </strong>EMR-based method accurately identifies all-cause mortality and demonstrates high accuracy for cardiopulmonary hospitalizations. This study underscores the importance of optimal time windows, data completeness, and domain variability in EMR systems.</p><p><strong>Conclusion: </strong>EMR-based methods are effective strategies for capturing death and hospitalizations in clinical trials; however, their effectiveness may be influenced by the complexity of events and domain variability across different EMR systems. Nonetheless, EMR-based methods can serve as a valuable complement to traditional methods.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142822674","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":"Clinical implementation of preemptive pharmacogenomics testing for personalized medicine at an academic medical center.","authors":"Bani Tamraz, Jaekyu Shin, Raman Khanna, Jessica Van Ziffle, Susan Knowles, Susan Stregowski, Eunice Wan, Rajesh Kamath, Christopher Collins, Choeying Phunsur, Benjamin Tsai, Patsy Kong, Clari Calanoc, Aleta Pollard, Rajeev Sawhney, Jennifer Pleiman, Walter Patrick Devine, Rhiannon Croci, Aparna Sashikanth, Lisa Kroon, Russell Cucina, Aleks Rajkovic","doi":"10.1093/jamia/ocae293","DOIUrl":"https://doi.org/10.1093/jamia/ocae293","url":null,"abstract":"<p><strong>Objective: </strong>This article describes the implementation of preemptive clinical pharmacogenomics (PGx) testing linked to an automated clinical decision support (CDS) system delivering actionable PGx information to clinicians at the point of care at UCSF Health, a large Academic Medical Center.</p><p><strong>Methods: </strong>A multidisciplinary team developed the strategic vision for the PGx program. Drug-gene interactions of interest were compiled, and actionable alleles identified. A genotyping platform was selected and validated in-house. Following HIPAA protocols, genotype results were electronically transferred and stored in electronic health records (EHRs). CDS was developed and integrated with electronic prescribing.</p><p><strong>Results: </strong>We developed a customized PGx program for 56 medications and 15 genes. Two hundred thirty-three pharmacogenomic prescribing alerts and 15 pharmacogenomic testing prompts, approved by clinicians, were built into EHR to deliver actionable clinical PGx information to clinicians.</p><p><strong>Conclusions: </strong>Our multidisciplinary team successfully implemented preemptive PGx testing linked to point-of-care CDS to guide clinicians with precise medication decision-making.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142813473","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":"Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications.","authors":"Maryam Zolnoori, Ali Zolnour, Sasha Vergez, Sridevi Sridharan, Ian Spens, Maxim Topaz, James M Noble, Suzanne Bakken, Julia Hirschberg, Kathryn Bowles, Nicole Onorato, Margaret V McDonald","doi":"10.1093/jamia/ocae300","DOIUrl":"https://doi.org/10.1093/jamia/ocae300","url":null,"abstract":"<p><strong>Background: </strong>Mild cognitive impairment and early-stage dementia significantly impact healthcare utilization and costs, yet more than half of affected patients remain underdiagnosed. This study leverages audio-recorded patient-nurse verbal communication in home healthcare settings to develop an artificial intelligence-based screening tool for early detection of cognitive decline.</p><p><strong>Objective: </strong>To develop a speech processing algorithm using routine patient-nurse verbal communication and evaluate its performance when combined with electronic health record (EHR) data in detecting early signs of cognitive decline.</p><p><strong>Method: </strong>We analyzed 125 audio-recorded patient-nurse verbal communication for 47 patients from a major home healthcare agency in New York City. Out of 47 patients, 19 experienced symptoms associated with the onset of cognitive decline. A natural language processing algorithm was developed to extract domain-specific linguistic and interaction features from these recordings. The algorithm's performance was compared against EHR-based screening methods. Both standalone and combined data approaches were assessed using F1-score and area under the curve (AUC) metrics.</p><p><strong>Results: </strong>The initial model using only patient-nurse verbal communication achieved an F1-score of 85 and an AUC of 86.47. The model based on EHR data achieved an F1-score of 75.56 and an AUC of 79. Combining patient-nurse verbal communication with EHR data yielded the highest performance, with an F1-score of 88.89 and an AUC of 90.23. Key linguistic indicators of cognitive decline included reduced linguistic diversity, grammatical challenges, repetition, and altered speech patterns. Incorporating audio data significantly enhanced the risk prediction models for hospitalization and emergency department visits.</p><p><strong>Discussion: </strong>Routine verbal communication between patients and nurses contains critical linguistic and interactional indicators for identifying cognitive impairment. Integrating audio-recorded patient-nurse communication with EHR data provides a more comprehensive and accurate method for early detection of cognitive decline, potentially improving patient outcomes through timely interventions. This combined approach could revolutionize cognitive impairment screening in home healthcare settings.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142820030","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":"Using large language models to detect outcomes in qualitative studies of adolescent depression.","authors":"Alison W Xin, Dylan M Nielson, Karolin Rose Krause, Guilherme Fiorini, Nick Midgley, Francisco Pereira, Juan Antonio Lossio-Ventura","doi":"10.1093/jamia/ocae298","DOIUrl":"https://doi.org/10.1093/jamia/ocae298","url":null,"abstract":"<p><strong>Objective: </strong>We aim to use large language models (LLMs) to detect mentions of nuanced psychotherapeutic outcomes and impacts than previously considered in transcripts of interviews with adolescent depression. Our clinical authors previously created a novel coding framework containing fine-grained therapy outcomes beyond the binary classification (eg, depression vs control) based on qualitative analysis embedded within a clinical study of depression. Moreover, we seek to demonstrate that embeddings from LLMs are informative enough to accurately label these experiences.</p><p><strong>Materials and methods: </strong>Data were drawn from interviews, where text segments were annotated with different outcome labels. Five different open-source LLMs were evaluated to classify outcomes from the coding framework. Classification experiments were carried out in the original interview transcripts. Furthermore, we repeated those experiments for versions of the data produced by breaking those segments into conversation turns, or keeping non-interviewer utterances (monologues).</p><p><strong>Results: </strong>We used classification models to predict 31 outcomes and 8 derived labels, for 3 different text segmentations. Area under the ROC curve scores ranged between 0.6 and 0.9 for the original segmentation and 0.7 and 1.0 for the monologues and turns.</p><p><strong>Discussion: </strong>LLM-based classification models could identify outcomes important to adolescents, such as friendships or academic and vocational functioning, in text transcripts of patient interviews. By using clinical data, we also aim to better generalize to clinical settings compared to studies based on public social media data.</p><p><strong>Conclusion: </strong>Our results demonstrate that fine-grained therapy outcome coding in psychotherapeutic text is feasible, and can be used to support the quantification of important outcomes for downstream uses.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142814632","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":"Toward an artificial intelligence code of conduct for health and healthcare: implications for the biomedical informatics community.","authors":"Philip R O Payne, Kevin B Johnson, Thomas M Maddox, Peter J Embi, Kenneth D Mandl, Deven McGraw, Suchi Saria, Laura Adams","doi":"10.1093/jamia/ocae306","DOIUrl":"https://doi.org/10.1093/jamia/ocae306","url":null,"abstract":"<p><strong>Introduction: </strong>The rapid advancement of artificial intelligence (AI) has led to significant transformations in health and healthcare. As AI technologies continue to evolve, there is an urgent need to establish a unified framework that guides the design, implementation, and evaluation of AI-driven interventions across individual and population health contexts.</p><p><strong>Approach: </strong>In response to this need, the National Academy of Medicine (NAM) has initiated the development of an AI code of conduct (AICC) through its Digital Health Action Collaborative. This code of conduct is grounded in shared principles and commitments, aiming to actualize ethical and effective AI practices within the broader health and healthcare ecosystem. Given its specialized expertise and insight, the biomedical informatics (BMI) community plays a pivotal role in shaping and applying these guidelines.</p><p><strong>Recommendations: </strong>We, as members of the AICC Steering Committee and the NAM Digital Health Action Collaborative, urge BMI educators, researchers, and practitioners to engage actively in refining and implementing the AICC. This involvement is critical to ensuring that the code is robust, applicable, and continuously improved to meet the evolving challenges facing health and healthcare.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142808378","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":"Regulation of artificial intelligence in healthcare: Clinical Laboratory Improvement Amendments (CLIA) as a model.","authors":"Brian R Jackson, Mark P Sendak, Anthony Solomonides, Suresh Balu, Dean F Sittig","doi":"10.1093/jamia/ocae296","DOIUrl":"https://doi.org/10.1093/jamia/ocae296","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the potential to adapt an existing technology regulatory model, namely the Clinical Laboratory Improvement Amendments (CLIA), for clinical artificial intelligence (AI).</p><p><strong>Materials and methods: </strong>We identify overlap in the quality management requirements for laboratory testing and clinical AI.</p><p><strong>Results: </strong>We propose modifications to the CLIA model that could make it suitable for oversight of clinical AI.</p><p><strong>Discussion: </strong>In national discussions of clinical AI, there has been surprisingly little consideration of this longstanding model for local technology oversight. While CLIA was specifically designed for laboratory testing, most of its principles are applicable to other technologies in patient care.</p><p><strong>Conclusion: </strong>A CLIA-like approach to regulating clinical AI would be complementary to the more centralized schemes currently under consideration, and it would ensure institutional and professional accountability for the longitudinal quality management of clinical AI.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142830530","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}