Npj health systemsPub Date : 2025-01-01Epub Date: 2025-07-15DOI: 10.1038/s44401-025-00027-2
Marian Obuseh, Sneha Singh, Nicholas E Anton, Robin Gardiner, Dimitrios Stefanidis, Denny Yu
{"title":"Feasibility of large language models for assessing and coaching surgeons' non-technical skills.","authors":"Marian Obuseh, Sneha Singh, Nicholas E Anton, Robin Gardiner, Dimitrios Stefanidis, Denny Yu","doi":"10.1038/s44401-025-00027-2","DOIUrl":"10.1038/s44401-025-00027-2","url":null,"abstract":"<p><p>This study demonstrates Large Language models (LLMs) to assess and coach surgeons on their non-technical skills, traditionally evaluated through subjective and resource-intensive methods. Llama 3.1 and Mistral effectively analyzed robotic-assisted surgery transcripts, identified exemplar and non-exemplar behaviors, and autonomously generated structured coaching feedback to guide surgeons' improvement. Our findings highlight the potential of LLMs as scalable, data-driven tools for enhancing surgical education and supporting consistent coaching practices.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"25"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12263418/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144661698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-07-23DOI: 10.1038/s44401-025-00030-7
Karlene Cunningham, Valentina Mărginean, Ray Hylock
{"title":"Navigating promise and perils: applying artificial intelligence to the perinatal mental health care cascade.","authors":"Karlene Cunningham, Valentina Mărginean, Ray Hylock","doi":"10.1038/s44401-025-00030-7","DOIUrl":"10.1038/s44401-025-00030-7","url":null,"abstract":"<p><p>The perinatal mental health care cascade is wrought with systemic issues contributing to under-detection and outcome disparities. Herein, we examine its unique characteristics and explore how artificial intelligence (AI) may improve care while acknowledging associated ethical considerations and implementation challenges. We emphasize the need for policy reforms to screening, data collection, and regulatory processes to build ethical and robust AI-enhanced health system infrastructures.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"26"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12286856/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144736537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-07-30DOI: 10.1038/s44401-025-00034-3
Henrique A Lima, Pedro H F S Trocoli-Couto, Marzia Zaman, Débora C Engelmann, Rosalind Parkes-Ratanshi, Leah Junck, Brenda Hendry, Amelia Taylor, Michelle El Kawak, Nirmal Ravi, Henrique D P Santos, Timothy M Pawlik, Vivian Resende
{"title":"Spotlighting healthcare frontline workers´ perceptions on artificial intelligence across the globe.","authors":"Henrique A Lima, Pedro H F S Trocoli-Couto, Marzia Zaman, Débora C Engelmann, Rosalind Parkes-Ratanshi, Leah Junck, Brenda Hendry, Amelia Taylor, Michelle El Kawak, Nirmal Ravi, Henrique D P Santos, Timothy M Pawlik, Vivian Resende","doi":"10.1038/s44401-025-00034-3","DOIUrl":"https://doi.org/10.1038/s44401-025-00034-3","url":null,"abstract":"<p><p>We sought to define healthcare workers' (HCW) views on the integration of generative artificial intelligence (AI) into healthcare delivery and to explore the associated challenges, opportunities, and ethical considerations in low- and middle-income countries (LMICs). We analysed unified data from selected 2023 Gates Foundation AI Grand Challenges projects using a mixed-methods, cross-sectional survey evaluated by an international panel across eight countries. Perceptions were rated on a simplified three-point Likert scale (sceptical, practical, enthusiastic). Among 191 frontline HCWs who interacted with AI tools, 617 responses were assessed by nine evaluators. Enthusiastic responses accounted for the majority (75.4%), while 21.6% were practical and only 3.0% were sceptical. The overall interclass correlation coefficient of 0.93 (95%CI: 0.91-0.94, with an average rating <i>k</i> = 9) indicated excellent inter-rater reliability. While quantitative data underscored a generally positive attitude towards AI, qualitative findings revealed recurring cultural and linguistic barriers and ethical concerns. This is a unique study analysing data from the first applications of generative AI in health in LMICs. these findings offer early insights into generative AI implementation in LMIC healthcare settings and highlights both its transformative potential and the need for careful policy and contextual adaptation.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"28"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12310525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144777633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-04-24DOI: 10.1038/s44401-025-00015-6
Shuang Zhou, Mingquan Lin, Sirui Ding, Jiashuo Wang, Canyu Chen, Genevieve B Melton, James Zou, Rui Zhang
{"title":"Explainable differential diagnosis with dual-inference large language models.","authors":"Shuang Zhou, Mingquan Lin, Sirui Ding, Jiashuo Wang, Canyu Chen, Genevieve B Melton, James Zou, Rui Zhang","doi":"10.1038/s44401-025-00015-6","DOIUrl":"https://doi.org/10.1038/s44401-025-00015-6","url":null,"abstract":"<p><p>Automatic differential diagnosis (DDx) involves identifying potential conditions that could explain a patient's symptoms and its accurate interpretation is of substantial significance. While large language models (LLMs) have demonstrated remarkable diagnostic accuracy, their capability to generate high-quality DDx explanations remains underexplored, largely due to the absence of specialized evaluation datasets and the inherent challenges of complex reasoning in LLMs. Therefore, building a tailored dataset and developing novel methods to elicit LLMs for generating precise DDx explanations are worth exploring. We developed the first publicly available DDx dataset, comprising expert-derived explanations for 570 clinical notes, to evaluate DDx explanations. Meanwhile, we proposed a novel framework, Dual-Inf, that could effectively harness LLMs to generate high-quality DDx explanations. To the best of our knowledge, it is the first study to tailor LLMs for DDx explanation and comprehensively evaluate their explainability. Overall, our study bridges a critical gap in DDx explanation, enhancing clinical decision-making.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"12"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-06-18DOI: 10.1038/s44401-025-00024-5
Zhiyuan Wang, Runze Yan, Sherilyn Francis, Carmen Diaz, Tabor Flickinger, Yufen Lin, Xiao Hu, Laura E Barnes, Virginia LeBaron
{"title":"Stakeholder-centric participation in large language models enhanced health systems.","authors":"Zhiyuan Wang, Runze Yan, Sherilyn Francis, Carmen Diaz, Tabor Flickinger, Yufen Lin, Xiao Hu, Laura E Barnes, Virginia LeBaron","doi":"10.1038/s44401-025-00024-5","DOIUrl":"10.1038/s44401-025-00024-5","url":null,"abstract":"<p><p>Large language models (LLMs) are transforming healthcare by advancing clinical decision support, patient care, and administrative efficiency. However, effectively and sustainably integrating LLMs into healthcare systems requires addressing participatory gaps that may hinder alignment with stakeholders' practical and ethical needs. This paper explores how participatory methods can be applied throughout the development lifecycle of LLM-enhanced health systems (LLMHS), arguing that: (1) participatory approaches are critical for engaging stakeholders in LLMHS development, and (2) LLM techniques can create novel participatory opportunities that reinforce stakeholder engagement while driving technical innovation in LLMHS. This dual perspective highlights the potential of LLMHS to align technical sophistication with real-world healthcare demands, paving the way for next-generation health systems.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"22"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12176632/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144478498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-06-02DOI: 10.1038/s44401-025-00022-7
James Anibal, Adam Landa, Hang Nguyen, Veronica Daoud, Tram Le, Hannah Huth, Miranda Song, Alec Peltekian, Ashley Shin, Lindsey Hazen, Anna Christou, Jocelyne Rivera, Robert Morhard, Jacqueline Brenner, Ulas Bagci, Ming Li, Yael Bensoussan, David Clifton, Bradford Wood
{"title":"Generative AI and unstructured audio data for precision public health.","authors":"James Anibal, Adam Landa, Hang Nguyen, Veronica Daoud, Tram Le, Hannah Huth, Miranda Song, Alec Peltekian, Ashley Shin, Lindsey Hazen, Anna Christou, Jocelyne Rivera, Robert Morhard, Jacqueline Brenner, Ulas Bagci, Ming Li, Yael Bensoussan, David Clifton, Bradford Wood","doi":"10.1038/s44401-025-00022-7","DOIUrl":"10.1038/s44401-025-00022-7","url":null,"abstract":"<p><p>In this study, transcribed videos about personal experiences with COVID-19 were used for variant classification. The o1 LLM was used to summarize the transcripts, excluding references to dates, vaccinations, testing methods, and other variables that were correlated with specific variants but unrelated to changes in the disease. This step was necessary to effectively simulate model deployment in the early days of a pandemic when subtle changes in symptomatology may be the only viable biomarkers of disease mutations. The embedded summaries were used for training a neural network to predict the variant status of the speaker as \"Omicron\" or \"Pre-Omicron\", resulting in an AUROC score of 0.823. This was compared to a neural network model trained on binary symptom data, which obtained a lower AUROC score of 0.769. Results of the study illustrated the future value of LLMs and audio data in the design of pandemic management tools for health systems.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"19"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12129811/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144228369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-02-03DOI: 10.1038/s44401-024-00011-2
Emma Croxford, Yanjun Gao, Nicholas Pellegrino, Karen Wong, Graham Wills, Elliot First, Frank Liao, Cherodeep Goswami, Brian Patterson, Majid Afshar
{"title":"Current and future state of evaluation of large language models for medical summarization tasks.","authors":"Emma Croxford, Yanjun Gao, Nicholas Pellegrino, Karen Wong, Graham Wills, Elliot First, Frank Liao, Cherodeep Goswami, Brian Patterson, Majid Afshar","doi":"10.1038/s44401-024-00011-2","DOIUrl":"10.1038/s44401-024-00011-2","url":null,"abstract":"<p><p>Large Language Models have expanded the potential for clinical Natural Language Generation (NLG), presenting new opportunities to manage the vast amounts of medical text. However, their use in such high-stakes environments necessitate robust evaluation workflows. In this review, we investigated the current landscape of evaluation metrics for NLG in healthcare and proposed a future direction to address the resource constraints of expert human evaluation while balancing alignment with human judgments.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11928168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143695072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-05-01DOI: 10.1038/s44401-025-00018-3
Zhen Hou, Hao Liu, Jiang Bian, Xing He, Yan Zhuang
{"title":"Enhancing medical coding efficiency through domain-specific fine-tuned large language models.","authors":"Zhen Hou, Hao Liu, Jiang Bian, Xing He, Yan Zhuang","doi":"10.1038/s44401-025-00018-3","DOIUrl":"10.1038/s44401-025-00018-3","url":null,"abstract":"<p><p>Medical coding is essential for healthcare operations yet remains predominantly manual, error-prone (up to 20%), and costly (up to $18.2 billion annually). Although large language models (LLMs) have shown promise in natural language processing, their application to medical coding has produced limited accuracy. In this study, we evaluated whether fine-tuning LLMs with specialized ICD-10 knowledge can automate code generation across clinical documentation. We adopted a two-phase approach: initial fine-tuning using 74,260 ICD-10 code-description pairs, followed by enhanced training to address linguistic and lexical variations. Evaluations using a proprietary model (GPT-4o mini) on a cloud platform and an open-source model (Llama) on local GPUs demonstrated that initial fine-tuning increased exact matching from <1% to 97%, while enhanced fine-tuning further improved performance in complex scenarios, with real-world clinical notes achieving 69.20% exact match and 87.16% category match. These findings indicate that domain-specific fine-tuned LLMs can reduce manual burdens and improve reliability.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"14"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12045799/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2025-01-01Epub Date: 2025-01-25DOI: 10.1038/s44401-024-00009-w
Betina Idnay, Zihan Xu, William G Adams, Mohammad Adibuzzaman, Nicholas R Anderson, Neil Bahroos, Douglas S Bell, Cody Bumgardner, Thomas Campion, Mario Castro, James J Cimino, I Glenn Cohen, David Dorr, Peter L Elkin, Jungwei W Fan, Todd Ferris, David J Foran, David Hanauer, Mike Hogarth, Kun Huang, Jayashree Kalpathy-Cramer, Manoj Kandpal, Niranjan S Karnik, Avnish Katoch, Albert M Lai, Christophe G Lambert, Lang Li, Christopher Lindsell, Jinze Liu, Zhiyong Lu, Yuan Luo, Peter McGarvey, Eneida A Mendonca, Parsa Mirhaji, Shawn Murphy, John D Osborne, Ioannis C Paschalidis, Paul A Harris, Fred Prior, Nicholas J Shaheen, Nawar Shara, Ida Sim, Umberto Tachinardi, Lemuel R Waitman, Rosalind J Wright, Adrian H Zai, Kai Zheng, Sandra Soo-Jin Lee, Bradley A Malin, Karthik Natarajan, W Nicholson Price Ii, Rui Zhang, Yiye Zhang, Hua Xu, Jiang Bian, Chunhua Weng, Yifan Peng
{"title":"Environment scan of generative AI infrastructure for clinical and translational science.","authors":"Betina Idnay, Zihan Xu, William G Adams, Mohammad Adibuzzaman, Nicholas R Anderson, Neil Bahroos, Douglas S Bell, Cody Bumgardner, Thomas Campion, Mario Castro, James J Cimino, I Glenn Cohen, David Dorr, Peter L Elkin, Jungwei W Fan, Todd Ferris, David J Foran, David Hanauer, Mike Hogarth, Kun Huang, Jayashree Kalpathy-Cramer, Manoj Kandpal, Niranjan S Karnik, Avnish Katoch, Albert M Lai, Christophe G Lambert, Lang Li, Christopher Lindsell, Jinze Liu, Zhiyong Lu, Yuan Luo, Peter McGarvey, Eneida A Mendonca, Parsa Mirhaji, Shawn Murphy, John D Osborne, Ioannis C Paschalidis, Paul A Harris, Fred Prior, Nicholas J Shaheen, Nawar Shara, Ida Sim, Umberto Tachinardi, Lemuel R Waitman, Rosalind J Wright, Adrian H Zai, Kai Zheng, Sandra Soo-Jin Lee, Bradley A Malin, Karthik Natarajan, W Nicholson Price Ii, Rui Zhang, Yiye Zhang, Hua Xu, Jiang Bian, Chunhua Weng, Yifan Peng","doi":"10.1038/s44401-024-00009-w","DOIUrl":"10.1038/s44401-024-00009-w","url":null,"abstract":"<p><p>This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the CTSA Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis reveals that 53% of institutions identified data security as a primary concern, followed by lack of clinician trust (50%) and AI bias (44%), which must be addressed to ensure the ethical and effective implementation of GenAI technologies.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"2 1","pages":"4"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11762411/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Npj health systemsPub Date : 2024-01-01Epub Date: 2024-12-23DOI: 10.1038/s44401-024-00006-z
Jiajie Zhang, Susan H Fenton
{"title":"Preparing healthcare education for an AI-augmented future.","authors":"Jiajie Zhang, Susan H Fenton","doi":"10.1038/s44401-024-00006-z","DOIUrl":"10.1038/s44401-024-00006-z","url":null,"abstract":"<p><p>Artificial intelligence (AI) fundamentally transforms healthcare education as a knowledge enterprise, creating a distributed cognitive system composed of the human brain, which remains relatively unchanged, and AI-based knowledge and cognitive functions, which have accelerated exponentially in scale and power. Education must focus on developing skills to collaborate with AI and on achieving outcomes like problems solved and discoveries made. Curriculum and education policies also need to adapt to this transformation.</p>","PeriodicalId":520349,"journal":{"name":"Npj health systems","volume":"1 1","pages":"4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11666452/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
