NPJ Digital Medicine最新文献_第4页

An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models 基于大型语言模型的临床记录端到端罕见病表型分析的人工智能框架

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-15 DOI: 10.1038/s41746-026-03275-0

Cathy Shyr,Yan Hu,Rory J. Tinker,Thomas A. Cassini,Kevin W. Byram,Rizwan Hamid,Daniel V. Fabbri,Adam Wright,Josh F. Peterson,Undiagnosed Diseases Network,Lisa Bastarache,Hua Xu

{"title":"An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models","authors":"Cathy Shyr,Yan Hu,Rory J. Tinker,Thomas A. Cassini,Kevin W. Byram,Rizwan Hamid,Daniel V. Fabbri,Adam Wright,Josh F. Peterson,Undiagnosed Diseases Network,Lisa Bastarache,Hua Xu","doi":"10.1038/s41746-026-03275-0","DOIUrl":"https://doi.org/10.1038/s41746-026-03275-0","url":null,"abstract":"Phenotyping is fundamental to rare disease diagnosis, but manually curating structured phenotypes from clinical notes is labor intensive and difficult to scale. Existing artificial intelligence (AI) approaches optimize individual components of phenotyping but generally do not operationalize the full workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontology (HPO) terms, and prioritizing rare disease-relevant HPO terms. We developed RARE-PHENIX, an end-to-end AI framework for rare disease phenotyping that integrates large language model-based phenotype extraction, ontology-grounded standardization to HPO terms, and supervised ranking of HPO terms. We trained RARE-PHENIX using data from 2671 patients across 11 Undiagnosed Diseases Network clinical sites, and externally validated it on 16,357 real-world clinical notes from 143 patients at Vanderbilt University Medical Center. Our findings suggest RARE-PHENIX generates structured, prioritized HPO terms highly concordant with clinician curation, demonstrates potential downstream disease-prioritization signal, and may support human-in-the-loop rare disease phenotyping in real-world settings.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"168 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection TrajOnco：用于多种癌症早期检测的纵向电子病历时间推理的多智能体框架

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-15 DOI: 10.1038/s41746-026-03377-9

Sihang Zeng,Young Won Kim,Wilson Lau,Ehsan Alipour,Ruth Etzioni,Meliha Yetisgen,Anand Oka

{"title":"TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection","authors":"Sihang Zeng,Young Won Kim,Wilson Lau,Ehsan Alipour,Ruth Etzioni,Meliha Yetisgen,Anand Oka","doi":"10.1038/s41746-026-03377-9","DOIUrl":"https://doi.org/10.1038/s41746-026-03377-9","url":null,"abstract":"Abstract Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling such complex patient trajectories remains challenging. We present TrajOnco, a training-free, multi-agent large language model (LLM) framework designed for scalable multi-cancer early detection. Using a chain-of-agents architecture with long-term memory, TrajOnco performs temporal reasoning over sequential clinical events to generate patient-level summaries, evidence-linked rationales, and predicted risk scores. We evaluated TrajOnco on de-identified Truveta EHR data across 15 cancer types using matched case-control cohorts, predicting risk of cancer diagnosis at 1 year. In zero-shot evaluation, TrajOnco achieved AUROCs of 0.64–0.80, performing comparably to supervised machine learning in a lung cancer benchmark while demonstrating better temporal reasoning than single-agent LLMs. The multi-agent design also enabled effective temporal reasoning with smaller-capacity models such as GPT-4.1-mini. The groundedness of TrajOnco’s output was supported by human evaluation. Furthermore, TrajOnco’s interpretable reasoning outputs can be aggregated to reveal population-level risk patterns that align with established clinical knowledge. These findings highlight the potential of multi-agent LLMs to execute interpretable temporal reasoning over longitudinal EHRs, advancing both scalable multi-cancer early detection and clinical insight generation.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"11 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Current status and future outlook of artificial intelligence and automation in intravenous infusion systems. 人工智能与自动化在静脉输液系统中的应用现状与展望。

IF 18 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03291-0

Islam M Ibrahim, Rahma A Elkomy, Merna A Mohamed, Fatemah A Farok, Roaa E Emam, Salma A Kamel, Reham M Asem

{"title":"Current status and future outlook of artificial intelligence and automation in intravenous infusion systems.","authors":"Islam M Ibrahim, Rahma A Elkomy, Merna A Mohamed, Fatemah A Farok, Roaa E Emam, Salma A Kamel, Reham M Asem","doi":"10.1038/s41746-026-03291-0","DOIUrl":"10.1038/s41746-026-03291-0","url":null,"abstract":"<p><p>The combination of the Internet of Things (IoT), artificial intelligence (AI), and wearable biosensors is transforming healthcare by allowing continuous, real-time monitoring and more intelligent clinical decision-making. This review explores AI-driven monitoring, smart intravenous (IV) infusion automation, and wearable biosensors, and proposes Intelligent IV Automation and Smart Patient Synchronization (INFUSYNC), a conceptual framework synchronizing monitoring, automated fluid delivery, and predictive analytics. The literature shows meaningful progress: wearables increasingly support non-contact monitoring with near clinical-grade accuracy for select parameters, while infusion pumps with dose-error-reduction and AI-assisted decision support are reported to improve delivery precision and safety. Predictive models further support early detection of physiological decline. Progress remains uneven, however: most AI-enabled infusion systems are prototype-stage, closed-loop control remains rare, and interoperability, data security, and privacy remain underdeveloped. Future systems will need compatible, security-by-design, clinically validated, feedback-controlled architectures. Overall, this review outlines a clear but early-stage trajectory toward integrated smart-health environments for IV therapy.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"9 1","pages":""},"PeriodicalIF":18.0,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669359/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149183290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sequence models reveal diagnosis accumulation pathways beyond comorbidity burden in population-scale hospital data 序列模型揭示了在人口规模的医院数据中超越合并症负担的诊断积累途径

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03265-2

Katharina Ledebur,Mitja Devetak,Peter Klimek

引用次数: 0

From compliance to competence: a multi-level model for AI governance in undergraduate medical education. 从服从到胜任：本科医学教育人工智能治理的多层次模型

IF 18 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03390-y

Juan José Gualda-Gea, Lourdes Estefanía Barón-Miras, Maria Jesús Bertran, Alberto L Garcia-Basteiro, Guillermo Mena, Marta Aldea, Gemina Santana, Jaume Grau, Andrés Prat Marin, Isabel Torá-Rocamora, Antoni Trilla

引用次数: 0

From research to clinical practice: Expert consensus on Neuroimaging AI tools for the Memory clinic (Neuro-AIM) 从研究到临床实践：记忆临床神经成像人工智能工具（neuroaim）专家共识

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03296-9

Natasha Clarke,Mathias Huybrechts,Jay Amin,Lewis Hotchkiss,James Leighs,Matthew Leming,Usman Saeed,Catherine J. Scott,Dirk Smeets,Angela Tam,Stefano Tamburin,Geert Vanhooren,Meike W. Vernooij,Jennifer Camaradou,David J. Llewellyn,Timothy Rittman,Rose Bruffaerts

{"title":"From research to clinical practice: Expert consensus on Neuroimaging AI tools for the Memory clinic (Neuro-AIM)","authors":"Natasha Clarke,Mathias Huybrechts,Jay Amin,Lewis Hotchkiss,James Leighs,Matthew Leming,Usman Saeed,Catherine J. Scott,Dirk Smeets,Angela Tam,Stefano Tamburin,Geert Vanhooren,Meike W. Vernooij,Jennifer Camaradou,David J. Llewellyn,Timothy Rittman,Rose Bruffaerts","doi":"10.1038/s41746-026-03296-9","DOIUrl":"https://doi.org/10.1038/s41746-026-03296-9","url":null,"abstract":"Abstract Although AI tools for neuroimaging show considerable promise in the diagnosis, prognosis, and management of neurodegenerative disorders, their uptake in memory clinics has been limited. A key barrier is lack of consensus on their effective design and implementation. Here we establish expert consensus on the specific goals, usage and challenges of AI tools for neuroimaging in the memory clinic using a Delphi process. Sixteen experts from clinical, academic, and industry backgrounds participated in three rounds of questionnaires, coordinated by the Imaging Working Group of the Deep Dementia Phenotyping (DEMON) network, with support from a patient and public involvement representative. Consensus was reached on eight statements covering four themes: purpose, quality, interactions with clinicians and memory clinics, and privacy and ethics. Implementation of these recommendations will further the adoption of AI neuroimaging tools from research to clinical practice, improving diagnostic and care pathways for patient benefit.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"8 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FedFound: Federated Foundation Model for GI endoscopy imaging FedFound：用于胃肠道内镜成像的联邦基金会模型

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03281-2

Alina Devkota,Annahita Amireskandari,Joel Palko,Soban Maan,Shyam Thakkar,Tapan Khan,Xiajun Jiang,Donald Adjeroh,Binod Bhattarai,Prashnna Gyawali

引用次数: 0

Author Correction: Large language models are powerful electronic health record encoders. 作者更正：大型语言模型是功能强大的电子健康记录编码器。

IF 18 1区医学

NPJ Digital Medicine Pub Date : 2026-10-14 DOI: 10.1038/s41746-026-03220-1

Stefan Hegselmann, Georg von Arnim, Tillmann Rheude, Noel Kronenberg, David Sontag, Gerhard Hindricks, Roland Eils, Benjamin Wild

引用次数: 0

Electronic health record developer adherence to federal AI risk transparency requirements 电子健康记录开发人员遵守联邦人工智能风险透明度要求