NPJ Digital Medicine最新文献_第7页

Early prediction of prolonged ICU stay in sepsis patients using an explainable hybrid deep learning model 使用可解释的混合深度学习模型早期预测败血症患者ICU住院时间延长

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-09 DOI: 10.1038/s41746-026-03387-7

Muhammad Salman,JinCheol Park,Seung Park

{"title":"Early prediction of prolonged ICU stay in sepsis patients using an explainable hybrid deep learning model","authors":"Muhammad Salman,JinCheol Park,Seung Park","doi":"10.1038/s41746-026-03387-7","DOIUrl":"https://doi.org/10.1038/s41746-026-03387-7","url":null,"abstract":"Abstract Sepsis remains a leading cause of intensive care unit (ICU) admission and is frequently associated with prolonged ICU stay, which contributes to increased morbidity, healthcare utilization, and strain on critical care resources. Despite widespread use, existing clinical severity scores inadequately capture the individual risk of prolonged ICU stay in sepsis. We developed a hybrid deep learning (FT-TabNet) model with an adaptive gated fusion framework to predict prolonged ICU stay (>4 days) using 17 routinely collected Sequential Organ Failure Assessment (SOFA)-based features available within the first 24 hours of ICU admission. Model development and internal validation were performed using the MIMIC-IV dataset, with external validation conducted in a single-center cohort from Chungbuk National University Hospital (CBNUH) and Chungnam National University Hospital (CNUH), South Korea. The hybrid model showed strong discriminative performance in internal validation, achieving an AUROC of 0.848, and consistent performance across the external validation cohort, with modest variability, achieving an AUROC of 0.823 in the CBNUH and 0.781 in the CNUH cohort. SHAP-based explainability enabled transparent, patient-level interpretation of key contributors to prolonged ICU stay risk. These findings suggest that an explainable hybrid deep learning approach can help clinicians to identify patients at risk of prolonged ICU stay early in sepsis, using routine clinical data to support clinical decision-making and ICU resource allocation.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"52 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150048","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

Development and validation of an objective skills scoring system for robotic inguinal hernia repairs 腹股沟疝机器人修复客观技能评分系统的开发与验证

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-09 DOI: 10.1038/s41746-026-03375-x

Aditya Amit Godbole,Maria Clara Morais,Emaad J. Iqbal,Mattia Ballo,Blake T. Beneville,Andrew Yee,Flavio Malcher,Michael M. Awad,Filippo Filicori

{"title":"Development and validation of an objective skills scoring system for robotic inguinal hernia repairs","authors":"Aditya Amit Godbole,Maria Clara Morais,Emaad J. Iqbal,Mattia Ballo,Blake T. Beneville,Andrew Yee,Flavio Malcher,Michael M. Awad,Filippo Filicori","doi":"10.1038/s41746-026-03375-x","DOIUrl":"https://doi.org/10.1038/s41746-026-03375-x","url":null,"abstract":"Abstract Competency-based surgical education requires objective, scalable assessment of technical skill, yet existing rating scales are subjective. Objective performance indicators (OPIs) derived from console kinematics, offer a solution; however, they lack a validated scoring framework. We developed and externally validated an OPI-based scoring system from robotic transabdominal preperitoneal inguinal hernia repairs performed by 6 attendings and 41 trainees at an academic center (2023–2026). Nineteen OPIs across four tasks were grouped into eight domains, reduced by principal component analysis, and integrated into task-specific 0–100 composite scores via ridge logistic regression. Among 2588 tasks from 392 cases, cross-validated AUCs for attending-trainee discrimination were 0.62–0.74, and composite scores increased from postgraduate year 2 to attending (Spearman ρ, 0.94–1.00; P ≤ 0.005). In an independent external cohort (84 observations, 21 cases), the overall AUC was 0.84 (95% CI, 0.69–0.93). This framework enables objective technical skills assessment in robotic hernia repair.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"9 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150047","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

The complexity paradox of generalist AI agents in medicine: exploring GPT-5 for real-world multimodal medical diagnosis 医学中多面手AI代理的复杂性悖论：探索GPT-5在现实世界多模式医学诊断中的应用

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-09 DOI: 10.1038/s41746-026-03325-7

Shaohui Zhang,Jiarong Qian,Kai Zhang,Zhiling Yan,Michael A. Catalano,Adam Kiridly,Omar Toubat,Gregory E. Tasian,Quanzheng Li,Yonghui Wu,Lei Xing,Wei Liu,Hua Xu,Lifang He,Xiang Li,Zhiyong Lu,Lichao Sun,Jing Huang

引用次数: 0

Implementing and Scaling Artificial Intelligence in Low-Resourced Radiation Oncology: A Systematic Review of Deployments 在低资源的放射肿瘤学中实施和扩展人工智能：部署的系统回顾

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-09 DOI: 10.1038/s41746-026-03391-x

Doris Keziah Ndassi,Solomon Kibudde,Sizhuo Meng,Zongwei Zhou,Xun Jia,Heng Li

{"title":"Implementing and Scaling Artificial Intelligence in Low-Resourced Radiation Oncology: A Systematic Review of Deployments","authors":"Doris Keziah Ndassi,Solomon Kibudde,Sizhuo Meng,Zongwei Zhou,Xun Jia,Heng Li","doi":"10.1038/s41746-026-03391-x","DOIUrl":"https://doi.org/10.1038/s41746-026-03391-x","url":null,"abstract":"Abstract Artificial intelligence (AI) has the potential to address workforce shortages and workflow inefficiencies in radiation oncology, particularly in low-resourced settings where limited specialist capacity constrains access to care. This systematic review evaluated AI deployments in radiation oncology in low- and middle-income countries (LMICs) and assessed readiness for safe implementation and scale-up. Following PRISMA 2020 guidelines, six databases were searched from January 2000 through December 2025. Eligible studies were classified using a radiation oncology-specific integration spectrum (Levels 0-4) and evaluated for workflow integration, validation, deployment, and governance characteristics. Eighteen studies met the inclusion criteria. Two studies (11.1%) focused on readiness or governance without clinical AI deployment (Level 0), nine (50.0%) reported task-level applications (Level 1), six (33.3%) demonstrated clinician-supervised workflow integration (Level 2), and one (5.6%) reported cross-stage workflow orchestration (Level 3). No study provided sufficient evidence for classification as Level 4 operation. Validation was predominantly retrospective, and continuous performance monitoring was not reported. AI deployment in LMIC radiation oncology remains concentrated at early stages of integration. This pattern reflects not a lack of innovation, but constraints in validation, workflow maturity, infrastructure, and governance. Safe and scalable deployment will require coordinated advances across these domains.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"86 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150051","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

Human-validated LLM-assisted assessment of a large-scale online precision medicine course in diabetes 人类验证法学硕士辅助评估大规模在线精准医学课程在糖尿病

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-09 DOI: 10.1038/s41746-026-03350-6

Lingsong Kong,Adelle Engmann,Chenchen Zhu,Sally L. Baxter,Amit Dixit,Antony Ross,Alireza Delfarah,Lisa L. Morselli,Delaram Rezaeikhonakdar,Alison Derbenwick Miller,Joseph Yracheta,Ramesh V. Nair,Eva McGhee,Scott Edmiston,Philip S. Tsao,Arash Alavi,Amir Bahmani

引用次数: 0

Beyond language: embodiment, interpersonal synchrony, and multisensory interaction in AI-mediated psychotherapy 超越语言：人工智能介导的心理治疗中的体现、人际同步和多感官互动

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-08 DOI: 10.1038/s41746-026-03344-4

Marte Roel Lesur,Bigna Lenggenhager,Dominique Recher

引用次数: 0

An audit-ready EHR foundation model for order-time medication-safety auditing across health systems 一个审计就绪的EHR基础模型，用于整个卫生系统的订单时间用药安全审计

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-08 DOI: 10.1038/s41746-026-03243-8

Shuang Cao,Rui Li,Ruihua Liu,Alexandre Duprey

引用次数: 0

Early epilepsy detection from electronic health records with large language models 基于大语言模型的电子病历早期癫痫检测

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-08 DOI: 10.1038/s41746-026-03346-2

Shuang Zhou,Kai Yu,Zaifu Zhan,Huixue Zhou,Min Zeng,Feng Xie,Zhiyi Sha,Rui Zhang

引用次数: 0

Infant neurodevelopmental impairment detection via large-scale motion screening with generative learning 基于生式学习的大规模运动筛查检测婴儿神经发育障碍

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-08 DOI: 10.1038/s41746-026-03180-6

Ning Ma,Hui Wang,Xuhui Li,Yu Du,Yonglin Yu,Jiajun Bu,Haifeng Li,Haishuai Wang

引用次数: 0

Digital Transitional Care Management and Lower Hospital Readmissions in Patients with Cancer: An Allocation Study 数字过渡护理管理和降低癌症患者再入院率：一项分配研究

IF 15.2 1区医学

NPJ Digital Medicine Pub Date : 2026-10-08 DOI: 10.1038/s41746-026-03360-4

Bobby Daly,Raymond Baser,Katherine S. Panageas,Jennie Huang,Mayur Pabba,Jennifer R. Cracchiolo,Jessie Holland,AnnMarie Mazzella-Ebstein,Chasity B. Walters,Jill Ackerman,Nitya Raj,Rachel Sanford,Mark Dickson,Alison Moskowitz,Raajit Rampal,William P. Tew,Lara Dunn,Alexander N. Shoushtari,Martin H. Voss,Deborah Schrag,Jun J. Mao

引用次数: 0