NPJ Digital Medicine最新文献

{"title":"Photography-based dental plaque detection and report generation among preschool children using PlaqueSAM","authors":"Jing Hao,Kaixin Guo,Zhiyi Shan,Yanqi Yang,James Kit Hon Tsoi,Phoebe Pui Ying Lam,Kuo Feng Hung","doi":"10.1038/s41746-026-03385-9","DOIUrl":"https://doi.org/10.1038/s41746-026-03385-9","url":null,"abstract":"Abstract Dental plaque is the primary etiological factor for common oral diseases such as dental caries and gingivitis, particularly affecting susceptible populations including children. Preventing plaque-induced dental diseases in pediatric patients remains a global challenge as certain plaque regions are often missed during daily cleaning. Early detection and removal of plaque are essential but often difficult to achieve consistently. A routine monitoring tool that visualizes plaque accumulation on primary teeth could allow parents to actively track their children’s oral health, enabling timely prevention and intervention for dental caries and periodontal diseases. Inspired by these, we present PlaqueSAM, an automatic plaque detection system using intraoral photographs captured by smartphones. By uploading six images captured with the assistance of alignment overlays, PlaqueSAM can generate a comprehensive plaque detection report with visual references. PlaqueSAM was developed using 3402 prospectively collected intraoral photographs from 567 preschool children across 11 kindergartens in Hong Kong using a three-stage training strategy based on a multi-task learning paradigm. The performance of PlaqueSAM was quantitatively evaluated on 81 children, achieving sensitivity, specificity, and accuracy of 76.58, 82.47, and 79.60%, respectively. These findings suggest that PlaqueSAM may support future plaque screening workflows without requiring disclosing agents or plastic retractors typically used by dental professionals, although home-based use requires further validation under real-world user-operated conditions. With further real-world validation, PlaqueSAM may support dynamic monitoring of children’s daily plaque accumulation and cleaning, thereby contributing to the advancement of teledentistry and promoting children’s oral health remotely, conveniently, and at a lower cost.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"36 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150039","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}

{"title":"Artificial intelligence across the medical education continuum: institutional, learning, readiness and safety systems","authors":"Rushi Patel,Ceyhun Haziroglu,Akshith Ullal,Ahmed Soliman,Smriti Seshadri,Evelyn Efron,Ori Sela,Pranay Arora,Azra Bihorac","doi":"10.1038/s41746-026-03362-2","DOIUrl":"https://doi.org/10.1038/s41746-026-03362-2","url":null,"abstract":"Abstract Artificial intelligence (AI) is entering every stage of medical education, yet guidance for responsible integration remains limited. We synthesize evidence across undergraduate, graduate, and continuing medical education within institutional, learning, and readiness and safety systems. Integration should reflect task structure, verifiability, consequence, and oversight. Continuing medical education remains comparatively underdeveloped despite its importance for practicing physicians, who use clinical AI directly and shape trainee practices, institutional adoption, and responsible implementation.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"10 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150042","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}

{"title":"FHIR-AgentEval: a modular sandbox for benchmarking clinical LLM agents with memory-augmented configurations","authors":"Youssef Mokssit,Kamalakkannan Ravi,Mengshu Nie,Junyoung Kim,Cong Liu","doi":"10.1038/s41746-026-03348-0","DOIUrl":"https://doi.org/10.1038/s41746-026-03348-0","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"39 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150043","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}

{"title":"Six pragmatic steps to separate medical GenAI’s promise from its inherent dangers","authors":"Stephen Gilbert,Max Ostermann,Oscar Freyer","doi":"10.1038/s41746-026-03384-w","DOIUrl":"https://doi.org/10.1038/s41746-026-03384-w","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"54 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150046","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}

{"title":"VOICE-AE: automated CTCAE scoring from ambient clinical audio using speech recognition and large language models","authors":"Federico Mastroleo,Mariana Borras-Osorio,Jonathan E. Moonen,Jake A. Jordan,Keldon K. Lin,Qian Liu,Mi Zhou,Brad J. Stish,Daniel J. Ma,Robert W. Mutter,Jann N. Sarkaria,Nadia N. Laack,Satomi Shiraishi,Andrew Y. K. Foong,David M. Routman,Mark R. Waddle","doi":"10.1038/s41746-026-03373-z","DOIUrl":"https://doi.org/10.1038/s41746-026-03373-z","url":null,"abstract":"Abstract Treatment-related adverse event documentation is labor-intensive and subject to inter-observer variability. We developed and evaluated VOICE-AE, a multi-stage pipeline integrating automatic speech recognition, speaker diarization and large language models (LLMs) for automated extraction and grading of Common Terminology Criteria for Adverse Events (CTCAE) toxicities from clinician-patient audio recordings. Encounters of prostate cancer patients undergoing radiotherapy were recorded and processed through VOICE-AE. Six blinded human raters independently graded 10 genitourinary/gastrointestinal toxicities from the same transcripts; hierarchical clustering identified an expert-rater subgroup that established the consensus reference standard. A total of 31 patients (39 encounters) were enrolled, yielding 390 encounter–toxicity assessments, of which 300 (76.9%) carried a reference grade of 0. Six-rater Krippendorff alpha was 0.677 for ordinal grading. Against reference standard, VOICE-AE achieved a mean weighted kappa of 0.717 and Krippendorff alpha of 0.669. Exact CTCAE grade match was 82.6% and within-one-grade accuracy 99.2%; because grade 0 predominated, a trivial classifier always predicting grade 0 would achieve 76.9% and 93.6% respectively. Performance was weaker at the grades that drive clinical action (grade 1 F1 0.58; grade 2 F1 0.57), and binary detection sensitivity was 77.8% with specificity 89.0% and precision 68.0%. In a like-for-like comparison restricted to the three expert-cluster raters, mean weighted kappa between VOICE-AE and those experts (0.666) fell just below agreement among the experts themselves (0.681). VOICE-AE performed within the range of inter-expert agreement, supporting the feasibility of automated, post-encounter AE documentation. Accuracy at grade ≥2 and detection of severe toxicity remain unproven.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"52 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150041","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}

{"title":"Longitudinal actigraphy reveals healthy maturation of preterm infants in the neonatal intensive care unit","authors":"Leonora Blodgett,Ally Richardson,Kinga Jenei,Joshua Chang,John Loyd,Alan Groves,Dagmar Sternad,David Paydarfar","doi":"10.1038/s41746-026-03347-1","DOIUrl":"https://doi.org/10.1038/s41746-026-03347-1","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"466 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150040","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}

{"title":"Artificial intelligence for opportunistic osteoporosis screening on chest radiographs","authors":"Youngjune Kim,Dong Hyun Lee,Sun-ju Byeon,Hye Soo Cho,Seungkwan Jo,Chang Min Park,Joon Woo Lee,Minyoung Chung,Ju Gang Nam","doi":"10.1038/s41746-026-03333-7","DOIUrl":"https://doi.org/10.1038/s41746-026-03333-7","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"31 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150045","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}

{"title":"Integrating generative artificial intelligence facilitates faculty interaction network and role transition in a biostatistics curriculum","authors":"Yen-Lin Chiu,Tzu-Chin Wu,Hao-Yuan Chang,Chi-Chuan Wang,Kang-Yi Su,Cheng-Heng Liu,Albert C. Yang,Duan-Rung Chen,Chiun Hsu","doi":"10.1038/s41746-026-03376-w","DOIUrl":"https://doi.org/10.1038/s41746-026-03376-w","url":null,"abstract":"","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":"149150049","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}

{"title":"Expanding the functional scope of AI-driven rehabilitation exergames: multimodal biofeedback and adaptive safety monitoring.","authors":"Ziwei Hou, Chen Chen","doi":"10.1038/s41746-026-03141-z","DOIUrl":"10.1038/s41746-026-03141-z","url":null,"abstract":"<p><p>We extend Tannús and colleagues' AI-driven rehabilitation exergame by proposing a closed-loop adaptive framework integrating real-time heart rate monitoring for cardiovascular safety. A three-phase validation roadmap is outlined. This commentary provides a technically specified pathway to transform passive motor assessment into responsive, safe home rehabilitation for stroke survivors.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"9 1","pages":""},"PeriodicalIF":18.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652799/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149147732","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}

{"title":"A scoping review of digital health technologies in glycogen storage diseases","authors":"Claudius Chan,Adam Potter,Florence Kinnafick,Emma Haycraft,Dale W Esliger,Andrew P Kingsnorth","doi":"10.1038/s41746-026-03308-8","DOIUrl":"https://doi.org/10.1038/s41746-026-03308-8","url":null,"abstract":"Abstract Glycogen storage diseases (GSDs) are rare inherited metabolic disorders requiring complex management. Digital health technologies (DHTs) offer solutions for improving care delivery, yet their implementation remains poorly characterised. This scoping review systematically mapped DHT applications in GSDs following PRISMA-ScR guidelines, searching four databases through June 2026. We identified 44 studies with 662 participants across 17 GSD subtypes, revealing geographic concentration in Europe (48%), focus on hepatic subtypes (59%), and predominant use of continuous glucose monitoring (CGM) (66%). Five themes of DHT in GSD research emerged: intervention evaluation, communication enhancement, clinical monitoring, population surveillance, and technology development. Critical gaps included underrepresentation of muscle subtypes and minimal research in movement behaviour and psychosocial evaluation. Glucose-centric DHT use predominates in research; whilst clinically valuable, this neglects holistic health monitoring. Future research should prioritise comprehensive digital ecosystems integrating metabolic, behavioural, and psychosocial monitoring to optimise care for all individuals with GSDs.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"28 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150044","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}