Yuhan Zhang, Xiao Ma, Mingchao Li, Kun Huang, Jie Zhu, Miao Wang, Xi Wang, Menglin Wu, Pheng-Ann Heng
{"title":"Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images","authors":"Yuhan Zhang, Xiao Ma, Mingchao Li, Kun Huang, Jie Zhu, Miao Wang, Xi Wang, Menglin Wu, Pheng-Ann Heng","doi":"10.1038/s41746-025-01756-2","DOIUrl":"https://doi.org/10.1038/s41746-025-01756-2","url":null,"abstract":"<p>Prostate cancer (PCa) is one of the most common types of cancer, seriously affecting adult male health. Accurate and automated PCa segmentation is essential for radiologists to confirm the location of cancer, evaluate its severity, and design appropriate treatments. This paper presents PCaSAM, a fully automated PCa segmentation model that allows us to input multi-modal MRI images into the foundation model to improve performance significantly. We collected multi-center datasets to conduct a comprehensive evaluation. The results showed that PCaSAM outperforms the generalist medical foundation model and the other representative segmentation models, with the average DSC of 0.721 and 0.706 in the internal and external datasets, respectively. Furthermore, with the assistance of segmentation, the PI-RADS scoring of PCa lesions was improved significantly, leading to a substantial increase in average AUC by 8.3–8.9% on two external datasets. Besides, PCaSAM achieved superior efficiency, making it highly suitable for real-world deployment scenarios.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"14 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144311785","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":"Multimodal model for the diagnosis of biliary atresia based on sonographic images and clinical parameters.","authors":"Wenying Zhou,Run Lin,Yuanhang Zheng,Shan Wang,Bin Xu,Zijian Tang,Ruixuan Wang,Cheng Yu,Hualin Yan,Juxian Liu,Wen Ling,Guangliang Huang,Zongjie Weng,Luyao Zhou","doi":"10.1038/s41746-025-01694-z","DOIUrl":"https://doi.org/10.1038/s41746-025-01694-z","url":null,"abstract":"It is still challenging to diagnose biliary atresia (BA) in current clinical practice. The study aimed to develop a multimodal model incorporated with uncertainty estimation by integrating sonographic images and clinical information to help diagnose BA. Multiple models were trained on 384 infants and validated externally on 156 infants. The model fused with sonographic images and clinical information yielded best performance, with an area under the curve (AUC) of 0.941 (95% CI: 0.891-0.972) on the external dataset. Moreover, the model based on sonographic video still yielded AUC of 0.930 (0.876-0.966). By excluding 39 cases with high uncertainty (>0.95), accuracy of the model improved from 84.6% to 91.5%. In addition, six radiologists with different experiences showed improved diagnostic performance (mean AUC increase: 0.066) when aided by the model. This fusion model incorporated with uncertainty estimation could potentially help radiologists identify BA more accurately and efficiently in real clinical practice.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"8 1","pages":"371"},"PeriodicalIF":15.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144311368","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}
Gadi Miron, Mustafa Halimeh, Simon Tietze, Martin Holtkamp, Christian Meisel
{"title":"Detection of epileptic spasms using foundational AI and smartphone videos","authors":"Gadi Miron, Mustafa Halimeh, Simon Tietze, Martin Holtkamp, Christian Meisel","doi":"10.1038/s41746-025-01773-1","DOIUrl":"https://doi.org/10.1038/s41746-025-01773-1","url":null,"abstract":"<p>Infantile epileptic spasm syndrome (IESS) is a severe neurological disorder characterized by epileptic spasms (ES). Timely diagnosis is crucial, but it is often delayed due to symptom misidentification. Smartphone videos can aid in diagnosis, but the availability of specialist review is limited. We fine-tuned a foundational video model for ES detection using social media videos, thus addressing this clinical need and the challenge of data scarcity in rare disorders. Our model, trained on 141 children with 991 ES and 127 children without seizures, achieved high performance (area under the receiver–operating-characteristic curve (AUC) 0.96, 82% sensitivity, 90% specificity) including validation on external datasets from social media derived smartphone videos (93 children, 70 seizures, AUC 0.98, false alarm rate (FAR) 0.75%) and gold-standard video-EEG (22 children, 45 seizures, AUC 0.98, FAR 3.4%). We demonstrate the potential of smartphone videos for AI-powered analysis as the basis for accelerated IESS diagnosis and a novel strategy for the diagnosis of rare disorders.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"14 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144305151","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}
Charles E. Binkley, David Bouslov, Ali Zaidi, Lauren Kaye, Ralph Whalen, Sameer Sethi, Jose Azar
{"title":"An early pipeline framework for assessing vendor AI solutions to support return on investment","authors":"Charles E. Binkley, David Bouslov, Ali Zaidi, Lauren Kaye, Ralph Whalen, Sameer Sethi, Jose Azar","doi":"10.1038/s41746-025-01767-z","DOIUrl":"https://doi.org/10.1038/s41746-025-01767-z","url":null,"abstract":"<p>The success of AI solutions in health systems depends on governance from use case inception through deployment and auditing. This proposed early pipeline governance framework for vendor AI solutions highlights a four-pronged approach: strategic alignment, executive sponsorship, impact and value case assessment, and risk assessment. Each component can be scaled to health systems of any size and the risk and impact assessments can take place simultaneously or sequentially.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"625 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144305113","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}
Marta Saiz-Vivó, Jordi Mill, Xavier Iriart, Hubert Cochet, Gemma Piella, Maxime Sermesant, Oscar Camara
{"title":"Digital twin integrating clinical, morphological and hemodynamic data to identify stroke risk factors","authors":"Marta Saiz-Vivó, Jordi Mill, Xavier Iriart, Hubert Cochet, Gemma Piella, Maxime Sermesant, Oscar Camara","doi":"10.1038/s41746-025-01676-1","DOIUrl":"https://doi.org/10.1038/s41746-025-01676-1","url":null,"abstract":"<p>Stroke remains a leading global cause of mortality, with ischemic stroke as the most common subtype. Atrial fibrillation (AF) increases ischemic stroke risk due to thrombus formation in the left atrium (LA), particularly in the left atrial appendage (LAA). Traditional risk assessments, like the CHA<sub>2</sub>DS<sub>2</sub>-VASc score, focus on clinical factors but often overlook LA morphology and hemodynamics. Existing studies either use mechanistic models with limited cases or rely solely on clinical data, missing hemodynamic insights. This study integrates statistical and mechanistic models within a Digital Twin framework, using unsupervised Multiple Kernel Learning on 130 AF patients. Combining LA morphology, hemodynamics, and clinical data improved patient stratification, identifying three phenogroups. The highest-risk group exhibited larger atrial dimensions, complex LAA structures, and elevated B-type natriuretic peptide levels. This study underscores the potential of Digital Twin models in assessing thrombus risk, emphasizing the need for further research to refine stroke prediction models.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"34 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144305114","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}
Wenhao Qi, Xiaohong Zhu, Bin Wang, Yankai Shi, Chaoqun Dong, Shiying Shen, Jiaqi Li, Kun Zhang, Yunfan He, Mengjiao Zhao, Shiyan Yao, Yongze Dong, Huajuan Shen, Junling Kang, Xiaodong Lu, Guowei Jiang, Lizzy M. M. Boots, Heming Fu, Li Pan, Hongkai Chen, Zhenyu Yan, Guoliang Xing, Shihua Cao
{"title":"Alzheimer’s disease digital biomarkers multidimensional landscape and AI model scoping review","authors":"Wenhao Qi, Xiaohong Zhu, Bin Wang, Yankai Shi, Chaoqun Dong, Shiying Shen, Jiaqi Li, Kun Zhang, Yunfan He, Mengjiao Zhao, Shiyan Yao, Yongze Dong, Huajuan Shen, Junling Kang, Xiaodong Lu, Guowei Jiang, Lizzy M. M. Boots, Heming Fu, Li Pan, Hongkai Chen, Zhenyu Yan, Guoliang Xing, Shihua Cao","doi":"10.1038/s41746-025-01640-z","DOIUrl":"https://doi.org/10.1038/s41746-025-01640-z","url":null,"abstract":"<p>As digital biomarkers gain traction in Alzheimer’s disease (AD) diagnosis, understanding recent advancements is crucial. This review conducts a bibliometric analysis of 431 studies from five online databases: Web of Science, PubMed, Embase, IEEE Xplore, and CINAHL, and provides a scoping review of 86 artificial intelligence (AI) models. Research in this field is supported by 224 grants across 54 disciplines and 1403 institutions in 44 countries, with 2571 contributing researchers. Key focuses include motor activity, neurocognitive tests, eye tracking, and speech analysis. Classical machine learning models dominate AI research, though many lack performance reporting. Of 21 AD-focused models, the average AUC is 0.887, while 45 models for mild cognitive impairment show an average AUC of 0.821. Notably, only 2 studies incorporated external validation, and 3 studies performed model calibration. This review highlights the progress and challenges of integrating digital biomarkers into clinical practice.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"45 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296003","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}
Kirsten I. Taylor, Florian Lipsmeier, Marzia A. Scelsi, Ekaterina Volkova-Volkmar, Daria Rukina, Werner Popp, Stefan Lambrecht, Judith Anzures-Cabrera, David Summers, Markus Abt, Annabelle Monnet, Timothy Kilchenmann, Jens Schjodt-Eriksen, Laurent Essioux, Thomas Kustermann, Wagner Zago, Hanno Svoboda, Tania Nikolcheva, Ronald B. Postuma, Gennaro Pagano, Michael Lindemann
{"title":"Exploratory digital outcome measures of motor sign progression in Parkinson’s disease patients treated with prasinezumab","authors":"Kirsten I. Taylor, Florian Lipsmeier, Marzia A. Scelsi, Ekaterina Volkova-Volkmar, Daria Rukina, Werner Popp, Stefan Lambrecht, Judith Anzures-Cabrera, David Summers, Markus Abt, Annabelle Monnet, Timothy Kilchenmann, Jens Schjodt-Eriksen, Laurent Essioux, Thomas Kustermann, Wagner Zago, Hanno Svoboda, Tania Nikolcheva, Ronald B. Postuma, Gennaro Pagano, Michael Lindemann","doi":"10.1038/s41746-025-01572-8","DOIUrl":"https://doi.org/10.1038/s41746-025-01572-8","url":null,"abstract":"<p>Digital health technology (DHT) tools for Parkinson’s disease (PD) e.g., smartphones and wearables were used for remote and frequent measurement of motor signs in the phase 2 PASADENA study of the anti-alpha-synuclein monoclonal antibody prasinezumab. 316 early-stage PD participants were randomized to placebo, 1500 mg, or 4500 mg prasinezumab for 52 weeks; placebo participants were re-randomized to prasinezumab for the ensuing 52 weeks. Patients performed daily smartphone motor “active tests”, and were passively monitored by smartphone/smartwatch throughout the day over 2 y. Change from baseline analyses censored data at dopaminergic treatment start. Bilateral speeded tapping variability and hand-turning, U-turn speed, passively monitored hand movement power, and summary Simple Sum scores progressed numerically less in prasinezumab-treated vs placebo at week 52. All findings except hand-turning persisted at week 104. DHT sensor-based outcome measures may contribute to quantifying disease progression in clinical research of early-stage, dopaminergic treatment-naïve PD. Clinical Trial Registry Name: ClinicalTrials.gov; Clinical Trial Registry ID: NCT03100149; registered 2017-03-29.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"228 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144295997","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}
Hanpei Miao, Sian Liu, Zehua Wang, Yu Ke, Linling Cheng, Wenyao Yu, Dihui Yu, Kang Zhang, Yuanxu Gao, Zhuo Sun
{"title":"Artificial intelligence-derived retinal age gap as a marker for reproductive aging in women","authors":"Hanpei Miao, Sian Liu, Zehua Wang, Yu Ke, Linling Cheng, Wenyao Yu, Dihui Yu, Kang Zhang, Yuanxu Gao, Zhuo Sun","doi":"10.1038/s41746-025-01699-8","DOIUrl":"https://doi.org/10.1038/s41746-025-01699-8","url":null,"abstract":"<p>Reproductive aging impacts women’s health through fertility decline, disease susceptibility, and systemic aging. This study explores the retinal age gap—the difference between predicted retinal age and chronological age—as a novel biomarker for reproductive aging. By developing a Swin-Transformer-based dual-channel transfer learning model with data from 1294 healthy women, we examined associations between the retinal age gap and Anti-Müllerian Hormone (AMH), a key marker of ovarian reserve. Findings revealed a negative association between the retinal age gap and AMH levels, particularly among women aged 40–50. Lower AMH levels correlated with earlier reproductive aging milestones, emphasizing the predictive value of retinal aging. Genetic data from genome-wide association studies further supported these associations and enhanced AMH prediction through multimodal modeling. These findings highlight the retinal age gap as a promising, non-invasive biomarker for reproductive aging and its potential role in disease prediction and personalized health interventions in women.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"13 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144305149","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}
Giorgos Papanastasiou, Marco Scutari, Raffi Tachdjian, Vivian Hernandez-Trujillo, Jason Raasch, Kaylyn Billmeyer, Nikolay V. Vasilyev, Vladimir Ivanov
{"title":"Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies","authors":"Giorgos Papanastasiou, Marco Scutari, Raffi Tachdjian, Vivian Hernandez-Trujillo, Jason Raasch, Kaylyn Billmeyer, Nikolay V. Vasilyev, Vladimir Ivanov","doi":"10.1038/s41746-025-01761-5","DOIUrl":"https://doi.org/10.1038/s41746-025-01761-5","url":null,"abstract":"<p>Combined immunodeficiencies (CID) and common variable immunodeficiencies (CVID), prevalent yet substantially underdiagnosed primary immunodeficiencies, necessitate improved early detection. Leveraging large-scale electronic health records (EHR) from four nationwide US cohorts, we developed a novel causal Bayesian Network (BN) model to identify antecedent clinical phenotypes associated with CID/CVID. Consensus directed acyclic graphs (DAGs) demonstrated robust predictive performance within each cohort (ROC AUC: 0.61–0.77) and generalizability across unseen cohorts (ROC AUC: 0.56–0.72) in identifying CID/CVID, despite varying inclusion criteria across cohorts. The consensus DAGs reveal causal relationships between comorbidities preceding CID/CVID diagnosis, including autoimmune and blood disorders, lymphomas, organ damage or inflammation, respiratory conditions, genetic anomalies, recurrent infections, and allergies. Further evaluation through causal inference and by expert clinical immunologists substantiates the clinical relevance of the identified phenotypic trajectories. These findings hold promise for translation into improved clinical practice, potentially leading to earlier identification and intervention of adults at risk for CID/CVID.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"225 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288367","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}
Mingxuan Liu, Yilin Ning, Salinelat Teixayavong, Xiaoxuan Liu, Mayli Mertens, Yuqing Shang, Xin Li, Di Miao, Jingchi Liao, Jie Xu, Daniel Shu Wei Ting, Lionel Tim-Ee Cheng, Jasmine Chiat Ling Ong, Zhen Ling Teo, Ting Fang Tan, Narrendar RaviChandran, Fei Wang, Leo Anthony Celi, Marcus Eng Hock Ong, Nan Liu
{"title":"A scoping review and evidence gap analysis of clinical AI fairness","authors":"Mingxuan Liu, Yilin Ning, Salinelat Teixayavong, Xiaoxuan Liu, Mayli Mertens, Yuqing Shang, Xin Li, Di Miao, Jingchi Liao, Jie Xu, Daniel Shu Wei Ting, Lionel Tim-Ee Cheng, Jasmine Chiat Ling Ong, Zhen Ling Teo, Ting Fang Tan, Narrendar RaviChandran, Fei Wang, Leo Anthony Celi, Marcus Eng Hock Ong, Nan Liu","doi":"10.1038/s41746-025-01667-2","DOIUrl":"https://doi.org/10.1038/s41746-025-01667-2","url":null,"abstract":"<p>The ethical integration of artificial intelligence (AI) in healthcare necessitates addressing fairness. AI fairness involves mitigating biases in AI and leveraging AI to promote equity. Despite advancements, significant disconnects persist between technical solutions and clinical applications. Through evidence gap analysis, this review systematically pinpoints the gaps at the intersection of healthcare contexts—including medical fields, healthcare datasets, and bias-relevant attributes (e.g., gender/sex)—and AI fairness techniques for bias detection, evaluation, and mitigation. We highlight the scarcity of AI fairness research in medical domains, the narrow focus on bias-relevant attributes, the dominance of group fairness centering on model performance equality, and the limited integration of clinician-in-the-loop to improve AI fairness. To bridge the gaps, we propose actionable strategies for future research to accelerate the development of AI fairness in healthcare, ultimately advancing equitable healthcare delivery.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"30 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288368","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}