Yosra Magdi Mekki, Gijs Luijten, Elisabet Hagert, Sirajeddin Belkhair, Chris Varghese, Junaid Qadir, Barry Solaiman, Muhammad Bilal, Jaghtar Dhanda, Jan Egger, Jun Deng, Vikas Khanduja, Alejandro F. Frangi, Susu M. Zughaier, Mitchell A. Stotland
{"title":"Digital twins for the era of personalized surgery","authors":"Yosra Magdi Mekki, Gijs Luijten, Elisabet Hagert, Sirajeddin Belkhair, Chris Varghese, Junaid Qadir, Barry Solaiman, Muhammad Bilal, Jaghtar Dhanda, Jan Egger, Jun Deng, Vikas Khanduja, Alejandro F. Frangi, Susu M. Zughaier, Mitchell A. Stotland","doi":"10.1038/s41746-025-01575-5","DOIUrl":"https://doi.org/10.1038/s41746-025-01575-5","url":null,"abstract":"<p>Digital twins can aid surgeons in training and in performing interventions with greater awareness and precision. The range and variety of digital twins in surgery are described, and their use across perioperative care is discussed. While largely experimental, they are beginning to show promise for the enhancement of personalized, adaptive, and data-driven surgical care. Issues relevant to the greater adoption and deployment of digital twins are all considered.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"115 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979395","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}
Mohammad Loni, Fatemeh Poursalim, Mehdi Asadi, Arash Gharehbaghi
{"title":"A review on generative AI models for synthetic medical text, time series, and longitudinal data","authors":"Mohammad Loni, Fatemeh Poursalim, Mehdi Asadi, Arash Gharehbaghi","doi":"10.1038/s41746-024-01409-w","DOIUrl":"https://doi.org/10.1038/s41746-024-01409-w","url":null,"abstract":"<p>This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"52 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979400","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}
Thierry Meurers, Karen Otte, Hammam Abu Attieh, Farah Briki, Jérémie Despraz, Mehmed Halilovic, Bayrem Kaabachi, Vladimir Milicevic, Armin Müller, Grigorios Papapostolou, Felix Nikolaus Wirth, Jean Louis Raisaro, Fabian Prasser
{"title":"A quantitative analysis of the use of anonymization in biomedical research","authors":"Thierry Meurers, Karen Otte, Hammam Abu Attieh, Farah Briki, Jérémie Despraz, Mehmed Halilovic, Bayrem Kaabachi, Vladimir Milicevic, Armin Müller, Grigorios Papapostolou, Felix Nikolaus Wirth, Jean Louis Raisaro, Fabian Prasser","doi":"10.1038/s41746-025-01644-9","DOIUrl":"https://doi.org/10.1038/s41746-025-01644-9","url":null,"abstract":"<p>Anonymized biomedical data sharing faces several challenges. This systematic review analyzes 1084 PubMed-indexed studies (2018–2022) using anonymized biomedical data to quantify usage trends across geographic, regulatory, and cultural regions to identify effective approaches and inform implementation agendas. We identified a significant yearly increase in such studies with a slope of 2.16 articles per 100,000 when normalized against the total number of PubMed-indexed articles (<i>p</i> = 0.021). Most studies used data from the US, UK, and Australia (78.2%). This trend remained when normalized by country-specific research output. Cross-border sharing was rare (10.5% of studies). We identified twelve common data sources, primarily in the US (seven) and UK (three), including commercial (seven) and public entities (five). The prevalence of anonymization in the US, UK, and Australia suggests their practices could guide broader adoption. Rare cross-border anonymized data sharing and differences between countries with comparable regulations underscore the need for global standards.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"27 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143945750","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}
Alifia Hasan, Noah Prizant, Jee Young Kim, Shreya Rao, David Vidal, Keo Shaw, Danny Tobey, Alexandra Valladares, Shira Zilberstein, Manesh Patel, Suresh Balu, Mark Sendak, Mark Lifson
{"title":"Aligning AI principles and healthcare delivery organization best practices to navigate the shifting regulatory landscape","authors":"Alifia Hasan, Noah Prizant, Jee Young Kim, Shreya Rao, David Vidal, Keo Shaw, Danny Tobey, Alexandra Valladares, Shira Zilberstein, Manesh Patel, Suresh Balu, Mark Sendak, Mark Lifson","doi":"10.1038/s41746-025-01605-2","DOIUrl":"https://doi.org/10.1038/s41746-025-01605-2","url":null,"abstract":"As artificial intelligence (AI) becomes further embedded in healthcare, healthcare delivery organizations (HDOs) must navigate a complex regulatory landscape. Health AI Partnership (HAIP) has created 31 best practice guides to inform the development, validation, and implementation of AI products. Here, we map the most common principles found in 8 key AI regulatory frameworks to HAIP recommended best practices to provide practical insights for compliance with expanding AI regulations.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"39 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143945752","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}
Tej D. Azad, Anmol Warman, Deven McGraw, Suchi Saria
{"title":"Lessons from Henrietta Lacks inform a transparency framework to catalyze generative artificial intelligence in medicine","authors":"Tej D. Azad, Anmol Warman, Deven McGraw, Suchi Saria","doi":"10.1038/s41746-025-01656-5","DOIUrl":"https://doi.org/10.1038/s41746-025-01656-5","url":null,"abstract":"The integration of generative artificial intelligence (AI) tools into healthcare poses significant challenges concerning data privacy and governance. Drawing on the historical vignette of Henrietta Lacks, this perspective examines the implications of using generative AI in clinical settings. We discuss current health data governance practices and their potential limitations in the generative AI era. We propose a framework of proactive transparency to preserve patient autonomy without limiting technologic progress.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"12 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979399","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}
Neslihan Dilruba Koseoglu, Eric Chen, Rudraksh Tuwani, Benjamin Kompa, Stephanie M. Cox, M. Cuneyt Ozmen, Mina Massaro-Giordano, Andrew L. Beam, Pedram Hamrah
{"title":"Development and validation of a deep learning model for diagnosing neuropathic corneal pain via in vivo confocal microscopy","authors":"Neslihan Dilruba Koseoglu, Eric Chen, Rudraksh Tuwani, Benjamin Kompa, Stephanie M. Cox, M. Cuneyt Ozmen, Mina Massaro-Giordano, Andrew L. Beam, Pedram Hamrah","doi":"10.1038/s41746-025-01577-3","DOIUrl":"https://doi.org/10.1038/s41746-025-01577-3","url":null,"abstract":"<p>Neuropathic corneal pain (NCP) is an underdiagnosed ocular disorder caused by aberrant nociception and hypersensitivity of corneal nerves, often resulting in chronic pain and discomfort even in the absence of noxious stimuli. Recently, microneuromas (aberrant growth and swelling of the corneal nerve endings) detected using in vivo <i>confocal microscopy</i> (IVCM) have emerged as a promising biomarker for NCP. However, this process is time-intensive and error-prone, limiting its clinical use and availability. In this work, we present a new NCP screening system based on a deep learning model trained to detect microneuromas using a multisite dataset with a combined total of 103,168 IVCM images. Our model showed excellent discriminative ability detecting microneuromas (AuROC: 0.97) and the ability to generalize to data from a new institution (AuROC: 0.90). Additionally, our pipeline provides an uncertainty quantification mechanism that allows it to communicate when its predictions are reliable, further increasing its clinical relevance.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"25 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946098","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":"A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation","authors":"Elham Asgari, Nina Montaña-Brown, Magda Dubois, Saleh Khalil, Jasmine Balloch, Joshua Au Yeung, Dominic Pimenta","doi":"10.1038/s41746-025-01670-7","DOIUrl":"https://doi.org/10.1038/s41746-025-01670-7","url":null,"abstract":"<p>Integrating large language models (LLMs) into healthcare can enhance workflow efficiency and patient care by automating tasks such as summarising consultations. However, the fidelity between LLM outputs and ground truth information is vital to prevent miscommunication that could lead to compromise in patient safety. We propose a framework comprising (1) an error taxonomy for classifying LLM outputs, (2) an experimental structure for iterative comparisons in our LLM document generation pipeline, (3) a clinical safety framework to evaluate the harms of errors, and (4) a graphical user interface, CREOLA, to facilitate these processes. Our clinical error metrics were derived from 18 experimental configurations involving LLMs for clinical note generation, consisting of 12,999 clinician-annotated sentences. We observed a 1.47% hallucination rate and a 3.45% omission rate. By refining prompts and workflows, we successfully reduced major errors below previously reported human note-taking rates, highlighting the framework’s potential for safer clinical documentation.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"8 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143945751","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}
David Chen,Kabir Chauhan,Rod Parsa,Zhihui Amy Liu,Fei-Fei Liu,Ernie Mak,Lawson Eng,Breffni Louise Hannon,Jennifer Croke,Andrew Hope,Nazanin Fallah-Rad,Phillip Wong,Srinivas Raman
{"title":"Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer.","authors":"David Chen,Kabir Chauhan,Rod Parsa,Zhihui Amy Liu,Fei-Fei Liu,Ernie Mak,Lawson Eng,Breffni Louise Hannon,Jennifer Croke,Andrew Hope,Nazanin Fallah-Rad,Phillip Wong,Srinivas Raman","doi":"10.1038/s41746-025-01671-6","DOIUrl":"https://doi.org/10.1038/s41746-025-01671-6","url":null,"abstract":"Artificial intelligence chatbots can draft empathetic responses to cancer questions, but how patients perceive chatbot empathy remains unclear. Here, we found that people with cancer rated chatbot responses as more empathetic than physician responses. However, differences between patient and physician perceptions of empathy highlight the need for further research to tailor clinical messaging to better meet patient needs. Chatbots may be effective in generating empathetic template responses to patient questions under clinician oversight.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"72 1","pages":"275"},"PeriodicalIF":15.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143945382","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}
Ali Rahimpour Jounghani, Anupam Kumar, Laura Moreno Carbonell, Ester Patrize Lopez Aguilar, Tulla Bee Picardi, Seth Crawford, Audrey K. Bowden, S. M. Hadi Hosseini
{"title":"Wearable fNIRS platform for dense sampling and precision functional neuroimaging","authors":"Ali Rahimpour Jounghani, Anupam Kumar, Laura Moreno Carbonell, Ester Patrize Lopez Aguilar, Tulla Bee Picardi, Seth Crawford, Audrey K. Bowden, S. M. Hadi Hosseini","doi":"10.1038/s41746-025-01690-3","DOIUrl":"https://doi.org/10.1038/s41746-025-01690-3","url":null,"abstract":"<p>Precision mental health aims to improve care by tailoring interventions based on individual neurobiological features. Functional near-infrared spectroscopy (fNIRS) is a cost-effective and portable alternative to traditional neuroimaging, making it a promising tool for this purpose. This study evaluates a self-administered, wearable fNIRS platform designed for precision mental health applications, focusing on its reliability and specificity in capturing individualized functional connectivity patterns. The platform incorporates a wireless, portable multichannel fNIRS device, augmented reality guidance for reproducible device placement, and a cloud-based system for remote data access. In this proof-of-concept study, eight adults completed ten dense-sampled sessions involving cognitive tasks and resting-state measurements. Results demonstrated high test-retest reliability and within-participant consistency in functional connectivity and activation patterns. These findings support the platform’s feasibility for individualized functional mapping. Future research with larger and more diverse cohorts, including clinical populations, is necessary to explore its potential for disorder-specific applications.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"3 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143940205","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}
Jung-Oh Lee,Hong-Yu Zhou,Tyler M Berzin,Daniel K Sodickson,Pranav Rajpurkar
{"title":"Multimodal generative AI for interpreting 3D medical images and videos.","authors":"Jung-Oh Lee,Hong-Yu Zhou,Tyler M Berzin,Daniel K Sodickson,Pranav Rajpurkar","doi":"10.1038/s41746-025-01649-4","DOIUrl":"https://doi.org/10.1038/s41746-025-01649-4","url":null,"abstract":"This perspective proposes adapting video-text generative AI to 3D medical imaging (CT/MRI) and medical videos (endoscopy/laparoscopy) by treating 3D images as videos. The approach leverages modern video models to analyze multiple sequences simultaneously and provide real-time AI assistance during procedures. The paper examines medical imaging's unique characteristics (synergistic information, metadata, and world model), outlines applications in automated reporting, case retrieval, and education, and addresses challenges of limited datasets, benchmarks, and specialized training.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"25 1","pages":"273"},"PeriodicalIF":15.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143945381","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}