{"title":"Approved trends and product characteristics of digital therapeutics in four countries","authors":"Jun Liang, Qichuan Fang, Xiaoyi Jiao, Peng Xiang, Junhao Ma, Zijiao Zhang, Yongcheng Liu, Yunfan He, Yingjun Li, Zhixu He, Jianbo Lei","doi":"10.1038/s41746-025-01660-9","DOIUrl":"https://doi.org/10.1038/s41746-025-01660-9","url":null,"abstract":"<p>Digital therapeutics (DTx) provide innovative treatment options. In this study, we identified and compared approved DTx in China, the US, Germany, and Belgium. In total, 507 DTx applications were identified (US, 192; China, 235; Germany, 55; Belgium, 25). China has approved the most, whereas the US initiated approval as early as 2017. In China, most DTx applications focus on disease treatment (88.09%), particularly for neurological (45.96%) and ophthalmic (21.28%) diseases. The US and Belgium emphasize disease management (US: 52.60%, Belgium: 72.00%), whereas Germany focuses on the treatment of mental and behavioral disorders (47.27%). Regarding therapeutic approaches, China’s DTx predominantly utilizes computerized cognitive correction (26.38%), whereas the US and Belgium primarily rely on health status monitoring (US, 44.27%; Belgium, 80.00%). Germany’s DTx primarily employs cognitive behavioral therapy (69.09%). An online database was established to ensure ease of access. Future studies should focus on generating further evidence to support the broader adoption of DTx.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"56 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144137103","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}
Alessandro Blasimme, Constantin Landers, Effy Vayena
{"title":"Fostering inclusive co-creation in digital health","authors":"Alessandro Blasimme, Constantin Landers, Effy Vayena","doi":"10.1038/s41746-025-01724-w","DOIUrl":"https://doi.org/10.1038/s41746-025-01724-w","url":null,"abstract":"Research on responsible digital health innovation has typically focused on technical aspects such as the reliability and trustworthiness. More recently, work in responsible digital health innovation has started to recognize that, to address those concerns, stakeholder involvement is key. Aligning technological advancements with stakeholders’ needs requires deliberate and inclusive processes. Such processes must incorporate diverse perspectives, including those of the users of digital health technologies, such as healthcare practitionerss and patients.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"132 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144137066","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}
Taavi Tillmann, Andrew Copas, Paul Stokes, Nick Udell, Jo Stead, Jin Lim, Gene Libow
{"title":"Agile evaluation including two pragmatic trials on the uptake of a digital screening service","authors":"Taavi Tillmann, Andrew Copas, Paul Stokes, Nick Udell, Jo Stead, Jin Lim, Gene Libow","doi":"10.1038/s41746-025-01672-5","DOIUrl":"https://doi.org/10.1038/s41746-025-01672-5","url":null,"abstract":"<p>Digital screening may divert lower-risk persons to lower-cost online screening, or offer higher-risk non-responders a more acceptable alternative. Population-based uptake estimates are lacking. We conducted four studies within four weeks by inviting 1700 Londoners (40–74 years, without cardiovascular disease) to a digital Health Check. A six-arm pragmatic unregistered randomised controlled trial (RCT) tested different Short Message Service (SMS) invitations. Uptake varied from 12% (standard SMS) to 20% (shortest SMS, <i>P</i> = 0.009). We tested three sequential reminders (an SMS, a second pragmatic trial [SMS vs postal reminder], and a final SMS). The first SMS reminder increased uptake by +3%. The postal reminder (+7%) was twice as effective as the SMS reminder (+3%, <i>P</i> < 0.0001). The “final reminder” SMS added +7%. Altogether, shorter invites, multi-modal reminders, and a “final reminder” all increased uptake. Adding digital care to in person care may raise uptake from 50 to 60%. Agile evaluations can rapidly improve invitation systems.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"47 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144137102","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}
Magali Boers, Aude Rochereau, Louisa Stuwe, Lorena San Miguel, Jochen Klucken, Fruzsina Mezei, Jérôme Fabiano, Sandrine Boulet, Aymeric Perchant, Rosanna Tarricone, Francesco Petracca, Barbara Hoefgen, Corinne Collignon, Sarah Zohar
{"title":"Classification grid and evidence matrix for evaluating digital medical devices under the European union landscape","authors":"Magali Boers, Aude Rochereau, Louisa Stuwe, Lorena San Miguel, Jochen Klucken, Fruzsina Mezei, Jérôme Fabiano, Sandrine Boulet, Aymeric Perchant, Rosanna Tarricone, Francesco Petracca, Barbara Hoefgen, Corinne Collignon, Sarah Zohar","doi":"10.1038/s41746-025-01697-w","DOIUrl":"https://doi.org/10.1038/s41746-025-01697-w","url":null,"abstract":"<p>A uniform and harmonised taxonomy of Digital Medical Devices (DMDs) and their evidence-based evaluation are essential to ensure their integration into healthcare systems across the European Union (EU). As part of the Taskforce for Harmonised Evaluation of DMDs, a Common European Classification Grid for DMDs (CEUGrid-DMD) associated with an Evidence Matrix is developed. These tools are based on the mapping of existing frameworks, a survey of Health Technology Assessment (HTA) practices, consensus meetings and workshop. The survey was sent to 32 national representatives of HTA bodies from 18 EU countries. Ten HTA bodies from nine countries completed the survey while others could not, in the absence of the effective implementation of a DMD evaluation framework. This work results in the CEUGrid-DMD including four taxonomy categories, associated with an evidence-based matrix. Overall, this first version should help to converge scientific assessments of DMDs in the context of HTA Regulations across the EU.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"485 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130217","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}
Elizabeth J Enichen,Kimia Heydari,Ben Li,Joseph C Kvedar
{"title":"Platform matters -- Differences in COVID data collected from Android and iOS app users.","authors":"Elizabeth J Enichen,Kimia Heydari,Ben Li,Joseph C Kvedar","doi":"10.1038/s41746-025-01734-8","DOIUrl":"https://doi.org/10.1038/s41746-025-01734-8","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"25 1","pages":"307"},"PeriodicalIF":15.2,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144136687","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":"Advancing efficacy prediction for electronic health records based emulated trials in repurposing heart failure therapies.","authors":"Nansu Zong,Shaika Chowdhury,Shibo Zhou,Sivaraman Rajaganapathy,Yue Yu,Liewei Wang,Qiying Dai,Pengyang Li,Xiaoke Liu,Suzette J Bielinski,Jun Chen,Yongbin Chen,James R Cerhan","doi":"10.1038/s41746-025-01705-z","DOIUrl":"https://doi.org/10.1038/s41746-025-01705-z","url":null,"abstract":"The complexities inherent in EHR data create discrepancies between real-world evidence and RCTs, posing substantial challenges in determining whether a treatment is likely to have a beneficial impact compared to the standard of care in RCTs. The objective of this study is to enhance the prediction of efficacy direction for repurposed drugs tested in RCTs for heart failure (HF). To achieve this, we propose an efficacy direction prediction framework that integrates drug-target predictions with EHR-based Emulation Trials (ET) to derive surrogate endpoints for prediction using HF prognostic markers. Our validation of the proposed novel drug-target prediction model against the BETA benchmark demonstrates superior performance, surpassing existing baseline algorithms. Furthermore, an evaluation of our framework in identifying 17 repurposed drugs-derived from 266 phase 3 HF RCTs-using data from 59,000 patients at the Mayo Clinic highlights its remarkable predictive accuracy.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"1 1","pages":"306"},"PeriodicalIF":15.2,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144136839","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}
Enyu Yuan, Yuntian Chen, Lei Ye, Ben He, ChunLei He, Junchao Ma, Ting Yang, Hao Zeng, Ling Yang, Jin Yao, Bin Song
{"title":"Enhanced staging of renal cell carcinoma using tumor morphology features: model development and multi-source validation","authors":"Enyu Yuan, Yuntian Chen, Lei Ye, Ben He, ChunLei He, Junchao Ma, Ting Yang, Hao Zeng, Ling Yang, Jin Yao, Bin Song","doi":"10.1038/s41746-025-01723-x","DOIUrl":"https://doi.org/10.1038/s41746-025-01723-x","url":null,"abstract":"<p>Preoperative detection of pT3a invasion in non-metastatic renal cell carcinoma (RCC) remains challenging with CT. This study developed and validated radiomic models using preoperative CT to identify pT3a invasions. Six models were trained and internally validated via nested cross-validation on 999 patients from one hospital. External validation included 313 patients from two hospitals and 204 patients from four TCIA datasets. A multi-reader multi-case study with seven radiologists evaluated the model’s incremental value. The morphology model achieved the highest internal AUC (0.867, 95% CI: 0.866–0.869) and maintained performance in external validations (AUC = 0.895 and 0.842). When used as a second reader, it significantly improved junior radiologists’ sensitivity and discrimination (AUC: 0.790 vs. 0.831, p < 0.001) without compromising specificity. This study demonstrates that CT-based radiomic models, particularly the morphology model, can reliably detect pT3a invasion and enhance diagnostic accuracy for junior radiologists, offering potential clinical utility in preoperative staging.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"31 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130214","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 Hein, Alana Christie, Michael Holcomb, Bingqing Xie, AJ Jain, Joseph Vento, Neil Rakheja, Ameer Hamza Shakur, Scott Christley, Lindsay G. Cowell, James Brugarolas, Andrew R. Jamieson, Payal Kapur
{"title":"Iterative refinement and goal articulation to optimize large language models for clinical information extraction","authors":"David Hein, Alana Christie, Michael Holcomb, Bingqing Xie, AJ Jain, Joseph Vento, Neil Rakheja, Ameer Hamza Shakur, Scott Christley, Lindsay G. Cowell, James Brugarolas, Andrew R. Jamieson, Payal Kapur","doi":"10.1038/s41746-025-01686-z","DOIUrl":"https://doi.org/10.1038/s41746-025-01686-z","url":null,"abstract":"<p>Extracting structured data from free-text medical records at scale is laborious, and traditional approaches struggle in complex clinical domains. We present a novel, end-to-end pipeline leveraging large language models (LLMs) for highly accurate information extraction and normalization from unstructured pathology reports, focusing initially on kidney tumors. Our innovation combines flexible prompt templates, the direct production of analysis-ready tabular data, and a rigorous, human-in-the-loop iterative refinement process guided by a comprehensive error ontology. Applying the finalized pipeline to 2297 kidney tumor reports with pre-existing templated data available for validation yielded a macro-averaged F1 of 0.99 for six kidney tumor subtypes and 0.97 for detecting kidney metastasis. We further demonstrate flexibility with multiple LLM backbones and adaptability to new domains, utilizing publicly available breast and prostate cancer reports. Beyond performance metrics or pipeline specifics, we emphasize the critical importance of task definition, interdisciplinary collaboration, and complexity management in LLM-based clinical workflows.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"41 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123035","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}
Yuqing Deng, Pujin Cheng, Ruiwen Xu, Lirong Ling, Hongliang Xue, Shiyou Zhou, Yansong Huang, Junyan Lyu, Zhonghua Wang, Kenneth K. Y. Wong, Yimin Zhang, Kang Yu, Tingting Zhang, Xiaoqing Hu, Xiaoyi Li, Xiaoying Tang, Yan Lou, Jin Yuan
{"title":"Advanced and interpretable corneal staining assessment through fine grained knowledge distillation","authors":"Yuqing Deng, Pujin Cheng, Ruiwen Xu, Lirong Ling, Hongliang Xue, Shiyou Zhou, Yansong Huang, Junyan Lyu, Zhonghua Wang, Kenneth K. Y. Wong, Yimin Zhang, Kang Yu, Tingting Zhang, Xiaoqing Hu, Xiaoyi Li, Xiaoying Tang, Yan Lou, Jin Yuan","doi":"10.1038/s41746-025-01706-y","DOIUrl":"https://doi.org/10.1038/s41746-025-01706-y","url":null,"abstract":"<p>The assessment of corneal fluorescein staining is essential, yet current AI models for Corneal Staining Score (CSS) assessments inadequately identify punctate lesions due to annotation challenges and noise, risk misrepresenting treatment responses through “plateau” effects, and highlight the necessity for real-world evaluations to enhance disease severity assessments. To address these limitations, we developed the Fine-grained Knowledge Distillation Corneal Staining Score (FKD-CSS) model. FKD-CSS integrates fine-grained features into CSS grading, providing continuous and nuanced scores with interpretability. Trained on corneal staining images collected from dry eye (DE) patients across 14 hospitals, FKD-CSS achieved robust accuracy, with a Pearson’s r of 0.898 and an AUC of 0.881 in internal validation, matching senior ophthalmologists’ performance. External tests on 2376 images from 23 hospitals across China further validated its efficacy (r: 0.844–0.899, AUC: 0.804-0.883). Additionally, FKD-CSS demonstrated generalizability in multi-ocular-surface-disease testing, underscoring its potential in handling different staining patterns.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"79 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130218","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}
Ruxian Tian, Feng Hou, Haicheng Zhang, Guohua Yu, Ping Yang, Jiaxuan Li, Ting Yuan, Xi Chen, Ying Chen, Yan Hao, Yisong Yao, Hongfei Zhao, Pengyi Yu, Han Fang, Liling Song, Anning Li, Zhonglu Liu, Huaiqing Lv, Dexin Yu, Hongxia Cheng, Ning Mao, Xicheng Song
{"title":"Multimodal fusion model for prognostic prediction and radiotherapy response assessment in head and neck squamous cell carcinoma","authors":"Ruxian Tian, Feng Hou, Haicheng Zhang, Guohua Yu, Ping Yang, Jiaxuan Li, Ting Yuan, Xi Chen, Ying Chen, Yan Hao, Yisong Yao, Hongfei Zhao, Pengyi Yu, Han Fang, Liling Song, Anning Li, Zhonglu Liu, Huaiqing Lv, Dexin Yu, Hongxia Cheng, Ning Mao, Xicheng Song","doi":"10.1038/s41746-025-01712-0","DOIUrl":"https://doi.org/10.1038/s41746-025-01712-0","url":null,"abstract":"<p>Accurate prediction of prognosis and postoperative radiotherapy response is critical for personalized treatment in head and neck squamous cell carcinoma (HNSCC). We developed a multimodal deep learning model (MDLM) integrating computed tomography, whole-slide images, and clinical features from 1087 HNSCC patients across multiple centers. The MDLM exhibited good performance in predicting overall survival (OS) and disease-free survival in external test cohorts. Additionally, the MDLM outperformed unimodal models. Patients with a high-risk score who underwent postoperative radiotherapy exhibited prolonged OS compared to those who did not (<i>P</i> = 0.016), whereas no significant improvement in OS was observed among patients with a low-risk score (<i>P</i> = 0.898). Biological exploration indicated that the model may be related to changes in the cytochrome P450 metabolic pathway, tumor microenvironment, and myeloid-derived cell subpopulations. Overall, the MDLM effectively predicts prognosis and postoperative radiotherapy response, offering a promising tool for personalized HNSCC therapy.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"21 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144122918","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}