Lancet Digital Health最新文献

筛选
英文 中文
Making patient-reported outcomes reusable at scale. 使患者报告的结果可大规模重复使用。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-11-13 DOI: 10.1016/j.landig.2026.101089
Laurent Boyer, Stefan Leucht, Sara Fernandes, Yann Brousse, Pierre Michel Llorca, Pascal Auquier, Bastien Boussat, Christopher G Chute
{"title":"Making patient-reported outcomes reusable at scale.","authors":"Laurent Boyer, Stefan Leucht, Sara Fernandes, Yann Brousse, Pierre Michel Llorca, Pascal Auquier, Bastien Boussat, Christopher G Chute","doi":"10.1016/j.landig.2026.101089","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101089","url":null,"abstract":"<p><p>Patient-reported outcomes (PROs) are essential to understanding how people live with illness, treatment, and care, and are increasingly promoted for routine use in clinical practice, quality improvement, and value-based health care. PROs are also increasingly relevant in digital health and artificial intelligence applications, both as inputs to predictive models and as outputs reflecting patient-centred aspects of health. Yet, PROs remain difficult to reuse at scale: their implementation is inconsistent across health-care settings, measurement approaches are highly heterogeneous, and PROs are rarely available as large, standardised, analysable datasets suitable for multisite analyses and advanced analytics, including artificial intelligence models. In this Viewpoint, we argue that the central challenge is not a lack of initiatives, but the absence of a coherent, end-to-end approach that connects measurement, routine capture, data standards, and analytic reuse. We propose a practical four-step pathway towards Findable, Accessible, Interoperable, and Reusable (FAIR) PROs. This pathway focuses on (1) defining the outcome domains that matter and selecting high-quality questionnaires; (2) capturing PROs consistently at the point of care in structured, computable formats; (3) storing them in analysable, shareable data models; and (4) establishing transparent cross-questionnaire linking to enable comparable scores. None of these steps poses major technical challenges in isolation; the primary difficulty is that these efforts are often developed in silos, with minimal coordination across disciplines, from questionnaire development and validation to clinical workflows, informatics standards, analytic infrastructures, and governance. A shared FAIR-PROs approach would allow PROs to become a routine, reusable component of learning health systems and a driver of both person-centred care and data-driven innovation.</p>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101089"},"PeriodicalIF":25.5,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149411933","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
Personalised mobile health coaching from early pregnancy to 12-months postpartum for females at risk of gestational diabetes (Bump2Baby and Me): a multicentre, randomised controlled trial. 从妊娠早期到产后12个月对妊娠糖尿病风险女性的个性化移动健康指导(Bump2Baby and Me):一项多中心随机对照试验。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-11-12 DOI: 10.1016/j.landig.2026.101059
Sharleen L O'Reilly, Fionnuala McAuliffe, Helena Teede, Christy Burden, Cristina Campoy, Helle T Maindal, Cheryce L Harrison, Anna Davies, Mercedes G Bermúdez, Rachel Laws, Vincent Versace, Tesfaye Feyissa, Graham R Lee, Paula O'Shea, Ditte Hjorth Laursen, Karsten Vrangbæk, Timothy Skinner
{"title":"Personalised mobile health coaching from early pregnancy to 12-months postpartum for females at risk of gestational diabetes (Bump2Baby and Me): a multicentre, randomised controlled trial.","authors":"Sharleen L O'Reilly, Fionnuala McAuliffe, Helena Teede, Christy Burden, Cristina Campoy, Helle T Maindal, Cheryce L Harrison, Anna Davies, Mercedes G Bermúdez, Rachel Laws, Vincent Versace, Tesfaye Feyissa, Graham R Lee, Paula O'Shea, Ditte Hjorth Laursen, Karsten Vrangbæk, Timothy Skinner","doi":"10.1016/j.landig.2026.101059","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101059","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Maternal overweight and obesity increase the risk of gestational diabetes and adverse pregnancy outcomes. Digital health interventions offer scalable, personalised support, but evidence for interventions spanning both pregnancy and postpartum remains scarce. We evaluated the effectiveness of a personalised mobile health (mHealth) coaching intervention for females at increased risk of gestational diabetes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This multicentre, randomised controlled trial conducted in Australia, Ireland, Spain, and the UK enrolled pregnant females aged 18 years and older between 12-24 weeks of gestation with increased risk of gestational diabetes (Monash GDM risk tool score ≥3; tool risk factors were maternal age, BMI, ethnicity, family history of diabetes, and past history of gestational diabetes). Participants were randomly assigned (1:1) using computer-generated block randomisation (block size 200; stratified by site) to receive either personalised mHealth coaching via smartphone providing synchronous and asynchronous support through pregnancy to 12 months postpartum alongside usual maternity care, or usual maternity care alone. Usual maternity care, including gestational diabetes screening and management, continued unchanged in both groups, and both groups received Bluetooth-enabled scales. Participants and health coaches could not be masked to allocation; clinical staff providing usual care, laboratory staff, and trial statisticians were masked. The primary outcome was the between-group mean difference in BMI at 12 months postpartum among females at risk of gestational diabetes. The trial was registered at Australia and New Zealand Clinical Trials Register, ACTRN12620001240932.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;Between Feb 9, 2021, and Oct 22, 2023, 4386 females were screened, 3521 were excluded, and 865 were randomly assigned (437 to the mHealth intervention group and 428 to the control group). The mean age of participants was 35·2 years (SD 4·3), and most participants were White (588 [73%] of 804). Mean BMI change did not differ between groups (intervention, -0·04 kg/m&lt;sup&gt;2&lt;/sup&gt; [SE 0·12] vs control, 0·04 kg/m&lt;sup&gt;2&lt;/sup&gt; [0·13]). Adverse events were recorded in 18% (79 of 437) of participants in the intervention group and 25% (106 of 428) of participants in the control group; serious adverse events occurred in 6% (28 of 437) of participants in the intervention group and 9% (40 of 428) of participants in the control group. No adverse or serious adverse events were considered related to the intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;Personalised mHealth coaching spanning pregnancy and an extended postpartum support period did not reduce mean maternal BMI at 12 months compared with usual care. Findings suggest that mHealth interventions targeting at-risk females might benefit from addressing a broader range of maternal health outcomes beyond weight management.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/stro","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101059"},"PeriodicalIF":25.5,"publicationDate":"2026-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149411934","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 early warning scores predicting 24 h mortality addressing intercurrent medical interventions in Denmark: a multicentre retrospective cohort study of 2·08 million hospital encounters. 开发和验证早期预警评分预测24小时死亡率处理丹麦的交叉医疗干预:一项多中心回顾性队列研究,涉及208万医院就诊。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-11-05 DOI: 10.1016/j.landig.2026.101067
Alexandros Katsiferis, Neil Scheidwasser, Tri-Long Nguyen, Theis Lange, Mark P Khurana, Pernille B Nielsen, Kasper Karmark Iversen, Christian S Meyhoff, Eske Kvanner Aasvang, Jesper Mølgaard, Adrian G Zucco, Tibor V Varga, Samir Bhatt
{"title":"Development and validation of early warning scores predicting 24 h mortality addressing intercurrent medical interventions in Denmark: a multicentre retrospective cohort study of 2·08 million hospital encounters.","authors":"Alexandros Katsiferis, Neil Scheidwasser, Tri-Long Nguyen, Theis Lange, Mark P Khurana, Pernille B Nielsen, Kasper Karmark Iversen, Christian S Meyhoff, Eske Kvanner Aasvang, Jesper Mølgaard, Adrian G Zucco, Tibor V Varga, Samir Bhatt","doi":"10.1016/j.landig.2026.101067","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101067","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The National Early Warning Score (NEWS) is widely used to predict patient deterioration, but retrospective validations face intervention bias and emphasise discrimination performance over clinical utility. We aimed to compare the clinical net benefit of NEWS against simplified scoring rules and machine learning models, to determine whether simpler approaches suffice or if complex models offer meaningful advantages, and to evaluate performance heterogeneity across patient subgroups.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this multicentre retrospective cohort study, we included data from 15 Danish hospitals (ten hospital networks) across the Capital and Zealand regions of Denmark, between Oct 16, 2018, and Oct 16, 2023. We included all adults (aged ≥18 years) with a hospital encounter with at least one NEWS assessment. Demographic and clinical data, NEWS data, and time of death were extracted from hospital and regional electronic health records. Patients were followed up until death or completion of the 24 h observation period after the initial NEWS score was recorded, whichever occurred first. The outcome was all-cause mortality within 24 h of the initial NEWS recording. We compared NEWS against both simpler and more complex approaches for predicting 24 h mortality: simplified NEWS (NEWS without blood pressure and temperature), Demographic Early Warning Score (DEWS; simplified NEWS with age and sex), and a model based on Extreme Gradient Boosting Early Warning Score (XGB-EWS) incorporating vital signs, demographics, laboratory markers, plus medical history embeddings extracted using sentence transformers. We used propensity score weighting to mitigate intervention bias and evaluated performance using net benefit, area under the receiver operating characteristic curve, and calibration.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;This study included data for 2 080 765 hospital encounters representing 825 200 unique patients over 5 years. The majority (50·9%) of the weighted population was aged 18-65 years, 50·4% were female, 49·6% were male, and 66·2% were admitted to internal and acute medicine clinical specialties. Decision curve analysis in the overall population showed maximum net benefit differences of 1·9 additional correct mortality identifications per 10 000 patients between XGB-EWS and NEWS, and 1·5 per 10 000 patients between NEWS and simplified NEWS. However, stratified analyses revealed substantial heterogeneity: in the high-risk group (initial NEWS ≥7), XGB-EWS provided a maximum gain of 78·1 correct identifications per 10 000 patients compared with NEWS, whereas simplified NEWS resulted in a maximum performance loss of 60·2 per 10 000 patients. Conversely, in the low-risk group (NEWS 0-4), differences were minimal: XGB-EWS provided a maximum gain of 0·9 correct identifications per 10 000 patients compared with NEWS, while simplified NEWS resulted in a maximum loss of 0·1 per 10 000 patients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretatio","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101067"},"PeriodicalIF":25.5,"publicationDate":"2026-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149344140","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
Context is built, not given: context readiness as the next benchmark for clinical use of artificial intelligence. 情境是建立的,而不是给定的:情境准备是人工智能临床应用的下一个基准。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-11-04 DOI: 10.1016/j.landig.2026.101124
Taro Shimizu, Ethan Goh
{"title":"Context is built, not given: context readiness as the next benchmark for clinical use of artificial intelligence.","authors":"Taro Shimizu, Ethan Goh","doi":"10.1016/j.landig.2026.101124","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101124","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101124"},"PeriodicalIF":25.5,"publicationDate":"2026-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149326282","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
Mathematical promises and clinical uncertainties in the validation of early warning scores. 早期预警评分验证中的数学承诺和临床不确定性。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-27 DOI: 10.1016/j.landig.2026.101111
Erika F Christensen, Christian H Nickel
{"title":"Mathematical promises and clinical uncertainties in the validation of early warning scores.","authors":"Erika F Christensen, Christian H Nickel","doi":"10.1016/j.landig.2026.101111","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101111","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101111"},"PeriodicalIF":25.5,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149275662","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
A deep learning model for detection and staging of osteonecrosis of the femoral head on x-ray images: a retrospective, large-scale, multicentre study in China. 股骨头坏死x线图像检测和分期的深度学习模型:中国的一项回顾性、大规模、多中心研究。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-26 DOI: 10.1016/j.landig.2026.101081
Zhanqi Wei, Shipeng Hu, Hanyang Sun, Jie Tan, Naomi Nommi Kemajou, Runze Zhou, Feng Feng, Chunxiang Zhou, Haining Yi, Dongyao Jiang, Ziji Zhang, Feng Liu, Chenliang Wang, Weishen Chen, Minghui Gu, Yonggen Zou, Bo Yang, Wengang Zhu, Peijin Xin, Jinjian Zheng, Zilong Wang, Xu Zhang, Bin Feng, Puyi Sheng, Sukun Tian, Xisheng Weng
{"title":"A deep learning model for detection and staging of osteonecrosis of the femoral head on x-ray images: a retrospective, large-scale, multicentre study in China.","authors":"Zhanqi Wei, Shipeng Hu, Hanyang Sun, Jie Tan, Naomi Nommi Kemajou, Runze Zhou, Feng Feng, Chunxiang Zhou, Haining Yi, Dongyao Jiang, Ziji Zhang, Feng Liu, Chenliang Wang, Weishen Chen, Minghui Gu, Yonggen Zou, Bo Yang, Wengang Zhu, Peijin Xin, Jinjian Zheng, Zilong Wang, Xu Zhang, Bin Feng, Puyi Sheng, Sukun Tian, Xisheng Weng","doi":"10.1016/j.landig.2026.101081","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101081","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Accurate detection and staging of osteonecrosis of the femoral head (ONFH) are essential for effective treatment yet frequently require specialist expertise and advanced equipment. To address this requirement, we aimed to develop a deep learning-based diagnostic model for the automatic detection and staging of ONFH using x-ray images, and compared its performance with clinicians to allow them to improve their diagnostic performance.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this retrospective, large-scale, multicentre study, we developed our deep learning model, Osteonecrosis Artificial Intelligence Diagnostician (OsteoAID), which was based on the You Only Look Once version 8 (YOLOv8) detection network and trained on a multicentre x-ray dataset. The dataset, dated from Jan 1, 2015, to Dec 31, 2023, and obtained from 16 399 patients across six Chinese tertiary hospitals, included 20 722 anteroposterior hip x-ray images of 28 785 hips, including hips with ONFH, healthy hips, and hips with other conditions radiographically similar to ONFH. To establish a rigorous ground truth for model training and evaluation, expert orthopaedists annotated each image to differentiate ONFH from confounding diseases and additionally classified the confirmed ONFH lesions on the basis of the Ficat and Arlet staging system. To verify the diagnostic performance of OsteoAID, we compared the model's accuracy, sensitivity, specificity, F1 score, and area under the curve (AUC) with those of the original YOLOv8 model on the internal testing set for both the staging and detection tasks. Furthermore, the performance of OsteoAID was compared with the performance of radiologists and orthopaedists on two external testing sets, and its diagnostic performance was also benchmarked against MRI-the gold standard for ONFH diagnosis-with a third external testing set in which x-ray images were staged by corresponding MRI scans. Diagnostic metrics were compared with those of clinicians using t tests and McNemar's tests, with significance set at p&lt;0·05.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;On the internal testing set, OsteoAID improved the staging accuracy from 87·42% (95% CI 85·88-89·20) to 96·44% (94·73-97·17) and the AUC from 88·54% (86·74-90·37) to 96·94% (95·75-97·98) compared with the original YOLOv8 model. For detection the model had a mean average precision of 92·97% (91·73-94·43) at an intersection-over-union threshold of 50%. In comparisons with clinicians on the external testing set I, the model showed staging accuracy of 96·60% (94·27-97·81), which was significantly higher than radiologists (74·96% [73·38-76·85]; p&lt;0·0001) and junior orthopaedists (83·98% [81·27-84·06]; p&lt;0·0001) and similar to that of expert orthopaedists (96·54% [94·18-97·79]; p=0·20). Furthermore, model-assisted diagnostics improved the accuracy of junior orthopaedists by an absolute difference of 12·70% and of radiologists by 21·47%. Although the accuracy improvement for expert orthopaed","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101081"},"PeriodicalIF":25.5,"publicationDate":"2026-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149275624","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
Missing links in Africa's digital health agenda. 非洲数字卫生议程中的缺失环节。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-23 DOI: 10.1016/j.landig.2026.101110
Abdulhammed Opeyemi Babatunde, Victor Oluwafemi Femi-Lawal, Tolulope Israel Oni, Kelvin Shaba, Mohamed Mustaf Ahmed, Edward Agyemang, Chrys Promesse Kabuya Kaniki
{"title":"Missing links in Africa's digital health agenda.","authors":"Abdulhammed Opeyemi Babatunde, Victor Oluwafemi Femi-Lawal, Tolulope Israel Oni, Kelvin Shaba, Mohamed Mustaf Ahmed, Edward Agyemang, Chrys Promesse Kabuya Kaniki","doi":"10.1016/j.landig.2026.101110","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101110","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101110"},"PeriodicalIF":25.5,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149246964","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
Examining reliance patterns on AI advice in medical imaging: a mixed-methods, randomised, crossover experiment. 检验医学成像中对人工智能建议的依赖模式:一项混合方法、随机、交叉实验。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-23 DOI: 10.1016/j.landig.2026.101050
Susanne Gaube, Ekaterina Jussupow, Eesha Kokje, Timo K Koch, Jowaria Khan, Elizabeth Bondi-Kelly, Andreas Schicho, Felipe C Kitamura, Timur Ezer, Juergen Mottok, Eva Lermer, Marzyeh Ghassemi, Errol Colak
{"title":"Examining reliance patterns on AI advice in medical imaging: a mixed-methods, randomised, crossover experiment.","authors":"Susanne Gaube, Ekaterina Jussupow, Eesha Kokje, Timo K Koch, Jowaria Khan, Elizabeth Bondi-Kelly, Andreas Schicho, Felipe C Kitamura, Timur Ezer, Juergen Mottok, Eva Lermer, Marzyeh Ghassemi, Errol Colak","doi":"10.1016/j.landig.2026.101050","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101050","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Artificial intelligence (AI) holds significant potential to support diagnostic decision making; however, the collaboration between clinicians and AI systems often does not surpass the performance of unaided humans or standalone AI. This study aimed to examine the effect of AI advice on diagnostic decision making among experts and novices, focusing on the occurrence of AI over-reliance and under-reliance and the potential mitigating effect of explainable AI.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We used a mixed-methods, randomised, crossover experimental design. Participants (50 task experts [radiologists] and 75 novices [non-radiologist physicians and medical trainees]) were randomly assigned in equal proportions to one of six groups, which determined the order in which the three conditions were presented across the three sessions. In each session, participants read 50 head CT scans with or without the presence of an intracranial haemorrhage, under one of three experimental conditions: control, no AI prediction; basic AI advice, AI prediction without annotations; and explainable AI advice, AI prediction with scan annotations. 80% of cases with basic or explainable AI advice received correct advice, and 20% received incorrect advice. The main outcomes were diagnostic performance (the correct identification of intracranial haemorrhage), confidence in the diagnosis, case reading time, and AI advice usefulness ratings. We defined under-reliance as a final decision that did not align with correct AI advice, and over-reliance as a final decision that aligned with incorrect AI advice. All elements of the project were preregistered and are available on the project's Open Science Framework repository.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;Data were collected between Feb 16, 2023, and Aug 10, 2023. Both over-reliance on incorrect advice and under-reliance on correct advice occurred. Under-reliance was associated with high uncertainty and, in absolute terms, had a more detrimental effect on diagnostic performance than over-reliance. Correct explainable AI advice reduced under-reliance and improved performance (OR=1·84, p&lt;0·0001, 95% CI 1·49-2·28) and confidence (b=0·15, p&lt;0·0001, 0·09-0·22) compared with no advice, particularly when reviewing more difficult cases with intracranial haemorrhage. Correct explainable AI did not reduce reading time compared with the no-advice condition (b=-1·81, p=0·071, -3·78 to 0·16). Explainable AI was perceived as more useful than basic AI advice (b=0·12, p=0·0029, 0·04-0·20), especially among novices.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;The occurrence of both under-reliance and over-reliance highlights the need for efficient counterstrategies beyond classic explainable AI methods to foster appropriate reliance and synergy in AI-supported clinical decision-making.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/strong&gt;Volkswagen Foundation, Forum for Interdisciplinary Research, and German Federal Ministry of Education and R","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101050"},"PeriodicalIF":25.5,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149246875","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
Keeping artificial intelligence agents within the clinical task. 让人工智能代理完成临床任务。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-16 DOI: 10.1016/j.landig.2026.101123
Mahmud Omar, Eyal Klang, Girish N Nadkarni
{"title":"Keeping artificial intelligence agents within the clinical task.","authors":"Mahmud Omar, Eyal Klang, Girish N Nadkarni","doi":"10.1016/j.landig.2026.101123","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101123","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101123"},"PeriodicalIF":25.5,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149207953","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
Improving clinical research through better use of clinical trial registry data. 通过更好地利用临床试验注册数据来改进临床研究。
IF 25.5 1区 医学
Lancet Digital Health Pub Date : 2026-10-15 DOI: 10.1016/j.landig.2026.101058
IJsbrand den Rooijen, Giacomo Capone, Jacobus van Wyk, Till Bruckner, Nikos Dedes, Frederik Grell Norgaard, Francois Houyez, Maria J Lamas, Marianne Lunzer, Laura Pioppo, Anton Ussi, Pieter Vankeerberghen, Ana Zanoletty Perez, Mira G P Zuidgeest, Peter Arlett
{"title":"Improving clinical research through better use of clinical trial registry data.","authors":"IJsbrand den Rooijen, Giacomo Capone, Jacobus van Wyk, Till Bruckner, Nikos Dedes, Frederik Grell Norgaard, Francois Houyez, Maria J Lamas, Marianne Lunzer, Laura Pioppo, Anton Ussi, Pieter Vankeerberghen, Ana Zanoletty Perez, Mira G P Zuidgeest, Peter Arlett","doi":"10.1016/j.landig.2026.101058","DOIUrl":"https://doi.org/10.1016/j.landig.2026.101058","url":null,"abstract":"<p><p>Clinical trials are crucial for evidence generation on medicines. As of June, 2025, the European Union's (EU) clinical trial registries (Clinical Trial Information System and European Clinical Trial Register) housed data on nearly 55 000 clinical trials. The full potential of these data, especially when integrated with other sources such as real-world data, has remained mostly untapped for wider health-care innovation. In this Viewpoint, we report on the outcomes of an exploratory workshop with key stakeholders from across clinical research, held in Jan 25 and 26, 2024 under the Accelerating Clinical Trials in the EU (ACT EU) initiative. The workshop identified needs and potential use cases for the clinical trial registry data by gathering and analysing perspectives from diverse stakeholders. The analysis presented in this Viewpoint groups the use cases into three themes: optimising trial design and planning to leverage historical trial data for research optimisation; enhancing patient centricity to meet the diverse needs of patients; and strengthening the evaluation of evidence to maximise the collective effect of clinical trial data for regulatory, clinical, and policy decision making. Strong consensus emerged on key enablers for better use of data. These enablers were data standardisation to ensure consistent data representation among registries; data quality to enable reliable data analysis and decision making; interoperability to allow digital health systems to communicate seamlessly; and transparency to ensure data are made available to the public. As an initial step in addressing these needs, the European Medicines Agency developed the ACT EU trial map as a patient-oriented platform enabling easy trial discovery. The use cases identified at the workshop provide different starting points for supporting the setup of a clinical trial analytics ecosystem to enhance evidence-based decision making, foster innovation, guide funding, and ultimately benefit public health.</p>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":" ","pages":"101058"},"PeriodicalIF":25.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149197374","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书