Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100916
Prof Ben Van Calster PhD , Prof Gary S Collins PhD , Prof Andrew J Vickers PhD , Laure Wynants PhD , Prof Kathleen F Kerr PhD , Lasai Barreñada MSc , Prof Gael Varoquaux PhD , Karandeep Singh PhD , Prof Karel GM Moons , Prof Tina Hernandez-Boussard PhD , Prof Dirk Timmerman PhD , David J McLernon PhD , Maarten van Smeden PhD , Prof Ewout W Steyerberg , Topic Group 6 of the STRATOS initiative
Numerous measures have been proposed to illustrate the performance of predictive artificial intelligence (AI) models. Selecting appropriate performance measures is essential for predictive AI models intended for use in medical practice. Poorly performing models are misleading and may lead to wrong clinical decisions that can be detrimental to patients and increase financial costs. In this Viewpoint, we assess the merits of classic and contemporary performance measures when validating predictive AI models for medical practice, focusing on models that estimate probabilities for a binary outcome. We discuss 32 performance measures covering five performance domains (discrimination, calibration, overall performance, classification, and clinical utility) along with corresponding graphical assessments. The first four domains address statistical performance, whereas the fifth domain covers decision–analytical performance. We discuss two key characteristics when selecting a performance measure and explain why these characteristics are important: (1) whether the measure’s expected value is optimised when calculated using the correct probabilities (ie, whether it is a proper measure) and (2) whether the measure solely reflects statistical performance or decision–analytical performance by properly accounting for misclassification costs. 17 measures showed both characteristics, 14 showed one, and one (F1 score) showed neither. All classification measures were improper for clinically relevant decision thresholds other than when the threshold was 0·5 or equal to the true prevalence. We illustrate these measures and characteristics using the ADNEX model which predicts the probability of malignancy in women with an ovarian tumour. We recommend the following measures and plots as essential to report: area under the receiver operating characteristic curve, calibration plot, a clinical utility measure such as net benefit with decision curve analysis, and a plot showing probability distributions by outcome category.
{"title":"Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance","authors":"Prof Ben Van Calster PhD , Prof Gary S Collins PhD , Prof Andrew J Vickers PhD , Laure Wynants PhD , Prof Kathleen F Kerr PhD , Lasai Barreñada MSc , Prof Gael Varoquaux PhD , Karandeep Singh PhD , Prof Karel GM Moons , Prof Tina Hernandez-Boussard PhD , Prof Dirk Timmerman PhD , David J McLernon PhD , Maarten van Smeden PhD , Prof Ewout W Steyerberg , Topic Group 6 of the STRATOS initiative","doi":"10.1016/j.landig.2025.100916","DOIUrl":"10.1016/j.landig.2025.100916","url":null,"abstract":"<div><div>Numerous measures have been proposed to illustrate the performance of predictive artificial intelligence (AI) models. Selecting appropriate performance measures is essential for predictive AI models intended for use in medical practice. Poorly performing models are misleading and may lead to wrong clinical decisions that can be detrimental to patients and increase financial costs. In this Viewpoint, we assess the merits of classic and contemporary performance measures when validating predictive AI models for medical practice, focusing on models that estimate probabilities for a binary outcome. We discuss 32 performance measures covering five performance domains (discrimination, calibration, overall performance, classification, and clinical utility) along with corresponding graphical assessments. The first four domains address statistical performance, whereas the fifth domain covers decision–analytical performance. We discuss two key characteristics when selecting a performance measure and explain why these characteristics are important: (1) whether the measure’s expected value is optimised when calculated using the correct probabilities (ie, whether it is a proper measure) and (2) whether the measure solely reflects statistical performance or decision–analytical performance by properly accounting for misclassification costs. 17 measures showed both characteristics, 14 showed one, and one (F1 score) showed neither. All classification measures were improper for clinically relevant decision thresholds other than when the threshold was 0·5 or equal to the true prevalence. We illustrate these measures and characteristics using the ADNEX model which predicts the probability of malignancy in women with an ovarian tumour. We recommend the following measures and plots as essential to report: area under the receiver operating characteristic curve, calibration plot, a clinical utility measure such as net benefit with decision curve analysis, and a plot showing probability distributions by outcome category.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100916"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145757993","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100938
Arjun Mahajan , Callie Fry , Li Zhou , David W Bates
{"title":"Evaluating the effect of visual data on multimodal artificial intelligence diagnostic performance","authors":"Arjun Mahajan , Callie Fry , Li Zhou , David W Bates","doi":"10.1016/j.landig.2025.100938","DOIUrl":"10.1016/j.landig.2025.100938","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100938"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145662427","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100934
Joowhan Sung MD , Peter James Kitonsa MBChB , Annet Nalutaaya MS , David Isooba , Susan Birabwa , Keneth Ndyabayunga , Rogers Okura , Jonathan Magezi , Deborah Nantale , Ivan Mugabi , Violet Nakiiza , Prof David W Dowdy MD , Achilles Katamba PhD , Emily A Kendall MD
<div><h3>Background</h3><div>Computer-aided detection (CAD) software analyses chest x-rays for features suggestive of tuberculosis and provides a numeric abnormality score. However, estimates of CAD accuracy for tuberculosis screening are hindered by the scarcity of confirmatory data among people with lower x-ray scores, including those without symptoms. Additionally, the appropriate x-ray score thresholds for obtaining further testing might vary according to population and client characteristics. We aimed to evaluate the accuracy of CAD among all screened individuals and assess whether stratifying CAD thresholds by age and sex could improve performance.</div></div><div><h3>Methods</h3><div>In this cross-sectional, diagnostic accuracy study, we screened for tuberculosis in individuals aged 15 years and older in Uganda using portable chest x-rays with CAD (qXR version 3.2). Participants not on active tuberculosis treatment were offered screening regardless of their symptoms. We included data from all participants from both facility-based and community-based sites who were screened from June 1, 2022 (study start), to March 31, 2024. Individuals with x-ray scores above a threshold of 0·1 (range 0–1) were asked to provide sputum for Xpert MTB/RIF Ultra (Xpert) testing. We estimated the diagnostic accuracy (sensitivity, specificity, and area under the curve [AUC]) of CAD for detecting Xpert-positive tuberculosis when using the same threshold for all individuals (under different assumptions about tuberculosis prevalence among people with x-ray scores <0·1), and compared this estimate with approaches stratified by age, sex, or both.</div></div><div><h3>Findings</h3><div>54 840 individuals were assessed for eligibility, 52 835 of whom were screened for tuberculosis using CAD. The median age was 38 years (IQR 26–50), 23 586 (44·6%) participants were male, and 29 249 (55·4%) were female. 8949 (16·9%) had x-ray scores of 0·1 or more. Of 7219 participants with valid Xpert results, 382 (5·3%) were Xpert-positive, including 81 with trace results. Assuming 0·1% of participants with x-ray scores less than 0·1 would have been Xpert-positive if tested, qXR had an estimated AUC of 0·92 (95% CI 0·90–0·94) for Xpert-positive tuberculosis. Stratifying x-ray score thresholds according to age and sex improved accuracy; for example, at 96·1% (95% CI 95·9–96·3) specificity, estimated sensitivity was 75·0% (69·9–79·5) for a universal threshold (of ≥0·65) versus 76·9% (71·9–81·2) for thresholds stratified by age and sex (p=0·046).</div></div><div><h3>Interpretation</h3><div>Our findings suggest that the accuracy of CAD for tuberculosis screening among all screening participants, including those without symptoms or abnormal chest x-rays, is higher than previously estimated. Stratifying x-ray score thresholds based on client characteristics such as age and sex could further improve accuracy, enabling a more effective and personalised approach to tuberculosis screening.</di
{"title":"Performance of universal and stratified computer-aided detection thresholds for chest x-ray-based tuberculosis screening: a cross-sectional, diagnostic accuracy study","authors":"Joowhan Sung MD , Peter James Kitonsa MBChB , Annet Nalutaaya MS , David Isooba , Susan Birabwa , Keneth Ndyabayunga , Rogers Okura , Jonathan Magezi , Deborah Nantale , Ivan Mugabi , Violet Nakiiza , Prof David W Dowdy MD , Achilles Katamba PhD , Emily A Kendall MD","doi":"10.1016/j.landig.2025.100934","DOIUrl":"10.1016/j.landig.2025.100934","url":null,"abstract":"<div><h3>Background</h3><div>Computer-aided detection (CAD) software analyses chest x-rays for features suggestive of tuberculosis and provides a numeric abnormality score. However, estimates of CAD accuracy for tuberculosis screening are hindered by the scarcity of confirmatory data among people with lower x-ray scores, including those without symptoms. Additionally, the appropriate x-ray score thresholds for obtaining further testing might vary according to population and client characteristics. We aimed to evaluate the accuracy of CAD among all screened individuals and assess whether stratifying CAD thresholds by age and sex could improve performance.</div></div><div><h3>Methods</h3><div>In this cross-sectional, diagnostic accuracy study, we screened for tuberculosis in individuals aged 15 years and older in Uganda using portable chest x-rays with CAD (qXR version 3.2). Participants not on active tuberculosis treatment were offered screening regardless of their symptoms. We included data from all participants from both facility-based and community-based sites who were screened from June 1, 2022 (study start), to March 31, 2024. Individuals with x-ray scores above a threshold of 0·1 (range 0–1) were asked to provide sputum for Xpert MTB/RIF Ultra (Xpert) testing. We estimated the diagnostic accuracy (sensitivity, specificity, and area under the curve [AUC]) of CAD for detecting Xpert-positive tuberculosis when using the same threshold for all individuals (under different assumptions about tuberculosis prevalence among people with x-ray scores <0·1), and compared this estimate with approaches stratified by age, sex, or both.</div></div><div><h3>Findings</h3><div>54 840 individuals were assessed for eligibility, 52 835 of whom were screened for tuberculosis using CAD. The median age was 38 years (IQR 26–50), 23 586 (44·6%) participants were male, and 29 249 (55·4%) were female. 8949 (16·9%) had x-ray scores of 0·1 or more. Of 7219 participants with valid Xpert results, 382 (5·3%) were Xpert-positive, including 81 with trace results. Assuming 0·1% of participants with x-ray scores less than 0·1 would have been Xpert-positive if tested, qXR had an estimated AUC of 0·92 (95% CI 0·90–0·94) for Xpert-positive tuberculosis. Stratifying x-ray score thresholds according to age and sex improved accuracy; for example, at 96·1% (95% CI 95·9–96·3) specificity, estimated sensitivity was 75·0% (69·9–79·5) for a universal threshold (of ≥0·65) versus 76·9% (71·9–81·2) for thresholds stratified by age and sex (p=0·046).</div></div><div><h3>Interpretation</h3><div>Our findings suggest that the accuracy of CAD for tuberculosis screening among all screening participants, including those without symptoms or abnormal chest x-rays, is higher than previously estimated. Stratifying x-ray score thresholds based on client characteristics such as age and sex could further improve accuracy, enabling a more effective and personalised approach to tuberculosis screening.</di","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100934"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145641207","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100939
Kristy A Horan PhD , Linda Viberg PhD , Susan A Ballard PhD , Maria Globan BSc , Wytamma Wirth PhD , Katherine Bond MBBS , Jessica R Webb PhD , Thinley Dorji PhD , Prof Deborah A Williamson PhD , Michelle L Sait PhD , Ee Laine Tay MPH , Prof Justin T Denholm PhD , Prof Benjamin P Howden PhD , Torsten Seemann PhD , Norelle L Sherry PhD
<div><h3>Background</h3><div>Whole-genome sequencing is increasingly contributing to the clinical management of tuberculosis. Although the availability of bioinformatics tools for analysis and clinical reporting of <em>Mycobacterium tuberculosis</em> sequence data is improving, there remains a need for accessible, flexible bioinformatics tools that can be easily tailored for clinical reporting needs in different settings and that are suitable for accreditation to international standards. We aimed to develop a robust software tool to identify <em>M tuberculosis</em> lineages and antimicrobial resistance from genomic data, tailored for clinical reporting and accessible to clinical microbiology laboratories.</div></div><div><h3>Methods</h3><div>We developed tbtAMR, a flexible yet comprehensive data-driven tool for analysis of <em>M tuberculosis</em> genomic data, including inference of phenotypic susceptibility and lineage calling. tbtAMR takes short-read sequencing data (fastq files) or an annotated vcf file (from short-read or long-read sequencing), maps genomic variants (single nucleotide polymorphisms, insertions or deletions, large structural changes, and gene loss or loss of function), identifies resistance-associated mutations from the WHO catalogue (or user-defined database), and interprets and classifies drug resistance to produce an output file ready for clinical reporting. Validation was undertaken by comparing tbtAMR results with phenotypic and genomic data from our laboratory (n=2005), and publicly available databases and literature (n=13 777), plus simulated genomic data (known variants introduced into a genome sequence) to determine the appropriate quality control metrics and extensively validate the pipeline for clinical use. We compared tbtAMR’s performance with selected publicly available tools (TBProfiler and Mykrobe) to evaluate performance.</div></div><div><h3>Findings</h3><div>tbtAMR accurately predicted lineages and phenotypic susceptibility for first-line (sensitivity 94·6% [95% CI 94·2–95·0], specificity 97·5% [97·3–97·7]) and second-line (sensitivity 83·7% [82·7–84·7], specificity 98·0% [97·9–98·1]) drugs, with equivalent computational and predictive performance compared with other bioinformatics tools currently used, including TBProfiler (first-line sensitivity 94·2% [93·0–95·3], specificity 97·9% [97·6–98·2]) and Mykrobe (first-line sensitivity 91·5% [90·0–92·8], specificity 98·4% [98·2–98·6]). tbtAMR is flexible, with modifiable criteria to tailor results to users’ needs.</div></div><div><h3>Interpretation</h3><div>The tbtAMR tool is suitable for use in clinical and public health microbiology laboratory settings and can be tailored to specific local needs by non-programmers. We have accredited this tool to ISO standards in our laboratory, and it has been implemented for routine reporting of antimicrobial resistance from genomic sequence data in a clinically relevant timeframe (similar to phenotypic susceptibility testing
{"title":"Bringing tuberculosis genomics to the clinic: development and validation of a comprehensive pipeline to predict antimicrobial susceptibility from genomic data, accredited to ISO standards","authors":"Kristy A Horan PhD , Linda Viberg PhD , Susan A Ballard PhD , Maria Globan BSc , Wytamma Wirth PhD , Katherine Bond MBBS , Jessica R Webb PhD , Thinley Dorji PhD , Prof Deborah A Williamson PhD , Michelle L Sait PhD , Ee Laine Tay MPH , Prof Justin T Denholm PhD , Prof Benjamin P Howden PhD , Torsten Seemann PhD , Norelle L Sherry PhD","doi":"10.1016/j.landig.2025.100939","DOIUrl":"10.1016/j.landig.2025.100939","url":null,"abstract":"<div><h3>Background</h3><div>Whole-genome sequencing is increasingly contributing to the clinical management of tuberculosis. Although the availability of bioinformatics tools for analysis and clinical reporting of <em>Mycobacterium tuberculosis</em> sequence data is improving, there remains a need for accessible, flexible bioinformatics tools that can be easily tailored for clinical reporting needs in different settings and that are suitable for accreditation to international standards. We aimed to develop a robust software tool to identify <em>M tuberculosis</em> lineages and antimicrobial resistance from genomic data, tailored for clinical reporting and accessible to clinical microbiology laboratories.</div></div><div><h3>Methods</h3><div>We developed tbtAMR, a flexible yet comprehensive data-driven tool for analysis of <em>M tuberculosis</em> genomic data, including inference of phenotypic susceptibility and lineage calling. tbtAMR takes short-read sequencing data (fastq files) or an annotated vcf file (from short-read or long-read sequencing), maps genomic variants (single nucleotide polymorphisms, insertions or deletions, large structural changes, and gene loss or loss of function), identifies resistance-associated mutations from the WHO catalogue (or user-defined database), and interprets and classifies drug resistance to produce an output file ready for clinical reporting. Validation was undertaken by comparing tbtAMR results with phenotypic and genomic data from our laboratory (n=2005), and publicly available databases and literature (n=13 777), plus simulated genomic data (known variants introduced into a genome sequence) to determine the appropriate quality control metrics and extensively validate the pipeline for clinical use. We compared tbtAMR’s performance with selected publicly available tools (TBProfiler and Mykrobe) to evaluate performance.</div></div><div><h3>Findings</h3><div>tbtAMR accurately predicted lineages and phenotypic susceptibility for first-line (sensitivity 94·6% [95% CI 94·2–95·0], specificity 97·5% [97·3–97·7]) and second-line (sensitivity 83·7% [82·7–84·7], specificity 98·0% [97·9–98·1]) drugs, with equivalent computational and predictive performance compared with other bioinformatics tools currently used, including TBProfiler (first-line sensitivity 94·2% [93·0–95·3], specificity 97·9% [97·6–98·2]) and Mykrobe (first-line sensitivity 91·5% [90·0–92·8], specificity 98·4% [98·2–98·6]). tbtAMR is flexible, with modifiable criteria to tailor results to users’ needs.</div></div><div><h3>Interpretation</h3><div>The tbtAMR tool is suitable for use in clinical and public health microbiology laboratory settings and can be tailored to specific local needs by non-programmers. We have accredited this tool to ISO standards in our laboratory, and it has been implemented for routine reporting of antimicrobial resistance from genomic sequence data in a clinically relevant timeframe (similar to phenotypic susceptibility testing","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100939"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145821558","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100970
The Lancet Digital Health
{"title":"Preserving the integrity of clinical trials","authors":"The Lancet Digital Health","doi":"10.1016/j.landig.2025.100970","DOIUrl":"10.1016/j.landig.2025.100970","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100970"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145828977","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100920
Shuranjeet Singh MSc , Alexandra Kenny BA , Laura Ospina-Pinillos PhD , Prof Sandra Bucci DClinPsy
Lived experience draws on unique insights gained from personal encounters with mental health challenges, irrespective of formal diagnoses. In this Viewpoint, we outline the important contribution of lived experience in digital mental health research in shaping research priorities and the design and delivery of digital mental health interventions and also examine ethical considerations involved. Although digital health technologies are frequently developed by researchers and industry experts, lived experience experts bring in an important voice to address issues such as usability, data privacy, and accessibility of digital tools in daily life. We draw on two case examples—the Wellcome Trust-funded Contributions of Social Networks to Community Thriving (CONNECT) study and the Wellcome Data Prize—that show how engaging lived experience experts can enhance recruitment, design, and equitable participation. We further recommend improved data governance, digital accessibility measures, capacity-building initiatives, and a global commitment to meaningful engagement to ensure that digital mental health research genuinely reflects and benefits the communities it intends to serve.
{"title":"Reflecting on lived experience expertise in digital mental health research","authors":"Shuranjeet Singh MSc , Alexandra Kenny BA , Laura Ospina-Pinillos PhD , Prof Sandra Bucci DClinPsy","doi":"10.1016/j.landig.2025.100920","DOIUrl":"10.1016/j.landig.2025.100920","url":null,"abstract":"<div><div>Lived experience draws on unique insights gained from personal encounters with mental health challenges, irrespective of formal diagnoses. In this Viewpoint, we outline the important contribution of lived experience in digital mental health research in shaping research priorities and the design and delivery of digital mental health interventions and also examine ethical considerations involved. Although digital health technologies are frequently developed by researchers and industry experts, lived experience experts bring in an important voice to address issues such as usability, data privacy, and accessibility of digital tools in daily life. We draw on two case examples—the Wellcome Trust-funded Contributions of Social Networks to Community Thriving (CONNECT) study and the Wellcome Data Prize—that show how engaging lived experience experts can enhance recruitment, design, and equitable participation. We further recommend improved data governance, digital accessibility measures, capacity-building initiatives, and a global commitment to meaningful engagement to ensure that digital mental health research genuinely reflects and benefits the communities it intends to serve.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100920"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145800748","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100926
Feng Xie PhD , Philip Chung MD MS , Jonathan D Reiss MD , Erico Tjoa PhD , Davide De Francesco PhD , Thanaphong Phongpreecha PhD , William Haberkorn MS , Dipro Chakraborty MS , Alan Lee Chang PhD , Tomin James PhD , Yeasul Kim MD , Samson Mataraso PhD , Camilo Espinosa PhD , Liu Yang PhD , Chi-Hung Shu MEng , Lei Xue PhD , Eloïse Berson PhD , Neshat Mohammadi PhD , Sayane Shome PhD , S Momsen Reincke MD , Nima Aghaeepour PhD
<div><h3>Background</h3><div>Early identification and monitoring of neonatal morbidities are critical for timely interventions that can prevent complications, optimise resource use, and support families. Although traditional tools based on tabular data and biomarkers are beneficial, they are restricted in assessing the risk of morbidities in newborns. In this study, we developed NeonatalBERT, a pre-trained large language model (LLM) that estimates the risk of neonatal morbidities from clinical notes.</div></div><div><h3>Methods</h3><div>This prognostic study investigated retrospective primary and external cohorts from two different quaternary-care academic medical centres in the USA: Stanford Health Care and Beth Israel Deaconess Medical Center. NeonatalBERT was initially pre-trained on clinical notes from the primary cohort and then fine-tuned separately for both cohorts. NeonatalBERT was also compared against other existing LLMs, such as BioBERT and Bio-ClinicalBERT, as well as traditional machine learning and logistic regression models using tabular features. NeonatalBERT was evaluated on 19 neonatal morbidities (respiratory distress syndrome, bronchopulmonary dysplasia, pulmonary haemorrhage, pulmonary hypertension, atelectasis, aspiration syndrome, intraventricular haemorrhage, periventricular leukomalacia, neonatal seizures, other CNS disorders, patent ductus arteriosus, cardiovascular instability, sepsis, candidiasis, anaemia, jaundice, necrotising enterocolitis, retinopathy of prematurity, and death) for the primary cohort and ten for the external cohort (respiratory distress syndrome, bronchopulmonary dysplasia, pulmonary haemorrhage, intraventricular haemorrhage, patent ductus arteriosus, sepsis, jaundice, necrotising enterocolitis, retinopathy of prematurity, and death). For each outcome, the area under the receiver operating characteristic curve, area under the precision-recall curve (AUPRC), and F1 scores were evaluated.</div></div><div><h3>Findings</h3><div>32 321 newborns were included in the primary cohort, including 27 411 in the primary training set (mean gestational age 38·64 weeks [SD 2·30]; 13 056 [47·6%] female and 14 355 [52·4%] male newborns) and 4910 in the primary testing set (mean gestational age 38·64 [2·13] weeks; 2336 [47·6%] female and 2574 [52·4%] male newborns). Additionally, 7061 newborns were selected into the external cohort, including 5653 in the external training set (1567 [27·7%] premature and 4086 [72·3%] term births; 2614 [46·2%] female and 3039 [53·8%] male newborns) and 1408 in the external testing set (383 [27·2%] premature and 1025 [72·8%] term births; 624 [44·3%] female and 784 [55·7%] male newborns). In the primary cohort, the mean AUPRC over 19 outcomes was 0·291 (95% CI 0·268–0·314) for NeonatalBERT, 0·238 (0·217–0·259) for Bio-ClinicalBERT, 0·217 (0·197–0·236) for BioBERT, and 0·194 (0·177–0·211) for the traditional model using tabular data. In the external cohort, NeonatalBERT had a mean AUPRC of
{"title":"Development and validation of a pre-trained language model for neonatal morbidities: a retrospective, multicentre, prognostic study","authors":"Feng Xie PhD , Philip Chung MD MS , Jonathan D Reiss MD , Erico Tjoa PhD , Davide De Francesco PhD , Thanaphong Phongpreecha PhD , William Haberkorn MS , Dipro Chakraborty MS , Alan Lee Chang PhD , Tomin James PhD , Yeasul Kim MD , Samson Mataraso PhD , Camilo Espinosa PhD , Liu Yang PhD , Chi-Hung Shu MEng , Lei Xue PhD , Eloïse Berson PhD , Neshat Mohammadi PhD , Sayane Shome PhD , S Momsen Reincke MD , Nima Aghaeepour PhD","doi":"10.1016/j.landig.2025.100926","DOIUrl":"10.1016/j.landig.2025.100926","url":null,"abstract":"<div><h3>Background</h3><div>Early identification and monitoring of neonatal morbidities are critical for timely interventions that can prevent complications, optimise resource use, and support families. Although traditional tools based on tabular data and biomarkers are beneficial, they are restricted in assessing the risk of morbidities in newborns. In this study, we developed NeonatalBERT, a pre-trained large language model (LLM) that estimates the risk of neonatal morbidities from clinical notes.</div></div><div><h3>Methods</h3><div>This prognostic study investigated retrospective primary and external cohorts from two different quaternary-care academic medical centres in the USA: Stanford Health Care and Beth Israel Deaconess Medical Center. NeonatalBERT was initially pre-trained on clinical notes from the primary cohort and then fine-tuned separately for both cohorts. NeonatalBERT was also compared against other existing LLMs, such as BioBERT and Bio-ClinicalBERT, as well as traditional machine learning and logistic regression models using tabular features. NeonatalBERT was evaluated on 19 neonatal morbidities (respiratory distress syndrome, bronchopulmonary dysplasia, pulmonary haemorrhage, pulmonary hypertension, atelectasis, aspiration syndrome, intraventricular haemorrhage, periventricular leukomalacia, neonatal seizures, other CNS disorders, patent ductus arteriosus, cardiovascular instability, sepsis, candidiasis, anaemia, jaundice, necrotising enterocolitis, retinopathy of prematurity, and death) for the primary cohort and ten for the external cohort (respiratory distress syndrome, bronchopulmonary dysplasia, pulmonary haemorrhage, intraventricular haemorrhage, patent ductus arteriosus, sepsis, jaundice, necrotising enterocolitis, retinopathy of prematurity, and death). For each outcome, the area under the receiver operating characteristic curve, area under the precision-recall curve (AUPRC), and F1 scores were evaluated.</div></div><div><h3>Findings</h3><div>32 321 newborns were included in the primary cohort, including 27 411 in the primary training set (mean gestational age 38·64 weeks [SD 2·30]; 13 056 [47·6%] female and 14 355 [52·4%] male newborns) and 4910 in the primary testing set (mean gestational age 38·64 [2·13] weeks; 2336 [47·6%] female and 2574 [52·4%] male newborns). Additionally, 7061 newborns were selected into the external cohort, including 5653 in the external training set (1567 [27·7%] premature and 4086 [72·3%] term births; 2614 [46·2%] female and 3039 [53·8%] male newborns) and 1408 in the external testing set (383 [27·2%] premature and 1025 [72·8%] term births; 624 [44·3%] female and 784 [55·7%] male newborns). In the primary cohort, the mean AUPRC over 19 outcomes was 0·291 (95% CI 0·268–0·314) for NeonatalBERT, 0·238 (0·217–0·259) for Bio-ClinicalBERT, 0·217 (0·197–0·236) for BioBERT, and 0·194 (0·177–0·211) for the traditional model using tabular data. In the external cohort, NeonatalBERT had a mean AUPRC of","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100926"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145794853","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100917
Ghazal Azarfar PhD , Prof Sara Naimimohasses MD PhD , Prof Sirisha Rambhatla PhD , Prof Matthieu Komorowski MD PhD , Diana Ferro PhD , Prof Peter R Lewis PhD , Darren Gates PhD , Prof Nawar Shara PhD , Prof Gregg M Gascon PhD , Prof Anthony Chang MD , Prof Muhammad Mamdani PharmaD , Prof Mamatha Bhat MD PhD , Alliance of Centers of Artificial Intelligence in Medicine working group
Clinicians rely on various data modalities—such as patient history, clinical signs, imaging, and laboratory results—to improve decision making. Multimodal artificial intelligence (AI) systems are emerging as powerful tools to process these diverse data types; however, the clinical adoption of multimodal AI systems is challenging because of data heterogeneity and integration complexities. The 2024 Temerty Centre for AI Research and Education in Medicine symposium, held on June 17, 2024, in Toronto, Canada, explored the potential and challenges of implementing multimodal AI in health care. In this Review, we summarise insights from the symposium. We discuss current applications, such as those used in early diagnosis of sepsis and cardiology, and identify key barriers, including fusion techniques, model selection, generalisation, fairness, safety, security, and international considerations on the responsible deployment of multimodal AI in health care. We outline practical strategies to overcome these obstacles, emphasising technologies such as federated learning to reduce bias and promote equitable health care. By addressing these challenges, multimodal AI can transform clinical practice and improve patient outcomes worldwide.
{"title":"Responsible adoption of multimodal artificial intelligence in health care: promises and challenges","authors":"Ghazal Azarfar PhD , Prof Sara Naimimohasses MD PhD , Prof Sirisha Rambhatla PhD , Prof Matthieu Komorowski MD PhD , Diana Ferro PhD , Prof Peter R Lewis PhD , Darren Gates PhD , Prof Nawar Shara PhD , Prof Gregg M Gascon PhD , Prof Anthony Chang MD , Prof Muhammad Mamdani PharmaD , Prof Mamatha Bhat MD PhD , Alliance of Centers of Artificial Intelligence in Medicine working group","doi":"10.1016/j.landig.2025.100917","DOIUrl":"10.1016/j.landig.2025.100917","url":null,"abstract":"<div><div>Clinicians rely on various data modalities—such as patient history, clinical signs, imaging, and laboratory results—to improve decision making. Multimodal artificial intelligence (AI) systems are emerging as powerful tools to process these diverse data types; however, the clinical adoption of multimodal AI systems is challenging because of data heterogeneity and integration complexities. The 2024 Temerty Centre for AI Research and Education in Medicine symposium, held on June 17, 2024, in Toronto, Canada, explored the potential and challenges of implementing multimodal AI in health care. In this Review, we summarise insights from the symposium. We discuss current applications, such as those used in early diagnosis of sepsis and cardiology, and identify key barriers, including fusion techniques, model selection, generalisation, fairness, safety, security, and international considerations on the responsible deployment of multimodal AI in health care. We outline practical strategies to overcome these obstacles, emphasising technologies such as federated learning to reduce bias and promote equitable health care. By addressing these challenges, multimodal AI can transform clinical practice and improve patient outcomes worldwide.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100917"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145745058","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100935
Prof Axel Haferkamp MD PhD , Lisa Frey MD , Gregor Duwe MD , Jan Hendrik Börner MD , Carola Hunfeld MD , Prof Kerstin A Brocker MD PhD , Stella Troilo MD , Prof Walter Lehmacher PhD , C Patrick Papp MD , Prof Kurt Miller MD PhD , Laura Wiemer MD
<div><h3>Background</h3><div>Urinary incontinence affects an estimated 25–45% of women aged 18 years and older. Despite guideline recommendations, conservative treatments are often underused. We hypothesised that an app-based digital therapeutic, when added to standard care, would significantly reduce incontinence episode frequency compared with standard care alone.</div></div><div><h3>Methods</h3><div>In this 12-week, single-blind, randomised, controlled trial across all regions of Germany, adult participants (aged 18 years or older) assigned female at birth with urinary incontinence (stress, urge, or mixed) as defined by their treating urologist or gynaecologist—with at least one urinary incontinence episode per day—were randomly assigned (1:1) to receive app-based therapy (Kranus Mictera) plus usual care (intervention group) or usual care alone (control group). The study centre was masked to treatment assignment. The primary endpoint was the relative change from baseline in incontinence episode frequency per day; a 50% reduction was considered clinically relevant. A 3-day incontinence diary using an electronic case report form measured the intervention effects. The primary endpoint was assessed by intention-to-treat (ITT), including all participants who were randomly assigned, regardless of study completion. App-based treatments consisted of pelvic floor training, behavioural therapy with methods of urinary urge control, and relaxation techniques. Safety was assessed in the safety population, defined as all participants who initiated the intervention. Because all randomly assigned participants activated the app, the safety population was the same as the ITT population. This trial is closed and registered with <span><span>ClinicalTrials.gov</span><svg><path></path></svg></span> (<span><span>NCT06389838</span><svg><path></path></svg></span>).</div></div><div><h3>Findings</h3><div>Between April 30 and Sep 2, 2024, after obtaining ethical committee approval, 194 patients were randomly assigned to the intervention group (96 [49%] participants) or the control group (98 [51%] participants), with eight participants subsequently withdrawing (four in the intervention group and four in the control group). Median age of the participants was 50 years (IQR 40–57). 121 (62%) participants had stress, 43 (22%) had urge, and 30 (15%) had mixed urinary incontinence. At week 12, mean relative reduction in incontinence episode frequency was 60·95% (SD 44·32) in the intervention group and 1·69% (43·75) in the control group (between-group difference −59·2%, 95% CI −71·7 to −46·7; p<0·0001). No relevant treatment-related adverse events occurred.</div></div><div><h3>Interpretation</h3><div>This study showed that app-based therapy improved standard care for urinary incontinence through a clinically meaningful reduction of urinary incontinence frequency, highlighting its potential to bridge treatment gaps in clinical practice.</div></div><div><h3>Funding</h3><div>Kra
{"title":"App-based therapy for female patients with urinary incontinence in Germany (DINKS): a single-blind, randomised, controlled trial","authors":"Prof Axel Haferkamp MD PhD , Lisa Frey MD , Gregor Duwe MD , Jan Hendrik Börner MD , Carola Hunfeld MD , Prof Kerstin A Brocker MD PhD , Stella Troilo MD , Prof Walter Lehmacher PhD , C Patrick Papp MD , Prof Kurt Miller MD PhD , Laura Wiemer MD","doi":"10.1016/j.landig.2025.100935","DOIUrl":"10.1016/j.landig.2025.100935","url":null,"abstract":"<div><h3>Background</h3><div>Urinary incontinence affects an estimated 25–45% of women aged 18 years and older. Despite guideline recommendations, conservative treatments are often underused. We hypothesised that an app-based digital therapeutic, when added to standard care, would significantly reduce incontinence episode frequency compared with standard care alone.</div></div><div><h3>Methods</h3><div>In this 12-week, single-blind, randomised, controlled trial across all regions of Germany, adult participants (aged 18 years or older) assigned female at birth with urinary incontinence (stress, urge, or mixed) as defined by their treating urologist or gynaecologist—with at least one urinary incontinence episode per day—were randomly assigned (1:1) to receive app-based therapy (Kranus Mictera) plus usual care (intervention group) or usual care alone (control group). The study centre was masked to treatment assignment. The primary endpoint was the relative change from baseline in incontinence episode frequency per day; a 50% reduction was considered clinically relevant. A 3-day incontinence diary using an electronic case report form measured the intervention effects. The primary endpoint was assessed by intention-to-treat (ITT), including all participants who were randomly assigned, regardless of study completion. App-based treatments consisted of pelvic floor training, behavioural therapy with methods of urinary urge control, and relaxation techniques. Safety was assessed in the safety population, defined as all participants who initiated the intervention. Because all randomly assigned participants activated the app, the safety population was the same as the ITT population. This trial is closed and registered with <span><span>ClinicalTrials.gov</span><svg><path></path></svg></span> (<span><span>NCT06389838</span><svg><path></path></svg></span>).</div></div><div><h3>Findings</h3><div>Between April 30 and Sep 2, 2024, after obtaining ethical committee approval, 194 patients were randomly assigned to the intervention group (96 [49%] participants) or the control group (98 [51%] participants), with eight participants subsequently withdrawing (four in the intervention group and four in the control group). Median age of the participants was 50 years (IQR 40–57). 121 (62%) participants had stress, 43 (22%) had urge, and 30 (15%) had mixed urinary incontinence. At week 12, mean relative reduction in incontinence episode frequency was 60·95% (SD 44·32) in the intervention group and 1·69% (43·75) in the control group (between-group difference −59·2%, 95% CI −71·7 to −46·7; p<0·0001). No relevant treatment-related adverse events occurred.</div></div><div><h3>Interpretation</h3><div>This study showed that app-based therapy improved standard care for urinary incontinence through a clinically meaningful reduction of urinary incontinence frequency, highlighting its potential to bridge treatment gaps in clinical practice.</div></div><div><h3>Funding</h3><div>Kra","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100935"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145776044","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}
Pub Date : 2025-12-01DOI: 10.1016/j.landig.2025.100927
Kiruba Nagaratnam MD , Ain A Neuhaus DPhil , Lauren Fensome , Matthew Epton DPhil , Tracey Marriott MBA , Zoe Woodhead PhD , Claire Fernandez DPhil , Michalis Papadakis PhD , Stephen Gerry DPhil , Deb Lowe FRCP , David Hargroves FRCP , Dermot H Mallon PhD , Rob Simister PhD , Pervinder Bhogal PhD , Oliver Spooner MBBS , Ingrid Kane MD , Phil Mathieson MBChB , William Mukonoweshuro MBChB , Martin James MD , Prof Gary A Ford FRCP , George Harston DPhil
Background
Endovascular thrombectomy is a standard of care for patients with large vessel occlusion stroke. Artificial intelligence (AI) imaging software is increasingly used to support identification and selection of patients with stroke for this treatment. We aimed to evaluate the effect of AI stroke imaging software on endovascular treatment in England.
Methods
This prospective observational study was undertaken with the use of data from stroke units in England’s National Health Service (NHS). Data on all patients aged 16 years and older admitted to an NHS hospital with a primary diagnosis of stroke were collected through the national stroke audit registry (Sentinel Stroke National Audit Programme; SSNAP). Endovascular thrombectomy rates and interhospital transfer times were measured through SSNAP for all 107 NHS hospitals admitting patients with acute stroke in England from Jan 1, 2019, to Dec 31, 2023, before and after the systematic implementation of stroke AI software (Brainomix 360 Stroke) in 26 hospitals (six comprehensive stroke centres and 20 primary stroke centres; evaluation sites). Hospital-level data were collected for all hospitals, and patient-level data were collected at evaluation sites. The primary outcome was the proportion of patients with stroke receiving endovascular thrombectomy. Changes in endovascular treatment rates were compared for patients who were reviewed with the use of AI software for image interpretation versus those who were reviewed without AI software.
Findings
452 952 patients with stroke were admitted to 107 hospitals in England between Jan 1, 2019, and Dec 31, 2023. Patient-level data were available for 71 017 patients with ischaemic stroke who were admitted to one of the 26 evaluation sites. For evaluation sites, the pre-implementation endovascular thrombectomy rate was 2·3% (376 of 15 969 patients) and the post-implementation rate was 4·6% (751 of 15 428 patients), a relative increase of 100%. For non-evaluation sites, the pre-implementation rate was 1·6% (1431 of 88 712 patients) and the post-implementation rate was 2·6% (2410 of 89 900 patients), a relative increase of 62·5% (odds ratio [OR] for the interaction between site and time period 1·24 [95% CI 1·08–1·43]; p=0·0026). At the patient level, use of AI stroke software was associated with an increased likelihood of endovascular thrombectomy (OR 1·57 [95% CI 1·33–1·86]; p<0·0001) compared with patients for whom AI software was not used.
Interpretation
Stroke AI imaging software was associated with increased endovascular thrombectomy rates across the English NHS. These results support the routine use of AI imaging software in the management of patients with stroke.
Funding
AI in Health and Care Award from the Accelerated Access Collaborative within NHS England.
{"title":"Artificial intelligence imaging decision support for acute stroke treatment in England: a prospective observational study","authors":"Kiruba Nagaratnam MD , Ain A Neuhaus DPhil , Lauren Fensome , Matthew Epton DPhil , Tracey Marriott MBA , Zoe Woodhead PhD , Claire Fernandez DPhil , Michalis Papadakis PhD , Stephen Gerry DPhil , Deb Lowe FRCP , David Hargroves FRCP , Dermot H Mallon PhD , Rob Simister PhD , Pervinder Bhogal PhD , Oliver Spooner MBBS , Ingrid Kane MD , Phil Mathieson MBChB , William Mukonoweshuro MBChB , Martin James MD , Prof Gary A Ford FRCP , George Harston DPhil","doi":"10.1016/j.landig.2025.100927","DOIUrl":"10.1016/j.landig.2025.100927","url":null,"abstract":"<div><h3>Background</h3><div>Endovascular thrombectomy is a standard of care for patients with large vessel occlusion stroke. Artificial intelligence (AI) imaging software is increasingly used to support identification and selection of patients with stroke for this treatment. We aimed to evaluate the effect of AI stroke imaging software on endovascular treatment in England.</div></div><div><h3>Methods</h3><div>This prospective observational study was undertaken with the use of data from stroke units in England’s National Health Service (NHS). Data on all patients aged 16 years and older admitted to an NHS hospital with a primary diagnosis of stroke were collected through the national stroke audit registry (Sentinel Stroke National Audit Programme; SSNAP). Endovascular thrombectomy rates and interhospital transfer times were measured through SSNAP for all 107 NHS hospitals admitting patients with acute stroke in England from Jan 1, 2019, to Dec 31, 2023, before and after the systematic implementation of stroke AI software (Brainomix 360 Stroke) in 26 hospitals (six comprehensive stroke centres and 20 primary stroke centres; evaluation sites). Hospital-level data were collected for all hospitals, and patient-level data were collected at evaluation sites. The primary outcome was the proportion of patients with stroke receiving endovascular thrombectomy. Changes in endovascular treatment rates were compared for patients who were reviewed with the use of AI software for image interpretation versus those who were reviewed without AI software.</div></div><div><h3>Findings</h3><div>452 952 patients with stroke were admitted to 107 hospitals in England between Jan 1, 2019, and Dec 31, 2023. Patient-level data were available for 71 017 patients with ischaemic stroke who were admitted to one of the 26 evaluation sites. For evaluation sites, the pre-implementation endovascular thrombectomy rate was 2·3% (376 of 15 969 patients) and the post-implementation rate was 4·6% (751 of 15 428 patients), a relative increase of 100%. For non-evaluation sites, the pre-implementation rate was 1·6% (1431 of 88 712 patients) and the post-implementation rate was 2·6% (2410 of 89 900 patients), a relative increase of 62·5% (odds ratio [OR] for the interaction between site and time period 1·24 [95% CI 1·08–1·43]; p=0·0026). At the patient level, use of AI stroke software was associated with an increased likelihood of endovascular thrombectomy (OR 1·57 [95% CI 1·33–1·86]; p<0·0001) compared with patients for whom AI software was not used.</div></div><div><h3>Interpretation</h3><div>Stroke AI imaging software was associated with increased endovascular thrombectomy rates across the English NHS. These results support the routine use of AI imaging software in the management of patients with stroke.</div></div><div><h3>Funding</h3><div>AI in Health and Care Award from the Accelerated Access Collaborative within NHS England.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 12","pages":"Article 100927"},"PeriodicalIF":24.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145670297","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号