Pub Date : 2025-05-01DOI: 10.1016/j.landig.2025.02.002
Jirong Yi PhD , Anna M Marcinkiewicz MD , Aakash Shanbhag MSc , Robert J H Miller MD , Jolien Geers MD , Wenhao Zhang PhD , Aditya Killekar MSc , Nipun Manral MSc , Mark Lemley BSc , Mikolaj Buchwald PhD , Jacek Kwiecinski MD , Jianhang Zhou MSc , Paul B Kavanagh MSc , Joanna X Liang MPH , Valerie Builoff BSc , Prof Terrence D Ruddy MD , Prof Andrew J Einstein MD , Attila Feher MD , Edward J Miller Prof , Prof Albert J Sinusas MD , Piotr J Slomka PhD
Background
CT attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only used for attenuation correction and visual calcium estimation. We aimed to develop a novel artificial intelligence (AI)-based approach to obtain volumetric measurements of chest body composition from CTAC scans and to evaluate these measures for all-cause mortality risk stratification.
Methods
We applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry at four sites (Yale University, University of Calgary, Columbia University, and University of Ottawa), to define the chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle, subcutaneous adipose tissue, intramuscular adipose tissue (IMAT), visceral adipose tissue (VAT), and epicardial adipose tissue (EAT) were quantified between automatically identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation and indexed volumes were evaluated for predicting all-cause mortality, adjusting for established risk factors and 18 other body composition measures via Cox regression models and Kaplan-Meier curves.
Findings
The end-to-end processing time was less than 2 min per scan with no user interaction. Between 2009 and 2021, we included 11 305 participants from four sites participating in the REFINE SPECT registry, who underwent single-photon emission computed tomography cardiac scans. After excluding patients who had incomplete T5–T11 scan coverage, missing clinical data, or who had been used for EAT model training, the final study group comprised 9918 patients. 5451 (55%) of 9918 participants were male and 4467 (45%) of 9918 participants were female. Median follow-up time was 2·48 years (IQR 1·46−3·65), during which 610 (6%) patients died. High VAT, EAT, and IMAT attenuation were associated with an increased all-cause mortality risk (adjusted hazard ratio 2·39, 95% CI 1·92–2·96; p<0·0001, 1·55, 1·26–1·90; p<0·0001, and 1·30, 1·06–1·60; p=0·012, respectively). Patients with high bone attenuation were at reduced risk of death (0·77, 0·62–0·95; p=0·016). Likewise, high skeletal muscle volume index was associated with a reduced risk of death (0·56, 0·44–0·71; p<0·0001).
Interpretation
CTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers that can be automatically measured and offer important additional prognostic value.
Funding
The National Heart, Lung, and Blood Institute, National Institutes of Health.
背景：CT衰减校正（CTAC）扫描在心脏灌注成像中是常规的，但目前仅用于衰减校正和视觉钙估计。我们的目标是开发一种新的基于人工智能（AI）的方法，从CTAC扫描中获得胸体成分的体积测量，并评估这些测量方法对全因死亡率风险分层的影响。方法：我们对来自四个地点（耶鲁大学、卡尔加里大学、哥伦比亚大学和渥太华大学）的大型国际图像注册中心的CTAC扫描应用基于人工智能的分割和图像处理技术，以定义胸廓和多个组织。对自动识别的T5和T11椎体间的骨、骨骼肌、皮下脂肪组织、肌内脂肪组织（IMAT）、内脏脂肪组织（VAT）和心外膜脂肪组织（EAT）的体积测量进行量化。通过Cox回归模型和Kaplan-Meier曲线，评估体积衰减和指数体积的独立预后价值，以预测全因死亡率，调整已确定的危险因素和其他18种身体成分测量。发现：端到端处理时间每次扫描不到2分钟，没有用户交互。2009年至2021年间，我们纳入了来自四个地点的11,305名参与者，他们参加了REFINE SPECT登记，接受了单光子发射计算机断层扫描心脏扫描。在排除T5-T11扫描覆盖不全、缺少临床数据或曾用于EAT模型训练的患者后，最终研究组包括9918例患者。9918名参与者中男性5451人（55%），女性4467人（45%）。中位随访时间为2.48年（IQR为1.46 ~ 3.65），随访期间死亡610例（6%）。高VAT、EAT和IMAT衰减与全因死亡风险增加相关(校正风险比2.39,95% CI 1.92 - 2.96；解释：在心脏灌注成像期间常规获得的CTAC扫描包含重要的体积体组成生物标志物，可以自动测量并提供重要的附加预后价值。资助：国家心脏，肺和血液研究所，国家卫生研究院。
{"title":"AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans for mortality prediction: a multicentre study","authors":"Jirong Yi PhD , Anna M Marcinkiewicz MD , Aakash Shanbhag MSc , Robert J H Miller MD , Jolien Geers MD , Wenhao Zhang PhD , Aditya Killekar MSc , Nipun Manral MSc , Mark Lemley BSc , Mikolaj Buchwald PhD , Jacek Kwiecinski MD , Jianhang Zhou MSc , Paul B Kavanagh MSc , Joanna X Liang MPH , Valerie Builoff BSc , Prof Terrence D Ruddy MD , Prof Andrew J Einstein MD , Attila Feher MD , Edward J Miller Prof , Prof Albert J Sinusas MD , Piotr J Slomka PhD","doi":"10.1016/j.landig.2025.02.002","DOIUrl":"10.1016/j.landig.2025.02.002","url":null,"abstract":"<div><h3>Background</h3><div>CT attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only used for attenuation correction and visual calcium estimation. We aimed to develop a novel artificial intelligence (AI)-based approach to obtain volumetric measurements of chest body composition from CTAC scans and to evaluate these measures for all-cause mortality risk stratification.</div></div><div><h3>Methods</h3><div>We applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry at four sites (Yale University, University of Calgary, Columbia University, and University of Ottawa), to define the chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle, subcutaneous adipose tissue, intramuscular adipose tissue (IMAT), visceral adipose tissue (VAT), and epicardial adipose tissue (EAT) were quantified between automatically identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation and indexed volumes were evaluated for predicting all-cause mortality, adjusting for established risk factors and 18 other body composition measures via Cox regression models and Kaplan-Meier curves.</div></div><div><h3>Findings</h3><div>The end-to-end processing time was less than 2 min per scan with no user interaction. Between 2009 and 2021, we included 11 305 participants from four sites participating in the REFINE SPECT registry, who underwent single-photon emission computed tomography cardiac scans. After excluding patients who had incomplete T5–T11 scan coverage, missing clinical data, or who had been used for EAT model training, the final study group comprised 9918 patients. 5451 (55%) of 9918 participants were male and 4467 (45%) of 9918 participants were female. Median follow-up time was 2·48 years (IQR 1·46−3·65), during which 610 (6%) patients died. High VAT, EAT, and IMAT attenuation were associated with an increased all-cause mortality risk (adjusted hazard ratio 2·39, 95% CI 1·92–2·96; p<0·0001, 1·55, 1·26–1·90; p<0·0001, and 1·30, 1·06–1·60; p=0·012, respectively). Patients with high bone attenuation were at reduced risk of death (0·77, 0·62–0·95; p=0·016). Likewise, high skeletal muscle volume index was associated with a reduced risk of death (0·56, 0·44–0·71; p<0·0001).</div></div><div><h3>Interpretation</h3><div>CTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers that can be automatically measured and offer important additional prognostic value.</div></div><div><h3>Funding</h3><div>The National Heart, Lung, and Blood Institute, National Institutes of Health.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 5","pages":"Article 100862"},"PeriodicalIF":23.8,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095796","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 : 2025-05-01DOI: 10.1016/j.landig.2025.02.008
Ziyao Meng MEng , Zhouyu Guan MD , Shujie Yu MBBS , Yilan Wu BSc , Yaoning Zhao BSc , Jie Shen PhD , Cynthia Ciwei Lim MMed , Tingli Chen MD , Dawei Yang PhD , An Ran Ran PhD , Feng He MSc , Haslina Hamzah BSc , Sarkaaj Singh MSc , Anis Syazwani Abd Raof MSc , Jian Wen Samuel Lee-Boey MBBS , Prof Soo-Kun Lim MBBS , Prof Xufang Sun MD , Shuwang Ge MD , Prof Gang Xu MD , Prof Hua Su , Tien Yin Wong Prof
Background
Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images.
Methods
In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD; and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up.
Findings
For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838–0·846) on the internal validation dataset and AUCs of 0·791–0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825–0·966) on the internal validation dataset and AUCs of 0·733–0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD with higher sensitivity (89·8% vs 66·3%, p<0·0001). In the longitudinal study, participants with isolated diabetic nephropathy and participants with NDKD identified by DeepDKD had a significant difference in renal function outcomes (proportion of estimated glomerular filtration rate decline: 27·45% vs 52·56%, p=0·0010).
Interpretation
Among diverse multi-ethnic populations with diabetes, a retinal image-based AI-deep learning system showed its potential for detecting DKD and differentiating isolated diabetic nephropathy from NDKD in clinical practice.
Funding
National Key R & D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Municipal Key Clinical Specialty, Shanghai Research Centre for Endocrine and Metabolic Diseases, Innovative research team of high-level local universiti
{"title":"Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study","authors":"Ziyao Meng MEng , Zhouyu Guan MD , Shujie Yu MBBS , Yilan Wu BSc , Yaoning Zhao BSc , Jie Shen PhD , Cynthia Ciwei Lim MMed , Tingli Chen MD , Dawei Yang PhD , An Ran Ran PhD , Feng He MSc , Haslina Hamzah BSc , Sarkaaj Singh MSc , Anis Syazwani Abd Raof MSc , Jian Wen Samuel Lee-Boey MBBS , Prof Soo-Kun Lim MBBS , Prof Xufang Sun MD , Shuwang Ge MD , Prof Gang Xu MD , Prof Hua Su , Tien Yin Wong Prof","doi":"10.1016/j.landig.2025.02.008","DOIUrl":"10.1016/j.landig.2025.02.008","url":null,"abstract":"<div><h3>Background</h3><div>Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images.</div></div><div><h3>Methods</h3><div>In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD; and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up.</div></div><div><h3>Findings</h3><div>For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838–0·846) on the internal validation dataset and AUCs of 0·791–0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825–0·966) on the internal validation dataset and AUCs of 0·733–0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD with higher sensitivity (89·8% <em>vs</em> 66·3%, p<0·0001). In the longitudinal study, participants with isolated diabetic nephropathy and participants with NDKD identified by DeepDKD had a significant difference in renal function outcomes (proportion of estimated glomerular filtration rate decline: 27·45% <em>vs</em> 52·56%, p=0·0010).</div></div><div><h3>Interpretation</h3><div>Among diverse multi-ethnic populations with diabetes, a retinal image-based AI-deep learning system showed its potential for detecting DKD and differentiating isolated diabetic nephropathy from NDKD in clinical practice.</div></div><div><h3>Funding</h3><div>National Key R & D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Municipal Key Clinical Specialty, Shanghai Research Centre for Endocrine and Metabolic Diseases, Innovative research team of high-level local universiti","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 5","pages":"Article 100868"},"PeriodicalIF":23.8,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144062786","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 : 2025-05-01DOI: 10.1016/j.landig.2025.01.007
Prof Mohan Pammi MD , Prakesh S Shah MD , Liu K Yang PhD , Joseph Hagan ScD , Nima Aghaeepour PhD , Prof Josef Neu MD
Randomised controlled trials are the gold standard to assess the effectiveness and safety of clinical interventions; however, many paediatric trials are discontinued early due to challenges in patient enrolment. Hence, most paediatric clinical trials suffer from lack of adequate power. Additionally, trials are expensive and might expose patients to unproven therapies. Alternatives to overcome these issues using virtual patient data—namely, digital twins, synthetic patient data, and in-silico trials—are now possible due to rapid advances in digital health-care tools and interventions. However, such digital innovations have been rarely used in paediatric trials. In this Viewpoint, we propose using virtual patient data to empower paediatric trials. The use of virtual patient data has the advantages of decreased exposure of children to potentially ineffective or risky interventions, shorter trial durations leading to more rapid ascertainment of safety and effectiveness of interventions, and faster drug approvals. Use of virtual patient data could lead to more personalised treatment options with low costs and could result in faster clinical implementation of interventions in children. However, ethical and regulatory concerns, including replacing humans with digital data, data privacy, and security should be addressed and the safety and sustainability of digital data innovation ensured before virtual patient data are adopted widely.
{"title":"Digital twins, synthetic patient data, and in-silico trials: can they empower paediatric clinical trials?","authors":"Prof Mohan Pammi MD , Prakesh S Shah MD , Liu K Yang PhD , Joseph Hagan ScD , Nima Aghaeepour PhD , Prof Josef Neu MD","doi":"10.1016/j.landig.2025.01.007","DOIUrl":"10.1016/j.landig.2025.01.007","url":null,"abstract":"<div><div>Randomised controlled trials are the gold standard to assess the effectiveness and safety of clinical interventions; however, many paediatric trials are discontinued early due to challenges in patient enrolment. Hence, most paediatric clinical trials suffer from lack of adequate power. Additionally, trials are expensive and might expose patients to unproven therapies. Alternatives to overcome these issues using virtual patient data—namely, digital twins, synthetic patient data, and in-silico trials—are now possible due to rapid advances in digital health-care tools and interventions. However, such digital innovations have been rarely used in paediatric trials. In this Viewpoint, we propose using virtual patient data to empower paediatric trials. The use of virtual patient data has the advantages of decreased exposure of children to potentially ineffective or risky interventions, shorter trial durations leading to more rapid ascertainment of safety and effectiveness of interventions, and faster drug approvals. Use of virtual patient data could lead to more personalised treatment options with low costs and could result in faster clinical implementation of interventions in children. However, ethical and regulatory concerns, including replacing humans with digital data, data privacy, and security should be addressed and the safety and sustainability of digital data innovation ensured before virtual patient data are adopted widely.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 5","pages":"Article 100851"},"PeriodicalIF":23.8,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144032536","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 : 2025-05-01DOI: 10.1016/j.landig.2025.02.006
Sergi Yun MD , Prof Josep Comín-Colet PhD , Esther Calero-Molina RN , Encarnación Hidalgo RN , Núria José-Bazán RN , Marta Cobo Marcos MD , Teresa Soria RN , Pau Llàcer PhD , Cristina Fernández MSc , José Manuel García-Pinilla PhD , Concepción Cruzado RN , Álvaro González-Franco MD , Eva María García-Marina RN , José Luis Morales-Rull PhD , Cristina Solé MD , Elena García-Romero MD , Julio Núñez PhD , José Civera RN , Coral Fernández RN , Mercedes Faraudo RN , Jordi Fernández
Background
The potential of mobile health (mHealth) technology combining telemonitoring and teleintervention as a non-invasive intervention to reduce the risk of cardiovascular events in patients with heart failure during the early post-discharge period (ie, the vulnerable phase) has not been evaluated to our knowledge. We investigated the efficacy of incorporating mHealth into routine heart failure management in vulnerable-phase patients.
Methods
The Heart Failure Events Reduction with Remote Monitoring and eHealth Support (HERMeS) trial was a 24-week, randomised, controlled, open-label with masked endpoint adjudication, phase 3 trial conducted in ten centres (hospitals [n=9] and a primary care service [n=1]) experienced in heart failure management in Spain. We enrolled adults (aged ≥18 years) with heart failure diagnosed according to the 2016 European Society of Cardiology criteria (then-current clinical practice guidelines at the initiation of the trial) who had recently been discharged (within the preceding 30 days of enrolment) from a hospital admission that was due to heart failure decompensation, or who were in the process of discharge planning. After discharge, participants were centrally randomly assigned (1:1) via a web-based system to mHealth, comprising telemonitoring and preplanned structured health-care follow-up via videoconference, or usual care according to each centre’s heart failure care framework including a nurse-led educational programme. The primary outcome was a composite of the occurrence of cardiovascular death or worsening heart failure events during the 6-month follow-up period, assessed by time-to-first-event analysis in the full analysis set by the intention-to-treat principle. No prospective systematic collection of harms information was planned. The HERMeS trial is registered with ClinicalTrials.gov, NCT03663907, and is completed.
Findings
From May 15, 2018, to April 4, 2022, 506 participants (207 [41%] women and 299 [59%] men) were randomly assigned: 255 to mHealth and 251 to usual care. The mean age of participants was 73 years (SD 13). Follow-up ended prematurely in 51 (20%) of 255 participants in the mHealth group and 36 (14%) of 251 in the usual care group. During follow-up in the mHealth group, cardiovascular death or a worsening heart failure event occurred in 43 (17%) of 255 participants, compared with 102 (41%) of 251 in the usual care group (hazard ratio for time to first event 0·35 [95% CI 0·24–0·50]; p<0·0001; relative risk reduction 65% [95% CI 50–76]). No spontaneously reported harms were reported in either group during follow-up.
Interpretation
mHealth-based heart failure care combining teleintervention and telemonitoring reduced the risk of new fatal and non-fatal cardiovascular events compared
背景：据我们所知，结合远程监测和远程干预的移动医疗（mHealth）技术作为一种非侵入性干预措施，在出院后早期（即脆弱期）降低心力衰竭患者心血管事件风险的潜力尚未得到评估。我们调查了将移动健康纳入易危期患者常规心力衰竭管理的有效性。方法：通过远程监测和电子健康支持减少心力衰竭事件（HERMeS）试验是一项为期24周、随机、对照、开放标签、模糊终点判断的3期试验，在西班牙有心力衰竭管理经验的10个中心（医院[n=9]和初级保健服务[n=1]）进行。我们招募了根据2016年欧洲心脏病学会标准（试验开始时的现行临床实践指南）诊断为心力衰竭的成年人（年龄≥18岁），他们最近（在入组前30天内）因心力衰竭失代偿而出院，或正在出院计划过程中。出院后，参与者通过网络系统集中随机分配（1:1）到移动医疗，包括远程监控和通过视频会议预先计划的结构化医疗保健随访，或根据每个中心的心力衰竭护理框架（包括护士主导的教育方案）进行常规护理。主要结局是在6个月的随访期间心血管死亡或心衰事件恶化发生率的综合结果，在意向治疗原则的完整分析集中通过首次事件的时间分析进行评估。没有计划对危害信息进行前瞻性系统收集。HERMeS试验已在ClinicalTrials.gov注册，注册号为NCT03663907，并已完成。研究结果：从2018年5月15日到2022年4月4日，506名参与者（207名[41%]女性和299名[59%]男性）被随机分配：255名参加移动健康，251名参加常规护理。参与者的平均年龄为73岁（SD 13）。移动健康组255名参与者中有51人（20%）过早结束随访，常规护理组251名参与者中有36人（14%）过早结束随访。在移动健康组的随访期间，255名参与者中有43人（17%）发生心血管死亡或心力衰竭恶化事件，而常规护理组的251名参与者中有102人（41%）发生心血管死亡(时间与首次事件的风险比为0.35 [95% CI 0.24 - 0.50]；结论：与常规护理相比，基于移动健康的心力衰竭护理结合远程干预和远程监测可降低因心力衰竭失代偿而近期入院的患者发生新的致命性和非致命性心血管事件的风险。通过鼓励将移动医疗整合到临床实践指南中，目前的研究结果可以帮助改善出院后过渡时期心力衰竭患者的护理。资金：爱马仕的试验是由诺华公司无限制的资助。
{"title":"Evaluation of mobile health technology combining telemonitoring and teleintervention versus usual care in vulnerable-phase heart failure management (HERMeS): a multicentre, randomised controlled trial","authors":"Sergi Yun MD , Prof Josep Comín-Colet PhD , Esther Calero-Molina RN , Encarnación Hidalgo RN , Núria José-Bazán RN , Marta Cobo Marcos MD , Teresa Soria RN , Pau Llàcer PhD , Cristina Fernández MSc , José Manuel García-Pinilla PhD , Concepción Cruzado RN , Álvaro González-Franco MD , Eva María García-Marina RN , José Luis Morales-Rull PhD , Cristina Solé MD , Elena García-Romero MD , Julio Núñez PhD , José Civera RN , Coral Fernández RN , Mercedes Faraudo RN , Jordi Fernández","doi":"10.1016/j.landig.2025.02.006","DOIUrl":"10.1016/j.landig.2025.02.006","url":null,"abstract":"<div><h3>Background</h3><div>The potential of mobile health (mHealth) technology combining telemonitoring and teleintervention as a non-invasive intervention to reduce the risk of cardiovascular events in patients with heart failure during the early post-discharge period (ie, the vulnerable phase) has not been evaluated to our knowledge. We investigated the efficacy of incorporating mHealth into routine heart failure management in vulnerable-phase patients.</div></div><div><h3>Methods</h3><div>The Heart Failure Events Reduction with Remote Monitoring and eHealth Support (HERMeS) trial was a 24-week, randomised, controlled, open-label with masked endpoint adjudication, phase 3 trial conducted in ten centres (hospitals [n=9] and a primary care service [n=1]) experienced in heart failure management in Spain. We enrolled adults (aged ≥18 years) with heart failure diagnosed according to the 2016 European Society of Cardiology criteria (then-current clinical practice guidelines at the initiation of the trial) who had recently been discharged (within the preceding 30 days of enrolment) from a hospital admission that was due to heart failure decompensation, or who were in the process of discharge planning. After discharge, participants were centrally randomly assigned (1:1) via a web-based system to mHealth, comprising telemonitoring and preplanned structured health-care follow-up via videoconference, or usual care according to each centre’s heart failure care framework including a nurse-led educational programme. The primary outcome was a composite of the occurrence of cardiovascular death or worsening heart failure events during the 6-month follow-up period, assessed by time-to-first-event analysis in the full analysis set by the intention-to-treat principle. No prospective systematic collection of harms information was planned. The HERMeS trial is registered with <span><span>ClinicalTrials.gov</span><svg><path></path></svg></span>, <span><span>NCT03663907</span><svg><path></path></svg></span>, and is completed.</div></div><div><h3>Findings</h3><div>From May 15, 2018, to April 4, 2022, 506 participants (207 [41%] women and 299 [59%] men) were randomly assigned: 255 to mHealth and 251 to usual care. The mean age of participants was 73 years (SD 13). Follow-up ended prematurely in 51 (20%) of 255 participants in the mHealth group and 36 (14%) of 251 in the usual care group. During follow-up in the mHealth group, cardiovascular death or a worsening heart failure event occurred in 43 (17%) of 255 participants, compared with 102 (41%) of 251 in the usual care group (hazard ratio for time to first event 0·35 [95% CI 0·24–0·50]; p<0·0001; relative risk reduction 65% [95% CI 50–76]). No spontaneously reported harms were reported in either group during follow-up.</div></div><div><h3>Interpretation</h3><div>mHealth-based heart failure care combining teleintervention and telemonitoring reduced the risk of new fatal and non-fatal cardiovascular events compared ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 5","pages":"Article 100866"},"PeriodicalIF":23.8,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081416","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 : 2025-03-25DOI: 10.1016/j.landig.2025.01.016
Jasmine Fardouly
{"title":"Potential effects of the social media age ban in Australia for children younger than 16 years","authors":"Jasmine Fardouly","doi":"10.1016/j.landig.2025.01.016","DOIUrl":"10.1016/j.landig.2025.01.016","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Pages e235-e236"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-25DOI: 10.1016/j.landig.2025.02.003
Jeffrey G Malins PhD , D M Anisuzzaman PhD , John I Jackson PhD , Eunjung Lee PhD , Jwan A Naser MBBS , Behrouz Rostami PhD , Jared G Bird MD , Dan Spiegelstein MD , Talia Amar MSc , Prof Jae K Oh MD , Prof Patricia A Pellikka MD , Jeremy J Thaden MD , Prof Francisco Lopez-Jimenez MD MSc , Prof Sorin V Pislaru MD PhD , Prof Paul A Friedman MD , Prof Garvan C Kane MD PhD , Zachi I Attia PhD
Background
Artificial intelligence (AI) is poised to transform point-of-care practice by providing rapid snapshots of cardiac functioning. Although previous AI models have been developed to estimate left ventricular ejection fraction (LVEF), they have typically used video clips as input, which can be computationally intensive. In the current study, we aimed to develop an LVEF estimation model that takes in static frames as input.
Methods
Using retrospective transthoracic echocardiography (TTE) data from Mayo Clinic Rochester and Mayo Clinic Health System sites (training: n=19 627; interval validation: n=862), we developed a two-dimensional convolutional neural network model that provides an LVEF estimate associated with an input frame from an echocardiogram video. We then evaluated model performance for Mayo Clinic TTE data (Rochester, n=1890; Arizona, n=1695; Florida, n=1862), the EchoNet-Dynamic TTE dataset (n=10 015), a prospective cohort of patients from whom TTE and handheld cardiac ultrasound (HCU) were simultaneously collected (n=625), and a prospective cohort of patients from whom HCU clips were collected by expert sonographers and novice users (n=100, distributed across three external sites).
Findings
We observed consistently strong model performance when estimates from single frames were averaged across multiple video clips, even when only one frame was taken per video (for classifying LVEF ≤40% vs LVEF>40%, area under the receiver operating characteristic curve [AUC]>0·90 for all datasets except for HCU clips collected by novice users, for which AUC>0·85). We also observed that LVEF estimates differed slightly depending on the phase of the cardiac cycle when images were captured.
Interpretation
When aiming to rapidly deploy such models, single frames from multiple videos might be sufficient for LVEF classification. Furthermore, the observed sensitivity to the cardiac cycle offers some insights on model performance from an explainability perspective.
Funding
Internal institutional funds provided by the Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.
{"title":"Snapshot artificial intelligence—determination of ejection fraction from a single frame still image: a multi-institutional, retrospective model development and validation study","authors":"Jeffrey G Malins PhD , D M Anisuzzaman PhD , John I Jackson PhD , Eunjung Lee PhD , Jwan A Naser MBBS , Behrouz Rostami PhD , Jared G Bird MD , Dan Spiegelstein MD , Talia Amar MSc , Prof Jae K Oh MD , Prof Patricia A Pellikka MD , Jeremy J Thaden MD , Prof Francisco Lopez-Jimenez MD MSc , Prof Sorin V Pislaru MD PhD , Prof Paul A Friedman MD , Prof Garvan C Kane MD PhD , Zachi I Attia PhD","doi":"10.1016/j.landig.2025.02.003","DOIUrl":"10.1016/j.landig.2025.02.003","url":null,"abstract":"<div><h3>Background</h3><div>Artificial intelligence (AI) is poised to transform point-of-care practice by providing rapid snapshots of cardiac functioning. Although previous AI models have been developed to estimate left ventricular ejection fraction (LVEF), they have typically used video clips as input, which can be computationally intensive. In the current study, we aimed to develop an LVEF estimation model that takes in static frames as input.</div></div><div><h3>Methods</h3><div>Using retrospective transthoracic echocardiography (TTE) data from Mayo Clinic Rochester and Mayo Clinic Health System sites (training: n=19 627; interval validation: n=862), we developed a two-dimensional convolutional neural network model that provides an LVEF estimate associated with an input frame from an echocardiogram video. We then evaluated model performance for Mayo Clinic TTE data (Rochester, n=1890; Arizona, n=1695; Florida, n=1862), the EchoNet-Dynamic TTE dataset (n=10 015), a prospective cohort of patients from whom TTE and handheld cardiac ultrasound (HCU) were simultaneously collected (n=625), and a prospective cohort of patients from whom HCU clips were collected by expert sonographers and novice users (n=100, distributed across three external sites).</div></div><div><h3>Findings</h3><div>We observed consistently strong model performance when estimates from single frames were averaged across multiple video clips, even when only one frame was taken per video (for classifying LVEF ≤40% <em>vs</em> LVEF>40%, area under the receiver operating characteristic curve [AUC]>0·90 for all datasets except for HCU clips collected by novice users, for which AUC>0·85). We also observed that LVEF estimates differed slightly depending on the phase of the cardiac cycle when images were captured.</div></div><div><h3>Interpretation</h3><div>When aiming to rapidly deploy such models, single frames from multiple videos might be sufficient for LVEF classification. Furthermore, the observed sensitivity to the cardiac cycle offers some insights on model performance from an explainability perspective.</div></div><div><h3>Funding</h3><div>Internal institutional funds provided by the Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Pages e255-e263"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-25DOI: 10.1016/j.landig.2025.01.001
Joshua Mayourian MD , Ivor B Asztalos MD , Amr El-Bokl MD , Platon Lukyanenko PhD , Ryan L Kobayashi MD , William G La Cava MD , Sunil J Ghelani MD , Prof Victoria L Vetter MD , Prof John K Triedman MD
Background
Left ventricular systolic dysfunction (LVSD) is independently associated with cardiovascular events in patients with congenital heart disease. Although artificial intelligence-enhanced electrocardiogram (AI-ECG) analysis is predictive of LVSD in the general adult population, it has yet to be applied comprehensively across congenital heart disease lesions.
Methods
We trained a convolutional neural network on paired ECG–echocardiograms (≤2 days apart) across the lifespan of a wide range of congenital heart disease lesions to detect left ventricular ejection fraction (LVEF) of 40% or less. Model performance was evaluated on single ECG–echocardiogram pairs per patient at Boston Children's Hospital (Boston, MA, USA) and externally at the Children's Hospital of Philadelphia (Philadelphia, PA, USA) using area under the receiver operating (AUROC) and precision-recall (AUPRC) curves.
Findings
The training cohort comprised 124 265 ECG–echocardiogram pairs (49 158 patients; median age 10·5 years [IQR 3·5–16·8]; 3381 [2·7%] of 124 265 ECG–echocardiogram pairs with LVEF ≤40%). Test groups included internal testing (21 068 patients; median age 10·9 years [IQR 3·7–17·0]; 3381 [2·7%] of 124 265 ECG–echocardiogram pairs with LVEF ≤40%) and external validation (42 984 patients; median age 10·8 years [IQR 4·9–15·0]; 1313 [1·7%] of 76 400 ECG–echocardiogram pairs with LVEF ≤40%) cohorts. High model performance was achieved during internal testing (AUROC 0·95, AUPRC 0·33) and external validation (AUROC 0·96, AUPRC 0·25) for a wide range of congenital heart disease lesions. Patients with LVEF greater than 40% by echocardiogram who were deemed high risk by AI-ECG were more likely to have future dysfunction compared with low-risk patients (hazard ratio 12·1 [95% CI 8·4–17·3]; p<0·0001). High-risk patients by AI-ECG were at increased risk of mortality in the overall cohort and lesion-specific subgroups. Common salient features highlighted across congenital heart disaese lesions include precordial QRS complexes and T waves, with common high-risk ECG features including deep V2 S waves and lateral precordial T wave inversion. A case study on patients with ventricular pacing showed similar findings.
Interpretation
Our externally validated algorithm shows promise in prediction of current and future LVSD in patients with congenital heart disease, providing a clinically impactful, inexpensive, and convenient cardiovascular health tool in this population.
Funding
Kostin Innovation Fund, Thrasher Research Fund Early Career Award, Boston Children's Hospital Electrophysiology Research Education Fund, National Institutes of Health, National Institute of Childhood Diseases and Human Development, and National Library of Medicine.
{"title":"Electrocardiogram-based deep learning to predict left ventricular systolic dysfunction in paediatric and adult congenital heart disease in the USA: a multicentre modelling study","authors":"Joshua Mayourian MD , Ivor B Asztalos MD , Amr El-Bokl MD , Platon Lukyanenko PhD , Ryan L Kobayashi MD , William G La Cava MD , Sunil J Ghelani MD , Prof Victoria L Vetter MD , Prof John K Triedman MD","doi":"10.1016/j.landig.2025.01.001","DOIUrl":"10.1016/j.landig.2025.01.001","url":null,"abstract":"<div><h3>Background</h3><div>Left ventricular systolic dysfunction (LVSD) is independently associated with cardiovascular events in patients with congenital heart disease. Although artificial intelligence-enhanced electrocardiogram (AI-ECG) analysis is predictive of LVSD in the general adult population, it has yet to be applied comprehensively across congenital heart disease lesions.</div></div><div><h3>Methods</h3><div>We trained a convolutional neural network on paired ECG–echocardiograms (≤2 days apart) across the lifespan of a wide range of congenital heart disease lesions to detect left ventricular ejection fraction (LVEF) of 40% or less. Model performance was evaluated on single ECG–echocardiogram pairs per patient at Boston Children's Hospital (Boston, MA, USA) and externally at the Children's Hospital of Philadelphia (Philadelphia, PA, USA) using area under the receiver operating (AUROC) and precision-recall (AUPRC) curves.</div></div><div><h3>Findings</h3><div>The training cohort comprised 124 265 ECG–echocardiogram pairs (49 158 patients; median age 10·5 years [IQR 3·5–16·8]; 3381 [2·7%] of 124 265 ECG–echocardiogram pairs with LVEF ≤40%). Test groups included internal testing (21 068 patients; median age 10·9 years [IQR 3·7–17·0]; 3381 [2·7%] of 124 265 ECG–echocardiogram pairs with LVEF ≤40%) and external validation (42 984 patients; median age 10·8 years [IQR 4·9–15·0]; 1313 [1·7%] of 76 400 ECG–echocardiogram pairs with LVEF ≤40%) cohorts. High model performance was achieved during internal testing (AUROC 0·95, AUPRC 0·33) and external validation (AUROC 0·96, AUPRC 0·25) for a wide range of congenital heart disease lesions. Patients with LVEF greater than 40% by echocardiogram who were deemed high risk by AI-ECG were more likely to have future dysfunction compared with low-risk patients (hazard ratio 12·1 [95% CI 8·4–17·3]; p<0·0001). High-risk patients by AI-ECG were at increased risk of mortality in the overall cohort and lesion-specific subgroups. Common salient features highlighted across congenital heart disaese lesions include precordial QRS complexes and T waves, with common high-risk ECG features including deep V2 S waves and lateral precordial T wave inversion. A case study on patients with ventricular pacing showed similar findings.</div></div><div><h3>Interpretation</h3><div>Our externally validated algorithm shows promise in prediction of current and future LVSD in patients with congenital heart disease, providing a clinically impactful, inexpensive, and convenient cardiovascular health tool in this population.</div></div><div><h3>Funding</h3><div>Kostin Innovation Fund, Thrasher Research Fund Early Career Award, Boston Children's Hospital Electrophysiology Research Education Fund, National Institutes of Health, National Institute of Childhood Diseases and Human Development, and National Library of Medicine.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Pages e264-e274"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-25DOI: 10.1016/j.landig.2025.01.003
Amelia Fiske PhD , Sarah Blacker PhD , Lester Darryl Geneviève PhD , Theresa Willem MA , Marie-Christine Fritzsche , Alena Buyx MD , Leo Anthony Celi MD , Stuart McLennan PhD
Many countries around the world do not collect race and ethnicity data in clinical settings. Without such identified data, it is difficult to identify biases in the training data or output of a given artificial intelligence (AI) algorithm, and to work towards medical AI tools that do not exclude or further harm marginalised groups. However, the collection of these data also poses specific risks to racially minoritised populations and other marginalised groups. This Viewpoint weighs the risks of collecting race and ethnicity data in clinical settings against the risks of not collecting those data. The collection of more comprehensive identified data (ie, data that include personal attributes such as race, ethnicity, and sex) has the possibility to benefit racially minoritised populations that have historically faced worse health outcomes and health-care access, and inadequate representation in research. However, the collection of extensive demographic data raises important concerns that include the construction of intersectional social categories (ie, race and its shifting meaning in different sociopolitical contexts), the risks of biological reductionism, and the potential for misuse, particularly in situations of historical exclusion, violence, conflict, genocide, and colonialism. Careful navigation of identified data collection is key to building better AI algorithms and to work towards medicine that does not exclude or harm marginalised groups.
{"title":"Weighing the benefits and risks of collecting race and ethnicity data in clinical settings for medical artificial intelligence","authors":"Amelia Fiske PhD , Sarah Blacker PhD , Lester Darryl Geneviève PhD , Theresa Willem MA , Marie-Christine Fritzsche , Alena Buyx MD , Leo Anthony Celi MD , Stuart McLennan PhD","doi":"10.1016/j.landig.2025.01.003","DOIUrl":"10.1016/j.landig.2025.01.003","url":null,"abstract":"<div><div>Many countries around the world do not collect race and ethnicity data in clinical settings. Without such identified data, it is difficult to identify biases in the training data or output of a given artificial intelligence (AI) algorithm, and to work towards medical AI tools that do not exclude or further harm marginalised groups. However, the collection of these data also poses specific risks to racially minoritised populations and other marginalised groups. This Viewpoint weighs the risks of collecting race and ethnicity data in clinical settings against the risks of not collecting those data. The collection of more comprehensive identified data (ie, data that include personal attributes such as race, ethnicity, and sex) has the possibility to benefit racially minoritised populations that have historically faced worse health outcomes and health-care access, and inadequate representation in research. However, the collection of extensive demographic data raises important concerns that include the construction of intersectional social categories (ie, race and its shifting meaning in different sociopolitical contexts), the risks of biological reductionism, and the potential for misuse, particularly in situations of historical exclusion, violence, conflict, genocide, and colonialism. Careful navigation of identified data collection is key to building better AI algorithms and to work towards medicine that does not exclude or harm marginalised groups.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Pages e286-e294"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-25DOI: 10.1016/j.landig.2025.03.004
{"title":"Correction to Lancet Digit Health 2025; 7: e161–66","authors":"","doi":"10.1016/j.landig.2025.03.004","DOIUrl":"10.1016/j.landig.2025.03.004","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Page e237"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-25DOI: 10.1016/j.landig.2025.03.003
The Lancet Digital Health
{"title":"Beyond the social media ban","authors":"The Lancet Digital Health","doi":"10.1016/j.landig.2025.03.003","DOIUrl":"10.1016/j.landig.2025.03.003","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"7 4","pages":"Page e232"},"PeriodicalIF":23.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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