Hafiz Naderi, Julia Ramírez, Stefan van Duijvenboden, Esmeralda Ruiz Pujadas, Nay Aung, Lin Wang, Choudhary Anwar Ahmed Chahal, Karim Lekadir, Steffen E Petersen, Patricia B Munroe
Aims: Left ventricular hypertrophy (LVH) is an established, independent predictor of cardiovascular disease. Indices derived from the electrocardiogram (ECG) have been used to infer the presence of LVH with limited sensitivity. This study aimed to classify LVH defined by cardiovascular magnetic resonance (CMR) imaging using the 12-lead ECG for cost-effective patient stratification.
Methods and results: We extracted ECG biomarkers with a known physiological association with LVH from the 12-lead ECG of 37 534 participants in the UK Biobank imaging study. Classification models integrating ECG biomarkers and clinical variables were built using logistic regression, support vector machine (SVM) and random forest (RF). The dataset was split into 80% training and 20% test sets for performance evaluation. Ten-fold cross validation was applied with further validation testing performed by separating data based on UK Biobank imaging centres. QRS amplitude and blood pressure (P < 0.001) were the features most strongly associated with LVH. Classification with logistic regression had an accuracy of 81% [sensitivity 70%, specificity 81%, Area under the receiver operator curve (AUC) 0.86], SVM 81% accuracy (sensitivity 72%, specificity 81%, AUC 0.85) and RF 72% accuracy (sensitivity 74%, specificity 72%, AUC 0.83). ECG biomarkers enhanced model performance of all classifiers, compared to using clinical variables alone. Validation testing by UK Biobank imaging centres demonstrated robustness of our models.
Conclusion: A combination of ECG biomarkers and clinical variables were able to predict LVH defined by CMR. Our findings provide support for the ECG as an inexpensive screening tool to risk stratify patients with LVH as a prelude to advanced imaging.
{"title":"Predicting left ventricular hypertrophy from the 12-lead electrocardiogram in the UK Biobank imaging study using machine learning.","authors":"Hafiz Naderi, Julia Ramírez, Stefan van Duijvenboden, Esmeralda Ruiz Pujadas, Nay Aung, Lin Wang, Choudhary Anwar Ahmed Chahal, Karim Lekadir, Steffen E Petersen, Patricia B Munroe","doi":"10.1093/ehjdh/ztad037","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad037","url":null,"abstract":"<p><strong>Aims: </strong>Left ventricular hypertrophy (LVH) is an established, independent predictor of cardiovascular disease. Indices derived from the electrocardiogram (ECG) have been used to infer the presence of LVH with limited sensitivity. This study aimed to classify LVH defined by cardiovascular magnetic resonance (CMR) imaging using the 12-lead ECG for cost-effective patient stratification.</p><p><strong>Methods and results: </strong>We extracted ECG biomarkers with a known physiological association with LVH from the 12-lead ECG of 37 534 participants in the UK Biobank imaging study. Classification models integrating ECG biomarkers and clinical variables were built using logistic regression, support vector machine (SVM) and random forest (RF). The dataset was split into 80% training and 20% test sets for performance evaluation. Ten-fold cross validation was applied with further validation testing performed by separating data based on UK Biobank imaging centres. QRS amplitude and blood pressure (<i>P</i> < 0.001) were the features most strongly associated with LVH. Classification with logistic regression had an accuracy of 81% [sensitivity 70%, specificity 81%, Area under the receiver operator curve (AUC) 0.86], SVM 81% accuracy (sensitivity 72%, specificity 81%, AUC 0.85) and RF 72% accuracy (sensitivity 74%, specificity 72%, AUC 0.83). ECG biomarkers enhanced model performance of all classifiers, compared to using clinical variables alone. Validation testing by UK Biobank imaging centres demonstrated robustness of our models.</p><p><strong>Conclusion: </strong>A combination of ECG biomarkers and clinical variables were able to predict LVH defined by CMR. Our findings provide support for the ECG as an inexpensive screening tool to risk stratify patients with LVH as a prelude to advanced imaging.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10393938/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9935781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Thomas Newman, Raunak Borker, Louise Aubiniere-Robb, Justin Hendrickson, Dipankar Choudhury, Ian Halliday, John Fenner, Andrew Narracott, D Rodney Hose, Rebecca Gosling, Julian P Gunn, Paul D Morris
Aims: Over the last ten years, virtual Fractional Flow Reserve (vFFR) has improved the utility of Fractional Flow Reserve (FFR), a globally recommended assessment to guide coronary interventions. Although the speed of vFFR computation has accelerated, techniques utilising full 3D computational fluid dynamics (CFD) solutions rather than simplified analytical solutions still require significant time to compute.
Methods and results: This study investigated the speed, accuracy and cost of a novel 3D-CFD software method based upon a graphic processing unit (GPU) computation, compared with the existing fastest central processing unit (CPU)-based 3D-CFD technique, on 40 angiographic cases. The novel GPU simulation was significantly faster than the CPU method (median 31.7 s (Interquartile Range (IQR) 24.0-44.4s) vs. 607.5 s (490-964 s), P < 0.0001). The novel GPU technique was 99.6% (IQR 99.3-99.9) accurate relative to the CPU method. The initial cost of the GPU hardware was greater than the CPU (£4080 vs. £2876), but the median energy consumption per case was significantly less using the GPU method (8.44 (6.80-13.39) Wh vs. 2.60 (2.16-3.12) Wh, P < 0.0001).
Conclusion: This study demonstrates that vFFR can be computed using 3D-CFD with up to 28-fold acceleration than previous techniques with no clinically significant sacrifice in accuracy.
目的:在过去的十年中,虚拟分数血流储备(vFFR)提高了分数血流储备(FFR)的效用,这是一种全球推荐的指导冠状动脉介入治疗的评估方法。尽管vFFR的计算速度已经加快,但利用全3D计算流体动力学(CFD)解决方案而不是简化的分析解决方案的技术仍然需要大量的计算时间。方法与结果:本研究以40例血管造影病例为研究对象,对比了基于图形处理单元(GPU)计算的新型3D-CFD软件方法与现有最快的基于中央处理单元(CPU)的3D-CFD技术的速度、准确性和成本。新型GPU模拟明显快于CPU方法(中位数31.7 s(四分位间距(IQR) 24.0-44.4s) vs. 607.5 s (490-964 s), P < 0.0001)。与CPU方法相比,该方法的准确率为99.6% (IQR为99.3-99.9)。GPU硬件的初始成本高于CPU(4080英镑对2876英镑),但使用GPU方法的每个案例的中位数能耗明显更低(8.44 (6.80-13.39)Wh vs 2.60 (2.16-3.12) Wh, P < 0.0001)。结论:本研究表明,使用3D-CFD计算vFFR可以比以前的技术加速28倍,并且没有临床上显著的准确性牺牲。
{"title":"Rapid virtual fractional flow reserve using 3D computational fluid dynamics.","authors":"Thomas Newman, Raunak Borker, Louise Aubiniere-Robb, Justin Hendrickson, Dipankar Choudhury, Ian Halliday, John Fenner, Andrew Narracott, D Rodney Hose, Rebecca Gosling, Julian P Gunn, Paul D Morris","doi":"10.1093/ehjdh/ztad028","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad028","url":null,"abstract":"<p><strong>Aims: </strong>Over the last ten years, virtual Fractional Flow Reserve (vFFR) has improved the utility of Fractional Flow Reserve (FFR), a globally recommended assessment to guide coronary interventions. Although the speed of vFFR computation has accelerated, techniques utilising full 3D computational fluid dynamics (CFD) solutions rather than simplified analytical solutions still require significant time to compute.</p><p><strong>Methods and results: </strong>This study investigated the speed, accuracy and cost of a novel 3D-CFD software method based upon a graphic processing unit (GPU) computation, compared with the existing fastest central processing unit (CPU)-based 3D-CFD technique, on 40 angiographic cases. The novel GPU simulation was significantly faster than the CPU method (median 31.7 s (Interquartile Range (IQR) 24.0-44.4s) vs. 607.5 s (490-964 s), <i>P</i> < 0.0001). The novel GPU technique was 99.6% (IQR 99.3-99.9) accurate relative to the CPU method. The initial cost of the GPU hardware was greater than the CPU (£4080 vs. £2876), but the median energy consumption per case was significantly less using the GPU method (8.44 (6.80-13.39) Wh vs. 2.60 (2.16-3.12) Wh, <i>P</i> < 0.0001).</p><p><strong>Conclusion: </strong>This study demonstrates that vFFR can be computed using 3D-CFD with up to 28-fold acceleration than previous techniques with no clinically significant sacrifice in accuracy.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10393878/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9938895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tommas Evan Biersteker, Mark J Boogers, Martin Jan Schalij, Jerry Braun, Rolf H H Groenwold, Douwe E Atsma, Roderick Willem Treskes
Aims: Lowering low-density lipoprotein (LDL-C) and blood pressure (BP) levels to guideline recommended values reduces the risk of major adverse cardiac events in patients who underwent coronary artery bypass grafting (CABG). To improve cardiovascular risk management, this study evaluated the effects of mobile health (mHealth) on BP and cholesterol levels in patients after standalone CABG.
Methods and results: This study is a post hoc analysis of an observational cohort study among 228 adult patients who underwent standalone CABG surgery at a tertiary care hospital in The Netherlands. A total of 117 patients received standard care, and 111 patients underwent an mHealth intervention. This consisted of frequent BP and weight monitoring with regimen adjustment in case of high BP. Primary outcome was difference in systolic BP and LDL-C between baseline and value after three months of follow-up. Mean age in the intervention group was 62.7 years, 98 (88.3%) patients were male. A total of 26 449 mHealth measurements were recorded. At three months, systolic BP decreased by 7.0 mmHg [standard deviation (SD): 15.1] in the intervention group vs. -0.3 mmHg (SD: 17.6; P < 0.00001) in controls; body weight decreased by 1.76 kg (SD: 3.23) in the intervention group vs. -0.31 kg (SD: 2.55; P = 0.002) in controls. Serum LDL-C was significantly lower in the intervention group vs. controls (median: 1.8 vs. 2.0 mmol/L; P = 0.0002).
Conclusion: This study showed an association between home monitoring after CABG and a reduction in systolic BP, body weight, and serum LDL-C. The causality of the association between the observed weight loss and decreased LDL-C in intervention group patients remains to be investigated.
目的:降低低密度脂蛋白(LDL-C)和血压(BP)水平至指南推荐值,可降低接受冠状动脉旁路移植术(CABG)患者发生主要心脏不良事件的风险。为了改善心血管风险管理,本研究评估了移动健康(mHealth)对独立冠脉搭桥术后患者血压和胆固醇水平的影响。方法和结果:本研究是对一项观察性队列研究的事后分析,该研究纳入了228名在荷兰一家三级医院接受独立冠脉搭桥手术的成年患者。共有117名患者接受了标准治疗,111名患者接受了移动健康干预。这包括频繁的血压和体重监测,并在血压高的情况下调整方案。主要转归是随访3个月后收缩压和LDL-C与基线值的差异。干预组平均年龄62.7岁,男性98例(88.3%)。总共记录了26 449次移动健康测量。3个月时,干预组收缩压下降7.0 mmHg[标准差(SD): 15.1],对照组为-0.3 mmHg (SD: 17.6;P < 0.00001);干预组体重下降1.76 kg (SD: 3.23),干预组体重下降-0.31 kg (SD: 2.55);P = 0.002)。干预组血清LDL-C明显低于对照组(中位数:1.8 vs 2.0 mmol/L;P = 0.0002)。结论:本研究显示CABG后的家庭监测与收缩压、体重和血清LDL-C的降低有关。干预组患者观察到的体重减轻与LDL-C降低之间的因果关系仍有待研究。
{"title":"Mobile health for cardiovascular risk management after cardiac surgery: results of a sub-analysis of The Box 2.0 study.","authors":"Tommas Evan Biersteker, Mark J Boogers, Martin Jan Schalij, Jerry Braun, Rolf H H Groenwold, Douwe E Atsma, Roderick Willem Treskes","doi":"10.1093/ehjdh/ztad035","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad035","url":null,"abstract":"<p><strong>Aims: </strong>Lowering low-density lipoprotein (LDL-C) and blood pressure (BP) levels to guideline recommended values reduces the risk of major adverse cardiac events in patients who underwent coronary artery bypass grafting (CABG). To improve cardiovascular risk management, this study evaluated the effects of mobile health (mHealth) on BP and cholesterol levels in patients after standalone CABG.</p><p><strong>Methods and results: </strong>This study is a <i>post hoc</i> analysis of an observational cohort study among 228 adult patients who underwent standalone CABG surgery at a tertiary care hospital in The Netherlands. A total of 117 patients received standard care, and 111 patients underwent an mHealth intervention. This consisted of frequent BP and weight monitoring with regimen adjustment in case of high BP. Primary outcome was difference in systolic BP and LDL-C between baseline and value after three months of follow-up. Mean age in the intervention group was 62.7 years, 98 (88.3%) patients were male. A total of 26 449 mHealth measurements were recorded. At three months, systolic BP decreased by 7.0 mmHg [standard deviation (SD): 15.1] in the intervention group vs. -0.3 mmHg (SD: 17.6; <i>P</i> < 0.00001) in controls; body weight decreased by 1.76 kg (SD: 3.23) in the intervention group vs. -0.31 kg (SD: 2.55; <i>P</i> = 0.002) in controls. Serum LDL-C was significantly lower in the intervention group vs. controls (median: 1.8 vs. 2.0 mmol/L; <i>P</i> = 0.0002).</p><p><strong>Conclusion: </strong>This study showed an association between home monitoring after CABG and a reduction in systolic BP, body weight, and serum LDL-C. The causality of the association between the observed weight loss and decreased LDL-C in intervention group patients remains to be investigated.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/5b/33/ztad035.PMC10393886.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9935780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27eCollection Date: 2023-10-01DOI: 10.1093/ehjdh/ztad046
Peter Daniel Serfözö, Robin Sandkühler, Bibiana Blümke, Emil Matthisson, Jana Meier, Jolein Odermatt, Patrick Badertscher, Christian Sticherling, Ivo Strebel, Philippe C Cattin, Jens Eckstein
Aims: It has been demonstrated that several cardiac pathologies, including myocardial ischaemia, can be detected using smartwatch electrocardiograms (ECGs). Correct placement of bipolar chest leads remains a major challenge in the outpatient population.
Methods and results: In this feasibility trial, we propose an augmented reality-based smartphone app that guides the user to place the smartwatch in predefined positions on the chest using the front camera of a smartphone. A machine-learning model using MobileNet_v2 as the backbone was trained to detect the bipolar lead positions V1-V6 and visually project them onto the user's chest. Following the smartwatch recordings, a conventional 10 s, 12-lead ECG was recorded for comparison purposes. All 50 patients participating in the study were able to conduct a 9-lead smartwatch ECG using the app and assistance from the study team. Twelve patients were able to record all the limb and chest leads using the app without additional support. Bipolar chest leads recorded with smartwatch ECGs were assigned to standard unipolar Wilson leads by blinded cardiologists based on visual characteristics. In every lead, at least 86% of the ECGs were assigned correctly, indicating the remarkable similarity of the smartwatch to standard ECG recordings.
Conclusion: We have introduced an augmented reality-based method to independently record multichannel smartwatch ECGs in an outpatient setting.
{"title":"An augmented reality-based method to assess precordial electrocardiogram leads: a feasibility trial.","authors":"Peter Daniel Serfözö, Robin Sandkühler, Bibiana Blümke, Emil Matthisson, Jana Meier, Jolein Odermatt, Patrick Badertscher, Christian Sticherling, Ivo Strebel, Philippe C Cattin, Jens Eckstein","doi":"10.1093/ehjdh/ztad046","DOIUrl":"10.1093/ehjdh/ztad046","url":null,"abstract":"<p><strong>Aims: </strong>It has been demonstrated that several cardiac pathologies, including myocardial ischaemia, can be detected using smartwatch electrocardiograms (ECGs). Correct placement of bipolar chest leads remains a major challenge in the outpatient population.</p><p><strong>Methods and results: </strong>In this feasibility trial, we propose an augmented reality-based smartphone app that guides the user to place the smartwatch in predefined positions on the chest using the front camera of a smartphone. A machine-learning model using MobileNet_v2 as the backbone was trained to detect the bipolar lead positions V1-V6 and visually project them onto the user's chest. Following the smartwatch recordings, a conventional 10 s, 12-lead ECG was recorded for comparison purposes. All 50 patients participating in the study were able to conduct a 9-lead smartwatch ECG using the app and assistance from the study team. Twelve patients were able to record all the limb and chest leads using the app without additional support. Bipolar chest leads recorded with smartwatch ECGs were assigned to standard unipolar Wilson leads by blinded cardiologists based on visual characteristics. In every lead, at least 86% of the ECGs were assigned correctly, indicating the remarkable similarity of the smartwatch to standard ECG recordings.</p><p><strong>Conclusion: </strong>We have introduced an augmented reality-based method to independently record multichannel smartwatch ECGs in an outpatient setting.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/d9/3d/ztad046.PMC10545517.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41123451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-25eCollection Date: 2023-10-01DOI: 10.1093/ehjdh/ztad045
Thomas Lindow, Maren Maanja, Erik B Schelbert, Antônio H Ribeiro, Antonio Luiz P Ribeiro, Todd T Schlegel, Martin Ugander
Aims: Deep neural network artificial intelligence (DNN-AI)-based Heart Age estimations have been presented and used to show that the difference between an electrocardiogram (ECG)-estimated Heart Age and chronological age is associated with prognosis. An accurate ECG Heart Age, without DNNs, has been developed using explainable advanced ECG (A-ECG) methods. We aimed to evaluate the prognostic value of the explainable A-ECG Heart Age and compare its performance to a DNN-AI Heart Age.
Methods and results: Both A-ECG and DNN-AI Heart Age were applied to patients who had undergone clinical cardiovascular magnetic resonance imaging. The association between A-ECG or DNN-AI Heart Age Gap and cardiovascular risk factors was evaluated using logistic regression. The association between Heart Age Gaps and death or heart failure (HF) hospitalization was evaluated using Cox regression adjusted for clinical covariates/comorbidities. Among patients [n = 731, 103 (14.1%) deaths, 52 (7.1%) HF hospitalizations, median (interquartile range) follow-up 5.7 (4.7-6.7) years], A-ECG Heart Age Gap was associated with risk factors and outcomes [unadjusted hazard ratio (HR) (95% confidence interval) (5 year increments): 1.23 (1.13-1.34) and adjusted HR 1.11 (1.01-1.22)]. DNN-AI Heart Age Gap was associated with risk factors and outcomes after adjustments [HR (5 year increments): 1.11 (1.01-1.21)], but not in unadjusted analyses [HR 1.00 (0.93-1.08)], making it less easily applicable in clinical practice.
Conclusion: A-ECG Heart Age Gap is associated with cardiovascular risk factors and HF hospitalization or death. Explainable A-ECG Heart Age Gap has the potential for improving clinical adoption and prognostic performance compared with existing DNN-AI-type methods.
{"title":"Heart age gap estimated by explainable advanced electrocardiography is associated with cardiovascular risk factors and survival.","authors":"Thomas Lindow, Maren Maanja, Erik B Schelbert, Antônio H Ribeiro, Antonio Luiz P Ribeiro, Todd T Schlegel, Martin Ugander","doi":"10.1093/ehjdh/ztad045","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad045","url":null,"abstract":"<p><strong>Aims: </strong>Deep neural network artificial intelligence (DNN-AI)-based Heart Age estimations have been presented and used to show that the difference between an electrocardiogram (ECG)-estimated Heart Age and chronological age is associated with prognosis. An accurate ECG Heart Age, without DNNs, has been developed using explainable advanced ECG (A-ECG) methods. We aimed to evaluate the prognostic value of the explainable A-ECG Heart Age and compare its performance to a DNN-AI Heart Age.</p><p><strong>Methods and results: </strong>Both A-ECG and DNN-AI Heart Age were applied to patients who had undergone clinical cardiovascular magnetic resonance imaging. The association between A-ECG or DNN-AI Heart Age Gap and cardiovascular risk factors was evaluated using logistic regression. The association between Heart Age Gaps and death or heart failure (HF) hospitalization was evaluated using Cox regression adjusted for clinical covariates/comorbidities. Among patients [<i>n</i> = 731, 103 (14.1%) deaths, 52 (7.1%) HF hospitalizations, median (interquartile range) follow-up 5.7 (4.7-6.7) years], A-ECG Heart Age Gap was associated with risk factors and outcomes [unadjusted hazard ratio (HR) (95% confidence interval) (5 year increments): 1.23 (1.13-1.34) and adjusted HR 1.11 (1.01-1.22)]. DNN-AI Heart Age Gap was associated with risk factors and outcomes after adjustments [HR (5 year increments): 1.11 (1.01-1.21)], but not in unadjusted analyses [HR 1.00 (0.93-1.08)], making it less easily applicable in clinical practice.</p><p><strong>Conclusion: </strong>A-ECG Heart Age Gap is associated with cardiovascular risk factors and HF hospitalization or death. Explainable A-ECG Heart Age Gap has the potential for improving clinical adoption and prognostic performance compared with existing DNN-AI-type methods.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ad/fe/ztad045.PMC10545529.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41143601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-16eCollection Date: 2023-10-01DOI: 10.1093/ehjdh/ztad040
Chris Plummer, Danny Mathysen, Clive Lawson
success in this or similar exams. The EECC’s remote proctoring
{"title":"Does ChatGPT succeed in the European Exam in Core Cardiology?","authors":"Chris Plummer, Danny Mathysen, Clive Lawson","doi":"10.1093/ehjdh/ztad040","DOIUrl":"10.1093/ehjdh/ztad040","url":null,"abstract":"success in this or similar exams. The EECC’s remote proctoring","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/7e/ba/ztad040.PMC10545492.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41180625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-13eCollection Date: 2023-10-01DOI: 10.1093/ehjdh/ztad044
Jorge Mariscal-Harana, Clint Asher, Vittoria Vergani, Maleeha Rizvi, Louise Keehn, Raymond J Kim, Robert M Judd, Steffen E Petersen, Reza Razavi, Andrew P King, Bram Ruijsink, Esther Puyol-Antón
Aims: Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases.
Methods and results: Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset (n = 414) and five external datasets (n = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups.
Conclusion: We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.
{"title":"An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases.","authors":"Jorge Mariscal-Harana, Clint Asher, Vittoria Vergani, Maleeha Rizvi, Louise Keehn, Raymond J Kim, Robert M Judd, Steffen E Petersen, Reza Razavi, Andrew P King, Bram Ruijsink, Esther Puyol-Antón","doi":"10.1093/ehjdh/ztad044","DOIUrl":"10.1093/ehjdh/ztad044","url":null,"abstract":"<p><strong>Aims: </strong>Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases.</p><p><strong>Methods and results: </strong>Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset (<i>n</i> = 414) and five external datasets (<i>n</i> = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups.</p><p><strong>Conclusion: </strong>We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10545512/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41157893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}