R. Herman, H. P. Meyers, Stephen W Smith, D. Bertolone, A. Leone, Konstantinos Bermpeis, M. M. Viscusi, M. Belmonte, A. Demolder, V. Boza, B. Vavrik, V. Kresnakova, Andrej Iring, M. Martonak, Jakub Bahyl, Timea Kisova, D. Schelfaut, M. Vanderheyden, L. Perl, Emre Aslanger, R. Hatala, Wojtek Wojakowski, J. Bartunek, Emanuele Barbato
Majority of acute coronary syndromes (ACS) present without typical ST-elevation. One third of Non-ST-elevation myocardial infarction (NSTEMI) patients have an acutely occluded culprit coronary artery (occlusion myocardial infarction [OMI]), leading to poor outcomes due to delayed identification and invasive management. We sought to develop a versatile artificial intelligence (AI)-model detecting acute OMI on single standard 12-lead electrocardiograms (ECGs) and compare its performance to existing state-of-the-art diagnostic criteria. An AI model was developed using 18,616 ECGs from 10,543 patients with suspected ACS from an international database with clinically validated outcomes. The model was evaluated in an international cohort and compared with STEMI criteria and ECG experts in detecting OMI. Primary outcome of OMI was an acutely occluded or flow-limiting culprit artery requiring emergent revascularization. In the overall test set of 3,254 ECGs from 2,222 patients (age 62 ± 14 years, 67% males, 21.6% OMI), the AI model achieved an area under the curve (AUC) of 0.938 (95% CI: 0.924-0.951) in identifying the primary OMI outcome, with superior performance (accuracy 90.9% [95% CI: 89.7-92.0], sensitivity 80.6% [95% CI: 76.8-84.0], specificity 93.7 [95% CI: 92.6-94.8]) compared to STEMI criteria (accuracy 83.6% [95% CI: 82.1-85.1], sensitivity 32.5% [95% CI: 28.4-36.6], specificity 97.7% [95% CI: 97.0-98.3]) and similar performance compared to ECG experts (accuracy 90.8% [95% CI: 89.5-91.9], sensitivity 73.0% [95% CI: 68.7-77.0], specificity 95.7% [95% CI: 94.7-96.6]). The present novel ECG AI model demonstrates superior accuracy to detect acute OMI when compared to the STEMI criteria. This suggests its potential to improve ACS triage ensuring appropriate and timely referral for immediate revascularization.
{"title":"International evaluation of an artificial intelligence-powered ecg model detecting acute coronary occlusion myocardial infarction","authors":"R. Herman, H. P. Meyers, Stephen W Smith, D. Bertolone, A. Leone, Konstantinos Bermpeis, M. M. Viscusi, M. Belmonte, A. Demolder, V. Boza, B. Vavrik, V. Kresnakova, Andrej Iring, M. Martonak, Jakub Bahyl, Timea Kisova, D. Schelfaut, M. Vanderheyden, L. Perl, Emre Aslanger, R. Hatala, Wojtek Wojakowski, J. Bartunek, Emanuele Barbato","doi":"10.1093/ehjdh/ztad074","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad074","url":null,"abstract":"Majority of acute coronary syndromes (ACS) present without typical ST-elevation. One third of Non-ST-elevation myocardial infarction (NSTEMI) patients have an acutely occluded culprit coronary artery (occlusion myocardial infarction [OMI]), leading to poor outcomes due to delayed identification and invasive management. We sought to develop a versatile artificial intelligence (AI)-model detecting acute OMI on single standard 12-lead electrocardiograms (ECGs) and compare its performance to existing state-of-the-art diagnostic criteria. An AI model was developed using 18,616 ECGs from 10,543 patients with suspected ACS from an international database with clinically validated outcomes. The model was evaluated in an international cohort and compared with STEMI criteria and ECG experts in detecting OMI. Primary outcome of OMI was an acutely occluded or flow-limiting culprit artery requiring emergent revascularization. In the overall test set of 3,254 ECGs from 2,222 patients (age 62 ± 14 years, 67% males, 21.6% OMI), the AI model achieved an area under the curve (AUC) of 0.938 (95% CI: 0.924-0.951) in identifying the primary OMI outcome, with superior performance (accuracy 90.9% [95% CI: 89.7-92.0], sensitivity 80.6% [95% CI: 76.8-84.0], specificity 93.7 [95% CI: 92.6-94.8]) compared to STEMI criteria (accuracy 83.6% [95% CI: 82.1-85.1], sensitivity 32.5% [95% CI: 28.4-36.6], specificity 97.7% [95% CI: 97.0-98.3]) and similar performance compared to ECG experts (accuracy 90.8% [95% CI: 89.5-91.9], sensitivity 73.0% [95% CI: 68.7-77.0], specificity 95.7% [95% CI: 94.7-96.6]). The present novel ECG AI model demonstrates superior accuracy to detect acute OMI when compared to the STEMI criteria. This suggests its potential to improve ACS triage ensuring appropriate and timely referral for immediate revascularization.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139219332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daniel Axford, Ferdous Sohel, V. Abedi, Ye Zhu, R. Zand, Ebrahim Barkoudah, Troy Krupica, Kingsley Iheasirim, U. M. Sharma, S. Dugani, Paul Y Takahashi, S. Bhagra, Mohammad H Murad, Gustavo Saposnik, M. Yousufuddin
We developed new ML models and externally validated existing statistical models (ischemic stroke predictive risk score [iScore] and totaled health risks in vascular events [THRIVE] scores) for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first AIS. In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models (random forest [RF], support vector machine [SVM], and extreme gradient boosting [XGBOOST]) and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11% and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curves (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE. The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new datasets.
{"title":"Development and internal validation of machine learning-based models and external validation of existing risk scores for outcome prediction in patients with ischemic stroke","authors":"Daniel Axford, Ferdous Sohel, V. Abedi, Ye Zhu, R. Zand, Ebrahim Barkoudah, Troy Krupica, Kingsley Iheasirim, U. M. Sharma, S. Dugani, Paul Y Takahashi, S. Bhagra, Mohammad H Murad, Gustavo Saposnik, M. Yousufuddin","doi":"10.1093/ehjdh/ztad073","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad073","url":null,"abstract":"We developed new ML models and externally validated existing statistical models (ischemic stroke predictive risk score [iScore] and totaled health risks in vascular events [THRIVE] scores) for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first AIS. In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models (random forest [RF], support vector machine [SVM], and extreme gradient boosting [XGBOOST]) and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11% and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curves (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE. The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new datasets.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139247684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"From Data to Wisdom: Harnessing the Power of Multimodal Approach for Personalized Atherosclerotic Cardiovascular Risk Assessment","authors":"Sadeer Al-Kindi, Khurram Nasir","doi":"10.1093/ehjdh/ztad068","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad068","url":null,"abstract":"","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"53 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139261015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Caroline Morbach, Götz Gelbrich, M. Schreckenberg, Maike Hedemann, Dora Pelin, N. Scholz, O. Miljukov, Achim Wagner, Fabian Theisen, N. Hitschrich, Hendrik Wiebel, Daniel Stapf, Oliver Karch, Stefan Frantz, Peter U Heuschmann, Stefan Störk
Machine-learning (ML)-based automated measurement of echocardiography images emerged as an option to reduce observer variability. To improve the accuracy of a pre-existing automated reading tool (“original detector”) by federated ML-based re-training. AVE (Automatisierte Vermessung der Echokardiographie) was based on the echocardiography images of n = 4,965 participants of the population-based Characteristics and Course of Heart Failure Stages A-B and Determinants of Progression Cohort Study. We implemented federated ML: echocardiography images were read by the Academic CoreLab Ultrasound-based Cardiovascular Imaging at the University Hospital Würzburg (UKW). A random algorithm selected 3,226 participants for re-training of the original detector. According to data protection rules, generation of ground truth and ML training cycles took place within the UKW network. Only non-personal training weights were exchanged with the external cooperation partner for refinement of ML algorithms. Both the original detector as the re-trained detector were then applied to the echocardiograms of n = 563 participants not used for training. With regards to the human referent the re-trained detector revealed 1) superior accuracy when contrasted with the original detector´s performance as it arrived at significantly smaller mean differences in all but one parameter, and 2) smaller absolute difference between measurements when compared to a group of different human observers. Population data based ML in a federated ML set-up was feasible. The re-trained detector exhibited a much lower measurement variability than human readers. This gain in accuracy and precision strengthens the confidence into automated echocardiographic readings, which carries large potential for applications in various settings.
基于机器学习（ML）的超声心动图图像自动测量是减少观察者变异性的一种选择。 通过基于联合 ML 的再训练，提高已有自动读取工具（"原始检测器"）的准确性。 AVE（Automatisierte Vermessung der Echokardiographie）基于基于人群的心力衰竭 A-B 期特征和病程及进展决定因素队列研究中 n = 4965 名参与者的超声心动图图像。我们采用了联盟式 ML：超声心动图图像由维尔茨堡大学医院（UKW）的超声心血管成像学术核心实验室读取。随机算法选择了 3226 名参与者对原始检测器进行再训练。根据数据保护规则，基本事实的生成和 ML 训练周期均在 UKW 网络内进行。为改进 ML 算法，只与外部合作伙伴交换非个人训练权重。 然后，原始检测器和重新训练的检测器都应用于未用于训练的 n = 563 名参与者的超声心动图。就人类参照物而言，重新训练的检测器显示：1）与原始检测器的性能相比，其准确性更高，因为除一个参数外，它在所有参数上的平均差异都明显更小；2）与一组不同的人类观察者相比，测量结果之间的绝对差异更小。 在联合 ML 设置中基于种群数据的 ML 是可行的。与人类读者相比，经过重新训练的检测器显示出更低的测量变异性。准确度和精确度的提高增强了人们对自动超声心动图读数的信心，这在各种场合都有巨大的应用潜力。
{"title":"Population data-based federated machine-learning improves automated echocardiographic quantification of cardiac structure and function – the AVE project","authors":"Caroline Morbach, Götz Gelbrich, M. Schreckenberg, Maike Hedemann, Dora Pelin, N. Scholz, O. Miljukov, Achim Wagner, Fabian Theisen, N. Hitschrich, Hendrik Wiebel, Daniel Stapf, Oliver Karch, Stefan Frantz, Peter U Heuschmann, Stefan Störk","doi":"10.1093/ehjdh/ztad069","DOIUrl":"https://doi.org/10.1093/ehjdh/ztad069","url":null,"abstract":"Machine-learning (ML)-based automated measurement of echocardiography images emerged as an option to reduce observer variability. To improve the accuracy of a pre-existing automated reading tool (“original detector”) by federated ML-based re-training. AVE (Automatisierte Vermessung der Echokardiographie) was based on the echocardiography images of n = 4,965 participants of the population-based Characteristics and Course of Heart Failure Stages A-B and Determinants of Progression Cohort Study. We implemented federated ML: echocardiography images were read by the Academic CoreLab Ultrasound-based Cardiovascular Imaging at the University Hospital Würzburg (UKW). A random algorithm selected 3,226 participants for re-training of the original detector. According to data protection rules, generation of ground truth and ML training cycles took place within the UKW network. Only non-personal training weights were exchanged with the external cooperation partner for refinement of ML algorithms. Both the original detector as the re-trained detector were then applied to the echocardiograms of n = 563 participants not used for training. With regards to the human referent the re-trained detector revealed 1) superior accuracy when contrasted with the original detector´s performance as it arrived at significantly smaller mean differences in all but one parameter, and 2) smaller absolute difference between measurements when compared to a group of different human observers. Population data based ML in a federated ML set-up was feasible. The re-trained detector exhibited a much lower measurement variability than human readers. This gain in accuracy and precision strengthens the confidence into automated echocardiographic readings, which carries large potential for applications in various settings.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"37 9-10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139275005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：