Lei Lu, Tingting Zhu, A. H. Ribeiro, Lei A. Clifton, Erying Zhao, Jiandong Zhou, A. L. Ribeiro, Yuanyuan Zhang, David A. Clifton
Electrocardiogram (ECG) is widely considered the primary test for evaluating cardiovascular diseases. However, the use of artificial intelligence to advance these medical practices and learn new clinical insights from ECGs remains largely unexplored. Utilising a dataset of 2,322,513 ECGs collected from 1,558,772 patients with 7 years of follow-up, we developed a deep learning model with state-of-the-art granularity for the interpretable diagnosis of cardiac abnormalities, gender identification, and hyper- tension screening solely from ECGs, which are then used to stratify the risk of mortality. The model achieved the area under the receiver operating characteristic curve (AUC) scores of 0.998 (95% confidence interval (CI), 0.995-0.999), 0.964 (0.963-0.965), and 0.839 (0.837-0.841) for the three diagnostic tasks separately. Using ECG-predicted results, we find high risks of mortality for subjects with sinus tachycardia (adjusted hazard ratio (HR) of 2.24, 1.96-2.57), and atrial fibrillation (adjusted HR of 2.22, 1.99-2.48). We further use salient morphologies produced by the deep learning model to identify key ECG leads that achieved similar performance for the three diagnoses, and we find that the V1 ECG lead is important for hypertension screening and mortality risk stratification of hypertensive cohorts, with an AUC of 0.816 (0.814-0.818) and a univariate HR of 1.70 (1.61-1.79) for the two tasks separately. Using ECGs alone, our developed model showed cardiologist-level accuracy in interpretable cardiac diagnosis, and the advancement in mortality risk stratification; In addition, the potential to facilitate clinical knowledge discovery for gender and hypertension detection which are not readily available.
{"title":"Decoding 2.3 Million ECGs: Interpretable Deep Learning for Advancing Cardiovascular Diagnosis and Mortality Risk Stratification","authors":"Lei Lu, Tingting Zhu, A. H. Ribeiro, Lei A. Clifton, Erying Zhao, Jiandong Zhou, A. L. Ribeiro, Yuanyuan Zhang, David A. Clifton","doi":"10.1093/ehjdh/ztae014","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae014","url":null,"abstract":"\u0000 Electrocardiogram (ECG) is widely considered the primary test for evaluating cardiovascular diseases. However, the use of artificial intelligence to advance these medical practices and learn new clinical insights from ECGs remains largely unexplored. Utilising a dataset of 2,322,513 ECGs collected from 1,558,772 patients with 7 years of follow-up, we developed a deep learning model with state-of-the-art granularity for the interpretable diagnosis of cardiac abnormalities, gender identification, and hyper- tension screening solely from ECGs, which are then used to stratify the risk of mortality. The model achieved the area under the receiver operating characteristic curve (AUC) scores of 0.998 (95% confidence interval (CI), 0.995-0.999), 0.964 (0.963-0.965), and 0.839 (0.837-0.841) for the three diagnostic tasks separately. Using ECG-predicted results, we find high risks of mortality for subjects with sinus tachycardia (adjusted hazard ratio (HR) of 2.24, 1.96-2.57), and atrial fibrillation (adjusted HR of 2.22, 1.99-2.48). We further use salient morphologies produced by the deep learning model to identify key ECG leads that achieved similar performance for the three diagnoses, and we find that the V1 ECG lead is important for hypertension screening and mortality risk stratification of hypertensive cohorts, with an AUC of 0.816 (0.814-0.818) and a univariate HR of 1.70 (1.61-1.79) for the two tasks separately. Using ECGs alone, our developed model showed cardiologist-level accuracy in interpretable cardiac diagnosis, and the advancement in mortality risk stratification; In addition, the potential to facilitate clinical knowledge discovery for gender and hypertension detection which are not readily available.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"256 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140451926","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}
C. Heeger, J. Vogler, Charlotte Eitel, M. Feher, S. Popescu, B. Kirstein, Sascha Hatahet, Benham Subin, K. Kuck, R. Tilz
Electroanatomical mapping (EAM) systems are essential for treatment of cardiac arrhythmias. The EAM system is usually operated by qualified staff or field technical engineers (FTE) from the control room. Novel remote support technology allows for remote access of EAM via online services. Remote access increases the flexibility of the electrophysiological lab, reduces travel time and overcomes hospital access limitations especially during the COVID-19 pandemic. Here we report on the feasibility and safety of EAM remote access for cardiac ablation procedures. Mapping and ablation were achieved by combining the EnsiteXTM EAM system and the integrated EnsiteTM Connect Remote Support software, together with an integrated audiovisual solution system for remote support (Medinbox). Communication between the operator and the remote support was achieved using an incorporated internet-based common communication platform (ZoomTM), headphones and high-resolution cameras. We investigated 50 remote access assisted consecutive electrophysiological procedures from 09/2022 to 02/2023 (remote group). The data was compared to matched patients (n=50) with onsite support from the control room (control group). The median procedure time was 100min (76, 120) (remote) vs. 86min (60, 110) (control), p=0.090. The procedural success (both groups 100%, p=0.999) and complication rate (remote: 2%, control: 0%, p=0.553) were comparable between the groups. Travel burden could be reduced by 11,280 km. Remote access for EAM was feasible and safe in this single center study. Procedural data were comparable to procedures with onsite support. In the future, this new solution might have a great impact on facilitating electrophysiological procedures.
{"title":"Initial experience, safety and feasibility using remote access or onsite technical support for complex ablation procedures: Results of the REMOTE study","authors":"C. Heeger, J. Vogler, Charlotte Eitel, M. Feher, S. Popescu, B. Kirstein, Sascha Hatahet, Benham Subin, K. Kuck, R. Tilz","doi":"10.1093/ehjdh/ztae013","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae013","url":null,"abstract":"\u0000 \u0000 \u0000 Electroanatomical mapping (EAM) systems are essential for treatment of cardiac arrhythmias. The EAM system is usually operated by qualified staff or field technical engineers (FTE) from the control room. Novel remote support technology allows for remote access of EAM via online services. Remote access increases the flexibility of the electrophysiological lab, reduces travel time and overcomes hospital access limitations especially during the COVID-19 pandemic. Here we report on the feasibility and safety of EAM remote access for cardiac ablation procedures.\u0000 \u0000 \u0000 \u0000 Mapping and ablation were achieved by combining the EnsiteXTM EAM system and the integrated EnsiteTM Connect Remote Support software, together with an integrated audiovisual solution system for remote support (Medinbox). Communication between the operator and the remote support was achieved using an incorporated internet-based common communication platform (ZoomTM), headphones and high-resolution cameras.\u0000 \u0000 \u0000 \u0000 We investigated 50 remote access assisted consecutive electrophysiological procedures from 09/2022 to 02/2023 (remote group). The data was compared to matched patients (n=50) with onsite support from the control room (control group). The median procedure time was 100min (76, 120) (remote) vs. 86min (60, 110) (control), p=0.090. The procedural success (both groups 100%, p=0.999) and complication rate (remote: 2%, control: 0%, p=0.553) were comparable between the groups. Travel burden could be reduced by 11,280 km.\u0000 \u0000 \u0000 \u0000 Remote access for EAM was feasible and safe in this single center study. Procedural data were comparable to procedures with onsite support. In the future, this new solution might have a great impact on facilitating electrophysiological procedures.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"4 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139958609","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}
G. Adasuriya, A. Barsky, I. Kralj-Hans, S. Mohan, S. Gill, Z. Chen, J. Jarman, D. Jones, H. Valli, G. Gkoutos, V. Markides, W. Hussain, T. Wong, D. Kotecha, S. Haldar
This proof-of-concept study sought to evaluate changes in heart rate (HR) obtained from a consumer wearable device and compare against implanted loop recorder (ILR)-detected recurrence of atrial fibrillation (AF) and atrial tachycardia (AT) after AF ablation. REMOTE-AF (NCT05037136) was a prospectively designed sub study of the CASA-AF randomised controlled trial (NCT04280042). Participants without a permanent pacemaker had an implantable loop recorder (ILR) implanted at their index ablation procedure for longstanding persistent atrial fibrillation. HR and step count were continuously monitored using photoplethysmography (PPG) from a commercially available wrist-worn wearable. PPG recorded HR data was pre-processed with noise filtration and episodes at 1-minute intervals over 30 minutes of heart rate elevations (Z-score = 2) were compared to corresponding ILR data. Thirty-five patients were enrolled, with mean age 70.3 +/- 6.8 yrs and median follow-up 10 months (IQR 8-12 months). ILR analysis revealed seventeen out of thirty-five patients (49%) had recurrence of AF/AT. Compared with ILR recurrence, wearable-derived elevations in HR ≥ 110 beats per minute had a sensitivity of 95.3%, specificity 54.1%, positive predictive value (PPV) 15.8%, negative predictive value (NPV) 99.2% and overall accuracy 57.4%. With PPG recorded HR elevation spikes (non-exercise related), the sensitivity was 87.5%, specificity 62.2%, PPV 39.2%, NPV 92.3% and overall accuracy 64.0% in the entire patient cohort. In the AF/AT recurrence only group, sensitivity was 87.6%, specificity 68.3%, PPV 53.6%, NPV 93.0% and overall accuracy 75.0%. Consumer wearable devices have the potential to contribute to arrhythmia detection after AF ablation.
{"title":"Remote Monitoring of AF Recurrence using mHealth Technology (REMOTE-AF)","authors":"G. Adasuriya, A. Barsky, I. Kralj-Hans, S. Mohan, S. Gill, Z. Chen, J. Jarman, D. Jones, H. Valli, G. Gkoutos, V. Markides, W. Hussain, T. Wong, D. Kotecha, S. Haldar","doi":"10.1093/ehjdh/ztae011","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae011","url":null,"abstract":"\u0000 \u0000 \u0000 This proof-of-concept study sought to evaluate changes in heart rate (HR) obtained from a consumer wearable device and compare against implanted loop recorder (ILR)-detected recurrence of atrial fibrillation (AF) and atrial tachycardia (AT) after AF ablation.\u0000 \u0000 \u0000 \u0000 REMOTE-AF (NCT05037136) was a prospectively designed sub study of the CASA-AF randomised controlled trial (NCT04280042). Participants without a permanent pacemaker had an implantable loop recorder (ILR) implanted at their index ablation procedure for longstanding persistent atrial fibrillation. HR and step count were continuously monitored using photoplethysmography (PPG) from a commercially available wrist-worn wearable. PPG recorded HR data was pre-processed with noise filtration and episodes at 1-minute intervals over 30 minutes of heart rate elevations (Z-score = 2) were compared to corresponding ILR data.\u0000 \u0000 \u0000 \u0000 Thirty-five patients were enrolled, with mean age 70.3 +/- 6.8 yrs and median follow-up 10 months (IQR 8-12 months). ILR analysis revealed seventeen out of thirty-five patients (49%) had recurrence of AF/AT. Compared with ILR recurrence, wearable-derived elevations in HR ≥ 110 beats per minute had a sensitivity of 95.3%, specificity 54.1%, positive predictive value (PPV) 15.8%, negative predictive value (NPV) 99.2% and overall accuracy 57.4%. With PPG recorded HR elevation spikes (non-exercise related), the sensitivity was 87.5%, specificity 62.2%, PPV 39.2%, NPV 92.3% and overall accuracy 64.0% in the entire patient cohort. In the AF/AT recurrence only group, sensitivity was 87.6%, specificity 68.3%, PPV 53.6%, NPV 93.0% and overall accuracy 75.0%.\u0000 \u0000 \u0000 \u0000 Consumer wearable devices have the potential to contribute to arrhythmia detection after AF ablation.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"40 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139784678","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}
G. Adasuriya, A. Barsky, I. Kralj-Hans, S. Mohan, S. Gill, Z. Chen, J. Jarman, D. Jones, H. Valli, G. Gkoutos, V. Markides, W. Hussain, T. Wong, D. Kotecha, S. Haldar
This proof-of-concept study sought to evaluate changes in heart rate (HR) obtained from a consumer wearable device and compare against implanted loop recorder (ILR)-detected recurrence of atrial fibrillation (AF) and atrial tachycardia (AT) after AF ablation. REMOTE-AF (NCT05037136) was a prospectively designed sub study of the CASA-AF randomised controlled trial (NCT04280042). Participants without a permanent pacemaker had an implantable loop recorder (ILR) implanted at their index ablation procedure for longstanding persistent atrial fibrillation. HR and step count were continuously monitored using photoplethysmography (PPG) from a commercially available wrist-worn wearable. PPG recorded HR data was pre-processed with noise filtration and episodes at 1-minute intervals over 30 minutes of heart rate elevations (Z-score = 2) were compared to corresponding ILR data. Thirty-five patients were enrolled, with mean age 70.3 +/- 6.8 yrs and median follow-up 10 months (IQR 8-12 months). ILR analysis revealed seventeen out of thirty-five patients (49%) had recurrence of AF/AT. Compared with ILR recurrence, wearable-derived elevations in HR ≥ 110 beats per minute had a sensitivity of 95.3%, specificity 54.1%, positive predictive value (PPV) 15.8%, negative predictive value (NPV) 99.2% and overall accuracy 57.4%. With PPG recorded HR elevation spikes (non-exercise related), the sensitivity was 87.5%, specificity 62.2%, PPV 39.2%, NPV 92.3% and overall accuracy 64.0% in the entire patient cohort. In the AF/AT recurrence only group, sensitivity was 87.6%, specificity 68.3%, PPV 53.6%, NPV 93.0% and overall accuracy 75.0%. Consumer wearable devices have the potential to contribute to arrhythmia detection after AF ablation.
{"title":"Remote Monitoring of AF Recurrence using mHealth Technology (REMOTE-AF)","authors":"G. Adasuriya, A. Barsky, I. Kralj-Hans, S. Mohan, S. Gill, Z. Chen, J. Jarman, D. Jones, H. Valli, G. Gkoutos, V. Markides, W. Hussain, T. Wong, D. Kotecha, S. Haldar","doi":"10.1093/ehjdh/ztae011","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae011","url":null,"abstract":"\u0000 \u0000 \u0000 This proof-of-concept study sought to evaluate changes in heart rate (HR) obtained from a consumer wearable device and compare against implanted loop recorder (ILR)-detected recurrence of atrial fibrillation (AF) and atrial tachycardia (AT) after AF ablation.\u0000 \u0000 \u0000 \u0000 REMOTE-AF (NCT05037136) was a prospectively designed sub study of the CASA-AF randomised controlled trial (NCT04280042). Participants without a permanent pacemaker had an implantable loop recorder (ILR) implanted at their index ablation procedure for longstanding persistent atrial fibrillation. HR and step count were continuously monitored using photoplethysmography (PPG) from a commercially available wrist-worn wearable. PPG recorded HR data was pre-processed with noise filtration and episodes at 1-minute intervals over 30 minutes of heart rate elevations (Z-score = 2) were compared to corresponding ILR data.\u0000 \u0000 \u0000 \u0000 Thirty-five patients were enrolled, with mean age 70.3 +/- 6.8 yrs and median follow-up 10 months (IQR 8-12 months). ILR analysis revealed seventeen out of thirty-five patients (49%) had recurrence of AF/AT. Compared with ILR recurrence, wearable-derived elevations in HR ≥ 110 beats per minute had a sensitivity of 95.3%, specificity 54.1%, positive predictive value (PPV) 15.8%, negative predictive value (NPV) 99.2% and overall accuracy 57.4%. With PPG recorded HR elevation spikes (non-exercise related), the sensitivity was 87.5%, specificity 62.2%, PPV 39.2%, NPV 92.3% and overall accuracy 64.0% in the entire patient cohort. In the AF/AT recurrence only group, sensitivity was 87.6%, specificity 68.3%, PPV 53.6%, NPV 93.0% and overall accuracy 75.0%.\u0000 \u0000 \u0000 \u0000 Consumer wearable devices have the potential to contribute to arrhythmia detection after AF ablation.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"57 34","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139844584","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}
Robert M A van der Boon, A. J. Camm, C. Aguiar, E. Biassin, G. Breithardt, H. Bueno, I. Drossart, N. Hoppe, E. Kamenjasevic, R. Ladeiras-Lopes, P. McrGreavy, P. Lanzer, R. Vidal-Perez, N. Bruining
Social media (SoMe) has witnessed remarkable growth and emerged as a dominant method of communication worldwide. Platforms such as Facebook, X (formerly Twitter), LinkedIn, Instagram, TikTok, and YouTube have become important tools of the digital native generation. In the field of medicine, particularly cardiology, attitudes towards SoMe have shifted, and professionals increasingly utilize it to share scientific findings, network with experts, and enhance teaching and learning. Notably, SoMe is being leveraged for teaching purposes, including the sharing of challenging and intriguing cases. However, sharing patient data, including photos or images, online carries significant implications and risks, potentially compromising individual privacy both online and offline. Privacy and data protection are fundamental rights within European Union (EU) treaties, and the General Data Protection Regulation (GDPR) serves as the cornerstone of data protection legislation. The GDPR outlines crucial requirements, such as obtaining “consent” and implementing “anonymization”, that must be met before sharing sensitive and patient-identifiable information. Additionally, it is vital to consider the patient perspective and prioritize ethical and social considerations when addressing challenges associated with sharing patient information on SoMe platforms. Given the absence of a peer review process and clear guidelines, we present an initial approach, a code of conduct, and recommendations for the ethical use of SoMe. In conclusion, this comprehensive review underscores the importance of a balanced approach that ensures patient privacy and upholds ethical standards while harnessing the immense potential of SoMe to advance cardiology practice and facilitate knowledge dissemination.
社交媒体（SoMe）发展迅猛，已成为世界范围内的主要交流方式。Facebook、X（前 Twitter）、LinkedIn、Instagram、TikTok 和 YouTube 等平台已成为数字原生一代的重要工具。在医学领域，尤其是心脏病学领域，人们对 SoMe 的态度发生了转变，专业人士越来越多地利用它来分享科研成果、与专家建立联系，以及加强教学和学习。值得注意的是，SoMe 正被用于教学目的，包括分享具有挑战性和引人入胜的病例。然而，在网上共享患者数据（包括照片或图像）会带来重大影响和风险，可能会在网上和网下损害个人隐私。隐私和数据保护是欧盟（EU）条约规定的基本权利，而《通用数据保护条例》（GDPR）则是数据保护立法的基石。GDPR 概述了在共享敏感信息和可识别患者身份的信息之前必须满足的关键要求，如获得 "同意 "和实施 "匿名化"。此外，在应对与 SoMe 平台共享患者信息相关的挑战时，必须从患者的角度出发，优先考虑伦理和社会因素。鉴于缺乏同行评审程序和明确的指导原则，我们提出了一种初步方法、行为准则以及关于 SoMe 道德使用的建议。总之，这篇综合评论强调了平衡方法的重要性，即在利用 SoMe 的巨大潜力推动心脏病学实践和促进知识传播的同时，确保患者隐私并坚持道德标准。
{"title":"Risks and Benefits of Sharing Patient Information on Social Media: A Digital Dilemma","authors":"Robert M A van der Boon, A. J. Camm, C. Aguiar, E. Biassin, G. Breithardt, H. Bueno, I. Drossart, N. Hoppe, E. Kamenjasevic, R. Ladeiras-Lopes, P. McrGreavy, P. Lanzer, R. Vidal-Perez, N. Bruining","doi":"10.1093/ehjdh/ztae009","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae009","url":null,"abstract":"\u0000 Social media (SoMe) has witnessed remarkable growth and emerged as a dominant method of communication worldwide. Platforms such as Facebook, X (formerly Twitter), LinkedIn, Instagram, TikTok, and YouTube have become important tools of the digital native generation. In the field of medicine, particularly cardiology, attitudes towards SoMe have shifted, and professionals increasingly utilize it to share scientific findings, network with experts, and enhance teaching and learning. Notably, SoMe is being leveraged for teaching purposes, including the sharing of challenging and intriguing cases. However, sharing patient data, including photos or images, online carries significant implications and risks, potentially compromising individual privacy both online and offline. Privacy and data protection are fundamental rights within European Union (EU) treaties, and the General Data Protection Regulation (GDPR) serves as the cornerstone of data protection legislation. The GDPR outlines crucial requirements, such as obtaining “consent” and implementing “anonymization”, that must be met before sharing sensitive and patient-identifiable information. Additionally, it is vital to consider the patient perspective and prioritize ethical and social considerations when addressing challenges associated with sharing patient information on SoMe platforms. Given the absence of a peer review process and clear guidelines, we present an initial approach, a code of conduct, and recommendations for the ethical use of SoMe. In conclusion, this comprehensive review underscores the importance of a balanced approach that ensures patient privacy and upholds ethical standards while harnessing the immense potential of SoMe to advance cardiology practice and facilitate knowledge dissemination.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"223 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139843469","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}
Robert M A van der Boon, A. J. Camm, C. Aguiar, E. Biassin, G. Breithardt, H. Bueno, I. Drossart, N. Hoppe, E. Kamenjasevic, R. Ladeiras-Lopes, P. McrGreavy, P. Lanzer, R. Vidal-Perez, N. Bruining
Social media (SoMe) has witnessed remarkable growth and emerged as a dominant method of communication worldwide. Platforms such as Facebook, X (formerly Twitter), LinkedIn, Instagram, TikTok, and YouTube have become important tools of the digital native generation. In the field of medicine, particularly cardiology, attitudes towards SoMe have shifted, and professionals increasingly utilize it to share scientific findings, network with experts, and enhance teaching and learning. Notably, SoMe is being leveraged for teaching purposes, including the sharing of challenging and intriguing cases. However, sharing patient data, including photos or images, online carries significant implications and risks, potentially compromising individual privacy both online and offline. Privacy and data protection are fundamental rights within European Union (EU) treaties, and the General Data Protection Regulation (GDPR) serves as the cornerstone of data protection legislation. The GDPR outlines crucial requirements, such as obtaining “consent” and implementing “anonymization”, that must be met before sharing sensitive and patient-identifiable information. Additionally, it is vital to consider the patient perspective and prioritize ethical and social considerations when addressing challenges associated with sharing patient information on SoMe platforms. Given the absence of a peer review process and clear guidelines, we present an initial approach, a code of conduct, and recommendations for the ethical use of SoMe. In conclusion, this comprehensive review underscores the importance of a balanced approach that ensures patient privacy and upholds ethical standards while harnessing the immense potential of SoMe to advance cardiology practice and facilitate knowledge dissemination.
社交媒体（SoMe）发展迅猛，已成为世界范围内的主要交流方式。Facebook、X（前 Twitter）、LinkedIn、Instagram、TikTok 和 YouTube 等平台已成为数字原生一代的重要工具。在医学领域，尤其是心脏病学领域，人们对 SoMe 的态度发生了转变，专业人士越来越多地利用它来分享科研成果、与专家建立联系，以及加强教学和学习。值得注意的是，SoMe 正被用于教学目的，包括分享具有挑战性和引人入胜的病例。然而，在网上共享患者数据（包括照片或图像）会带来重大影响和风险，可能会在网上和网下损害个人隐私。隐私和数据保护是欧盟（EU）条约规定的基本权利，而《通用数据保护条例》（GDPR）则是数据保护立法的基石。GDPR 概述了在共享敏感信息和可识别患者身份的信息之前必须满足的关键要求，如获得 "同意 "和实施 "匿名化"。此外，在应对与 SoMe 平台共享患者信息相关的挑战时，必须从患者的角度出发，优先考虑伦理和社会因素。鉴于缺乏同行评审程序和明确的指导原则，我们提出了一种初步方法、行为准则以及关于 SoMe 道德使用的建议。总之，这篇综合评论强调了平衡方法的重要性，即在利用 SoMe 的巨大潜力推动心脏病学实践和促进知识传播的同时，确保患者隐私并坚持道德标准。
{"title":"Risks and Benefits of Sharing Patient Information on Social Media: A Digital Dilemma","authors":"Robert M A van der Boon, A. J. Camm, C. Aguiar, E. Biassin, G. Breithardt, H. Bueno, I. Drossart, N. Hoppe, E. Kamenjasevic, R. Ladeiras-Lopes, P. McrGreavy, P. Lanzer, R. Vidal-Perez, N. Bruining","doi":"10.1093/ehjdh/ztae009","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae009","url":null,"abstract":"\u0000 Social media (SoMe) has witnessed remarkable growth and emerged as a dominant method of communication worldwide. Platforms such as Facebook, X (formerly Twitter), LinkedIn, Instagram, TikTok, and YouTube have become important tools of the digital native generation. In the field of medicine, particularly cardiology, attitudes towards SoMe have shifted, and professionals increasingly utilize it to share scientific findings, network with experts, and enhance teaching and learning. Notably, SoMe is being leveraged for teaching purposes, including the sharing of challenging and intriguing cases. However, sharing patient data, including photos or images, online carries significant implications and risks, potentially compromising individual privacy both online and offline. Privacy and data protection are fundamental rights within European Union (EU) treaties, and the General Data Protection Regulation (GDPR) serves as the cornerstone of data protection legislation. The GDPR outlines crucial requirements, such as obtaining “consent” and implementing “anonymization”, that must be met before sharing sensitive and patient-identifiable information. Additionally, it is vital to consider the patient perspective and prioritize ethical and social considerations when addressing challenges associated with sharing patient information on SoMe platforms. Given the absence of a peer review process and clear guidelines, we present an initial approach, a code of conduct, and recommendations for the ethical use of SoMe. In conclusion, this comprehensive review underscores the importance of a balanced approach that ensures patient privacy and upholds ethical standards while harnessing the immense potential of SoMe to advance cardiology practice and facilitate knowledge dissemination.","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"71 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139783777","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}
M. Falter, D. Godderis, M. Scherrenberg, S. Kizilkilic, Linqi Xu, Marc Mertens, Jan Jansen, Pascal Legroux, H. Kindermans, Peter Sinnaeve, Frank Neven, P. Dendale
ICD-codes are used for classification of hospitalisations. The codes are used for administrative, financial and research purposes. It is known however that errors occur. Natural language processing (NLP) offers promising solutions for optimising the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding. Two datasets were used: the open-source MIMIC-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses “atrial fibrillation” and “heart failure”. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), XGBoost and BioBERT. All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After pre-processing a total of 1.438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF respectively. There were 211 mismatches between algorithm and ICD codes. 103 were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD-coding (2% of total hospitalisations). A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimise and support the ICD-coding process.
{"title":"Using Natural Language Processing for Automated Classification of Disease and to Identify Misclassified ICD Codes in Cardiac Disease","authors":"M. Falter, D. Godderis, M. Scherrenberg, S. Kizilkilic, Linqi Xu, Marc Mertens, Jan Jansen, Pascal Legroux, H. Kindermans, Peter Sinnaeve, Frank Neven, P. Dendale","doi":"10.1093/ehjdh/ztae008","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae008","url":null,"abstract":"\u0000 \u0000 \u0000 ICD-codes are used for classification of hospitalisations. The codes are used for administrative, financial and research purposes. It is known however that errors occur. Natural language processing (NLP) offers promising solutions for optimising the process.\u0000 \u0000 \u0000 \u0000 To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding.\u0000 \u0000 \u0000 \u0000 Two datasets were used: the open-source MIMIC-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses “atrial fibrillation” and “heart failure”. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), XGBoost and BioBERT. All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset.\u0000 \u0000 \u0000 \u0000 After pre-processing a total of 1.438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF respectively. There were 211 mismatches between algorithm and ICD codes. 103 were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD-coding (2% of total hospitalisations).\u0000 \u0000 \u0000 \u0000 A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimise and support the ICD-coding process.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"411 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139847728","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}
M. Falter, D. Godderis, M. Scherrenberg, S. Kizilkilic, Linqi Xu, Marc Mertens, Jan Jansen, Pascal Legroux, H. Kindermans, Peter Sinnaeve, Frank Neven, P. Dendale
ICD-codes are used for classification of hospitalisations. The codes are used for administrative, financial and research purposes. It is known however that errors occur. Natural language processing (NLP) offers promising solutions for optimising the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding. Two datasets were used: the open-source MIMIC-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses “atrial fibrillation” and “heart failure”. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), XGBoost and BioBERT. All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After pre-processing a total of 1.438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF respectively. There were 211 mismatches between algorithm and ICD codes. 103 were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD-coding (2% of total hospitalisations). A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimise and support the ICD-coding process.
{"title":"Using Natural Language Processing for Automated Classification of Disease and to Identify Misclassified ICD Codes in Cardiac Disease","authors":"M. Falter, D. Godderis, M. Scherrenberg, S. Kizilkilic, Linqi Xu, Marc Mertens, Jan Jansen, Pascal Legroux, H. Kindermans, Peter Sinnaeve, Frank Neven, P. Dendale","doi":"10.1093/ehjdh/ztae008","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae008","url":null,"abstract":"\u0000 \u0000 \u0000 ICD-codes are used for classification of hospitalisations. The codes are used for administrative, financial and research purposes. It is known however that errors occur. Natural language processing (NLP) offers promising solutions for optimising the process.\u0000 \u0000 \u0000 \u0000 To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding.\u0000 \u0000 \u0000 \u0000 Two datasets were used: the open-source MIMIC-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses “atrial fibrillation” and “heart failure”. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), XGBoost and BioBERT. All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset.\u0000 \u0000 \u0000 \u0000 After pre-processing a total of 1.438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF respectively. There were 211 mismatches between algorithm and ICD codes. 103 were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD-coding (2% of total hospitalisations).\u0000 \u0000 \u0000 \u0000 A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimise and support the ICD-coding process.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":" 87","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139788123","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}
Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using preprocedural 12-lead electrocardiogram (ECG) data. We collected preprocedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using fivefold cross validation, and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an AUC of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG data. The performance was better than the Emory score (AUC = 0.704), as well as the Logistic (AUC = 0.574) and XGboost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752. AI-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.
{"title":"ECG-based Prediction of Conduction Disturbances after Transcatheter Aortic Valve Replacement with Convolutional Neural Network","authors":"Yuheng Jia, Yiming Li, Gaden Luosang, Jianyong Wang, Gang Peng, Xingzhou Pu, Weili Jiang, Wenjian Li, Zhengang Zhao, Yong Peng, Yuan Feng, Jiafu Wei, Yuanning Xu, Xingbin Liu, Zhang Yi, Mao Chen","doi":"10.1093/ehjdh/ztae007","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae007","url":null,"abstract":"\u0000 \u0000 \u0000 Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis.\u0000 \u0000 \u0000 \u0000 This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using preprocedural 12-lead electrocardiogram (ECG) data.\u0000 \u0000 \u0000 \u0000 We collected preprocedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using fivefold cross validation, and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features.\u0000 \u0000 \u0000 \u0000 After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an AUC of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG data. The performance was better than the Emory score (AUC = 0.704), as well as the Logistic (AUC = 0.574) and XGboost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752.\u0000 \u0000 \u0000 \u0000 AI-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":" 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139791241","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}
M. van Vliet, S. Monnink, M. Kuiper, J. Constandse, D. Hoftijzer, E. Ronner
Elevated blood pressure is a key risk factor in cardiovascular diseases. However, obtaining reliable and reproducible blood pressure remains a challenge. This study, therefore, aimed to evaluate a novel cuffless wristband, based on photoplethysmography, for continuous blood pressure monitoring. Predictions by a photoplethysmography-guided algorithm were compared to arterial blood pressure measurements (in the subclavian artery), obtained during cardiac catheterisation. Eligible patients were included and screened based on AAMI/ESH/ISO Universal Standard requirements. The machine learning-based blood pressure algorithm required three cuff-based initialisation measurements in combination with approximately 100 features (signal-derived and patient demographic-based). 97 patients and 420 samples were included. Mean age, weight, and height were 67.1 years (SD 11.1), 83.4 kg (SD 16.1), and 174 cm (SD 10), respectively. Systolic blood pressure was ≤100 mmHg in 48 samples (11%) and ≥160 mmHg in 106 samples (25%). Diastolic blood pressure was ≤70 mmHg in 222 samples (53%) and ≥85 mmHg in 99 samples (24%). The algorithm showed mean errors of ±3.7 mmHg (SD 4.4 mmHg) and ±2.5 mmHg (SD 3.7 mmHg) for systolic and diastolic blood pressure, respectively. Similar results were observed across all genders and skin colours (Fitzpatrick I-VI). This study provides initial evidence for the accuracy of a photoplethysmography-based blood pressure algorithm in combination with a cuffless wristband across a range of blood pressure distributions. This research complies with the AAMI/ESH/ISO Universal Standard, however, further research is required to evaluate the algorithms performance in light of the remaining European Society of Hypertension recommendations. Trial registration: www.clinicaltrials.gov, NCT05566886.
{"title":"Evaluation of a novel cuffless photoplethysmography-based wristband for measuring blood pressure according to the regulatory standards","authors":"M. van Vliet, S. Monnink, M. Kuiper, J. Constandse, D. Hoftijzer, E. Ronner","doi":"10.1093/ehjdh/ztae006","DOIUrl":"https://doi.org/10.1093/ehjdh/ztae006","url":null,"abstract":"\u0000 \u0000 \u0000 Elevated blood pressure is a key risk factor in cardiovascular diseases. However, obtaining reliable and reproducible blood pressure remains a challenge. This study, therefore, aimed to evaluate a novel cuffless wristband, based on photoplethysmography, for continuous blood pressure monitoring.\u0000 \u0000 \u0000 \u0000 Predictions by a photoplethysmography-guided algorithm were compared to arterial blood pressure measurements (in the subclavian artery), obtained during cardiac catheterisation. Eligible patients were included and screened based on AAMI/ESH/ISO Universal Standard requirements. The machine learning-based blood pressure algorithm required three cuff-based initialisation measurements in combination with approximately 100 features (signal-derived and patient demographic-based).\u0000 \u0000 \u0000 \u0000 97 patients and 420 samples were included. Mean age, weight, and height were 67.1 years (SD 11.1), 83.4 kg (SD 16.1), and 174 cm (SD 10), respectively. Systolic blood pressure was ≤100 mmHg in 48 samples (11%) and ≥160 mmHg in 106 samples (25%). Diastolic blood pressure was ≤70 mmHg in 222 samples (53%) and ≥85 mmHg in 99 samples (24%). The algorithm showed mean errors of ±3.7 mmHg (SD 4.4 mmHg) and ±2.5 mmHg (SD 3.7 mmHg) for systolic and diastolic blood pressure, respectively. Similar results were observed across all genders and skin colours (Fitzpatrick I-VI).\u0000 \u0000 \u0000 \u0000 This study provides initial evidence for the accuracy of a photoplethysmography-based blood pressure algorithm in combination with a cuffless wristband across a range of blood pressure distributions. This research complies with the AAMI/ESH/ISO Universal Standard, however, further research is required to evaluate the algorithms performance in light of the remaining European Society of Hypertension recommendations.\u0000 Trial registration: www.clinicaltrials.gov, NCT05566886.\u0000","PeriodicalId":508387,"journal":{"name":"European Heart Journal - Digital Health","volume":"132 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139852614","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：