1
|
Bivona DJ, Ghadimi S, Wang Y, Oomen PJA, Malhotra R, Darby A, Mangrum JM, Mason PK, Mazimba S, Patel AR, Epstein FH, Bilchick KC. Machine learning of ECG waveforms and cardiac magnetic resonance for response and survival after cardiac resynchronization therapy. Comput Biol Med 2024; 178:108627. [PMID: 38850959 DOI: 10.1016/j.compbiomed.2024.108627] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2024] [Revised: 04/22/2024] [Accepted: 05/18/2024] [Indexed: 06/10/2024]
Abstract
Cardiac resynchronization therapy (CRT) can lead to marked symptom reduction and improved survival in selected patients with heart failure with reduced ejection fraction (HFrEF); however, many candidates for CRT based on clinical guidelines do not have a favorable response. A better way to identify patients expected to benefit from CRT that applies machine learning to accessible and cost-effective diagnostic tools such as the 12-lead electrocardiogram (ECG) could have a major impact on clinical care in HFrEF by helping providers personalize treatment strategies and avoid delays in initiation of other potentially beneficial treatments. This study addresses this need by demonstrating that a novel approach to ECG waveform analysis using functional principal component decomposition (FPCD) performs better than measures that require manual ECG analysis with the human eye and also at least as well as a previously validated but more expensive approach based on cardiac magnetic resonance (CMR). Analyses are based on five-fold cross validation of areas under the curve (AUCs) for CRT response and survival time after the CRT implant using Cox proportional hazards regression with stratification of groups using a Gaussian mixture model approach. Furthermore, FPCD and CMR predictors are shown to be independent, which demonstrates that the FPCD electrical findings and the CMR mechanical findings together provide a synergistic model for response and survival after CRT. In summary, this study provides a highly effective approach to prognostication after CRT in HFrEF using an accessible and inexpensive diagnostic test with a major expected impact on personalization of therapies.
Collapse
Affiliation(s)
- Derek J Bivona
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA; Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA
| | - Sona Ghadimi
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA
| | - Yu Wang
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA
| | - Pim J A Oomen
- Department of Biomedical Engineering, University of California Irvine, Irvine, CA 92697, USA
| | - Rohit Malhotra
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - Andrew Darby
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - J Michael Mangrum
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - Pamela K Mason
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - Sula Mazimba
- Advent Health Transplant Institute, AdventHealth, Orlando, FL 32804, USA
| | - Amit R Patel
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA; Department of Radiology and Medical Imaging, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - Frederick H Epstein
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA; Department of Radiology and Medical Imaging, University of Virginia Health System, Charlottesville, VA 22903, USA
| | - Kenneth C Bilchick
- Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA.
| |
Collapse
|
2
|
Manne M, Niebauer M, Tchou P, Varma N. LBBB and heart failure-Relationships among QRS amplitude, duration, height, LV mass, and sex. J Cardiovasc Electrophysiol 2024; 35:583-591. [PMID: 37811553 DOI: 10.1111/jce.16097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 09/26/2023] [Accepted: 09/27/2023] [Indexed: 10/10/2023]
Abstract
BACKGROUND Height, left ventricular (LV) size, and sex were proposed as additional criteria for patient selection for cardiac resynchronization therapy (CRT) but their connections with the QRS complex in left bundle branch block (LBBB) are little investigated. We evaluated these. METHODS Among patients with "true" LBBB, QRS duration (QRSd) and amplitude, and LV hypertrophy indices, were correlated with patient's height and LV mass, and compared between sexes. RESULTS In this study cohort (n = 220; 60 ± 12 years; left ventricular ejection fraction [LVEF] 21 ± 7%; mostly New York Heart Association II-III, QRSd 165 ± 19 ms; 57% female; 70% responders [LVEF increased ≥5%]), LV mass was increased in all patients. QRS amplitude did not correlate with LV mass or height in any individual lead or with Sokolow-Lyon or Cornell-Lyon indices. QRSd did not correlate with height. In contrast, QRSd correlated strongly with LV mass (r = .51). CRT response rate was greater in women versus men (84% vs. 58%, p < .001) despite shorter QRSd [7% shorter (p < .0001)]. QRSd normalized for height resulted in a 2.7% and for LV mass 24% greater index in women. CONCLUSION True LBBB criteria do not exclude HF patients with increased LV mass. QRS amplitudes do not correlate with height or LV mass. Height does not affect QRSd. However, QRSd correlates with LV size. QRSd normalized for LV mass results in 24% greater value in women in the direction of sex-specific responses. LV mass may be a significant nonelectrical modifier of QRSd for CRT.
Collapse
Affiliation(s)
- Mahesh Manne
- Section of Cardiac Pacing and Electrophysiology, Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, Ohio, USA
| | - Mark Niebauer
- Section of Cardiac Pacing and Electrophysiology, Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, Ohio, USA
| | - Patrick Tchou
- Section of Cardiac Pacing and Electrophysiology, Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, Ohio, USA
| | - Niraj Varma
- Section of Cardiac Pacing and Electrophysiology, Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, Ohio, USA
| |
Collapse
|
3
|
Nazar W, Szymanowicz S, Nazar K, Kaufmann D, Wabich E, Braun-Dullaeus R, Daniłowicz-Szymanowicz L. Artificial intelligence models in prediction of response to cardiac resynchronization therapy: a systematic review. Heart Fail Rev 2024; 29:133-150. [PMID: 37861853 PMCID: PMC10904439 DOI: 10.1007/s10741-023-10357-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 09/28/2023] [Indexed: 10/21/2023]
Abstract
The aim of the presented review is to summarize the literature data on the accuracy and clinical applicability of artificial intelligence (AI) models as a valuable alternative to the current guidelines in predicting cardiac resynchronization therapy (CRT) response and phenotyping of patients eligible for CRT implantation. This systematic review was performed according to the PRISMA guidelines. After a search of Scopus, PubMed, Cochrane Library, and Embase databases, 675 records were identified. Twenty supervised (prediction of CRT response) and 9 unsupervised (clustering and phenotyping) AI models were analyzed qualitatively (22 studies, 14,258 patients). Fifty-five percent of AI models were based on retrospective studies. Unsupervised AI models were able to identify clusters of patients with significantly different rates of primary outcome events (death, heart failure event). In comparison to the guideline-based CRT response prediction accuracy of 70%, supervised AI models trained on cohorts with > 100 patients achieved up to 85% accuracy and an AUC of 0.86 in their prediction of response to CRT for echocardiographic and clinical outcomes, respectively. AI models seem to be an accurate and clinically applicable tool in phenotyping of patients eligible for CRT implantation and predicting potential responders. In the future, AI may help to increase CRT response rates to over 80% and improve clinical decision-making and prognosis of the patients, including reduction of mortality rates. However, these findings must be validated in randomized controlled trials.
Collapse
Affiliation(s)
- Wojciech Nazar
- Faculty of Medicine, Medical University of Gdańsk, Marii Skłodowskiej-Curie 3a, 80-210, Gdańsk, Poland
| | | | - Krzysztof Nazar
- Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gabriela Narutowicza 11/12, 80-233, Gdańsk, Poland
| | - Damian Kaufmann
- Department of Cardiology and Electrotherapy, Faculty of Medicine, Medical University of Gdańsk, Smoluchowskiego 17, 80-213, Gdańsk, Poland
| | - Elżbieta Wabich
- Department of Cardiology and Electrotherapy, Faculty of Medicine, Medical University of Gdańsk, Smoluchowskiego 17, 80-213, Gdańsk, Poland
| | - Rüdiger Braun-Dullaeus
- Department of Cardiology and Angiology, Otto von Guericke University Magdeburg, Leipziger Street 44, 39120, Magdeburg, Germany
| | - Ludmiła Daniłowicz-Szymanowicz
- Department of Cardiology and Electrotherapy, Faculty of Medicine, Medical University of Gdańsk, Smoluchowskiego 17, 80-213, Gdańsk, Poland.
| |
Collapse
|
4
|
Simon A, Pilecky D, Kiss LZ, Vamos M. Useful Electrocardiographic Signs to Support the Prediction of Favorable Response to Cardiac Resynchronization Therapy. J Cardiovasc Dev Dis 2023; 10:425. [PMID: 37887872 PMCID: PMC10607456 DOI: 10.3390/jcdd10100425] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Revised: 10/12/2023] [Accepted: 10/12/2023] [Indexed: 10/28/2023] Open
Abstract
Cardiac resynchronization therapy (CRT) is a cornerstone therapeutic opportunity for selected patients with heart failure. For optimal patient selection, no other method has been proven to be more effective than the 12-lead ECG, and hence ECG characteristics are extensively researched. The evaluation of particular ECG signs before the implantation may improve selection and, consequently, clinical outcomes. The definition of a true left bundle branch block (LBBB) seems to be the best starting point with which to select patients for CRT. Although there are no universally accepted definitions of LBBB, using the classical LBBB criteria, some ECG parameters are associated with CRT response. In patients with non-true LBBB or non-LBBB, further ECG predictors of response and non-response could be analyzed, such as QRS fractionation, signs of residual left bundle branch conduction, S-waves in V6, intrinsicoid deflection, or non-invasive estimates of Q-LV which are described in newer publications. The most important and recent study results of the topic are summarized and discussed in this current review.
Collapse
Affiliation(s)
- Andras Simon
- Department of Cardiology, Szent Imre University Teaching Hospital, 1115 Budapest, Hungary;
| | - David Pilecky
- Gottsegen National Cardiovascular Center, 1096 Budapest, Hungary;
- Doctoral School of Clinical Medicine, University of Szeged, 6725 Szeged, Hungary
| | | | - Mate Vamos
- Cardiac Electrophysiology Division, Department of Internal Medicine, University of Szeged, 6725 Szeged, Hungary
| |
Collapse
|
5
|
Sau A, Ng FS. --The emerging role of artificial intelligence enabled electrocardiograms in healthcare. BMJ MEDICINE 2023; 2:e000193. [PMID: 37841970 PMCID: PMC10568120 DOI: 10.1136/bmjmed-2022-000193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/06/2022] [Accepted: 06/01/2023] [Indexed: 10/17/2023]
Affiliation(s)
- Arunashis Sau
- National Heart and Lung Institute, Imperial College London, London, UK
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Fu Siong Ng
- National Heart and Lung Institute, Imperial College London, London, UK
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
- Department of Cardiology, Chelsea and Westminster Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
6
|
Dokuchaev A, Chumarnaya T, Bazhutina A, Khamzin S, Lebedeva V, Lyubimtseva T, Zubarev S, Lebedev D, Solovyova O. Combination of personalized computational modeling and machine learning for optimization of left ventricular pacing site in cardiac resynchronization therapy. Front Physiol 2023; 14:1162520. [PMID: 37497440 PMCID: PMC10367108 DOI: 10.3389/fphys.2023.1162520] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Accepted: 06/26/2023] [Indexed: 07/28/2023] Open
Abstract
Introduction: The 30-50% non-response rate to cardiac resynchronization therapy (CRT) calls for improved patient selection and optimized pacing lead placement. The study aimed to develop a novel technique using patient-specific cardiac models and machine learning (ML) to predict an optimal left ventricular (LV) pacing site (ML-PS) that maximizes the likelihood of LV ejection fraction (LVEF) improvement in a given CRT candidate. To validate the approach, we evaluated whether the distance DPS between the clinical LV pacing site (ref-PS) and ML-PS is associated with improved response rate and magnitude. Materials and methods: We reviewed retrospective data for 57 CRT recipients. A positive response was defined as a more than 10% LVEF improvement. Personalized models of ventricular activation and ECG were created from MRI and CT images. The characteristics of ventricular activation during intrinsic rhythm and biventricular (BiV) pacing with ref-PS were derived from the models and used in combination with clinical data to train supervised ML classifiers. The best logistic regression model classified CRT responders with a high accuracy of 0.77 (ROC AUC = 0.84). The LR classifier, model simulations and Bayesian optimization with Gaussian process regression were combined to identify an optimal ML-PS that maximizes the ML-score of CRT response over the LV surface in each patient. Results: The optimal ML-PS improved the ML-score by 17 ± 14% over the ref-PS. Twenty percent of the non-responders were reclassified as positive at ML-PS. Selection of positive patients with a max ML-score >0.5 demonstrated an improved clinical response rate. The distance DPS was shorter in the responders. The max ML-score and DPS were found to be strong predictors of CRT response (ROC AUC = 0.85). In the group with max ML-score > 0.5 and DPS< 30 mm, the response rate was 83% compared to 14% in the rest of the cohort. LVEF improvement in this group was higher than in the other patients (16 ± 8% vs. 7 ± 8%). Conclusion: A new technique combining clinical data, personalized heart modelling and supervised ML demonstrates the potential for use in clinical practice to assist in optimizing patient selection and predicting optimal LV pacing lead position in HF candidates for CRT.
Collapse
Affiliation(s)
- Arsenii Dokuchaev
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
| | - Tatiana Chumarnaya
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Laboratory of Mathematical Modeling in Physiology and Medicine Based on Supercomputers, Ural Federal University, Ekaterinburg, Russia
| | - Anastasia Bazhutina
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Laboratory of Mathematical Modeling in Physiology and Medicine Based on Supercomputers, Ural Federal University, Ekaterinburg, Russia
| | - Svyatoslav Khamzin
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
| | | | - Tamara Lyubimtseva
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Almazov National Medical Research Centre, Saint Petersburg, Russia
| | - Stepan Zubarev
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Almazov National Medical Research Centre, Saint Petersburg, Russia
| | - Dmitry Lebedev
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Almazov National Medical Research Centre, Saint Petersburg, Russia
| | - Olga Solovyova
- Institute of Immunology and Physiology, Ural Branch of the Russian Academy of Sciences, Ekaterinburg, Russia
- Laboratory of Mathematical Modeling in Physiology and Medicine Based on Supercomputers, Ural Federal University, Ekaterinburg, Russia
| |
Collapse
|
7
|
Wouters PC, van de Leur RR, Vessies MB, van Stipdonk AMW, Ghossein MA, Hassink RJ, Doevendans PA, van der Harst P, Maass AH, Prinzen FW, Vernooy K, Meine M, van Es R. Electrocardiogram-based deep learning improves outcome prediction following cardiac resynchronization therapy. Eur Heart J 2022; 44:680-692. [PMID: 36342291 PMCID: PMC9940988 DOI: 10.1093/eurheartj/ehac617] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/23/2022] [Revised: 09/23/2022] [Accepted: 10/13/2022] [Indexed: 11/09/2022] Open
Abstract
AIMS This study aims to identify and visualize electrocardiogram (ECG) features using an explainable deep learning-based algorithm to predict cardiac resynchronization therapy (CRT) outcome. Its performance is compared with current guideline ECG criteria and QRSAREA. METHODS AND RESULTS A deep learning algorithm, trained on 1.1 million ECGs from 251 473 patients, was used to compress the median beat ECG, thereby summarizing most ECG features into only 21 explainable factors (FactorECG). Pre-implantation ECGs of 1306 CRT patients from three academic centres were converted into their respective FactorECG. FactorECG predicted the combined clinical endpoint of death, left ventricular assist device, or heart transplantation [c-statistic 0.69, 95% confidence interval (CI) 0.66-0.72], significantly outperforming QRSAREA and guideline ECG criteria [c-statistic 0.61 (95% CI 0.58-0.64) and 0.57 (95% CI 0.54-0.60), P < 0.001 for both]. The addition of 13 clinical variables was of limited added value for the FactorECG model when compared with QRSAREA (Δ c-statistic 0.03 vs. 0.10). FactorECG identified inferolateral T-wave inversion, smaller right precordial S- and T-wave amplitude, ventricular rate, and increased PR interval and P-wave duration to be important predictors for poor outcome. An online visualization tool was created to provide interactive visualizations (https://crt.ecgx.ai). CONCLUSION Requiring only a standard 12-lead ECG, FactorECG held superior discriminative ability for the prediction of clinical outcome when compared with guideline criteria and QRSAREA, without requiring additional clinical variables. End-to-end automated visualization of ECG features allows for an explainable algorithm, which may facilitate rapid uptake of this personalized decision-making tool in CRT.
Collapse
Affiliation(s)
| | | | - Melle B Vessies
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
| | - Antonius M W van Stipdonk
- Department of Cardiology, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University Medical Centre (MUMC+), Maastricht, The Netherlands
| | - Mohammed A Ghossein
- Department of Physiology, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, The Netherlands
| | - Rutger J Hassink
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
| | - Pieter A Doevendans
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands,Netherlands Heart Institute, Utrecht, The Netherlands
| | - Pim van der Harst
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
| | - Alexander H Maass
- Department of Cardiology, Thoraxcentre, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Frits W Prinzen
- Department of Physiology, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, The Netherlands
| | - Kevin Vernooy
- Department of Cardiology, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University Medical Centre (MUMC+), Maastricht, The Netherlands
| | - Mathias Meine
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
| | - René van Es
- Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
| |
Collapse
|
8
|
Siva Kumar S, Al-Kindi S, Tashtish N, Rajagopalan V, Fu P, Rajagopalan S, Madabhushi A. Machine learning derived ECG risk score improves cardiovascular risk assessment in conjunction with coronary artery calcium scoring. Front Cardiovasc Med 2022; 9:976769. [PMID: 36277775 PMCID: PMC9580025 DOI: 10.3389/fcvm.2022.976769] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Accepted: 09/05/2022] [Indexed: 11/13/2022] Open
Abstract
Background Precision estimation of cardiovascular risk remains the cornerstone of atherosclerotic cardiovascular disease (ASCVD) prevention. While coronary artery calcium (CAC) scoring is the best available non-invasive quantitative modality to evaluate risk of ASCVD, it excludes risk related to prior myocardial infarction, cardiomyopathy, and arrhythmia which are implicated in ASCVD. The high-dimensional and inter-correlated nature of ECG data makes it a good candidate for analysis using machine learning techniques and may provide additional prognostic information not captured by CAC. In this study, we aimed to develop a quantitative ECG risk score (eRiS) to predict major adverse cardiovascular events (MACE) alone, or when added to CAC. Further, we aimed to construct and validate a novel nomogram incorporating ECG, CAC and clinical factors for ASCVD. Methods We analyzed 5,864 patients with at least 1 cardiovascular risk factor who underwent CAC scoring and a standard ECG as part of the CLARIFY study (ClinicalTrials.gov Identifier: NCT04075162). Events were defined as myocardial infarction, coronary revascularization, stroke or death. A total of 649 ECG features, consisting of measurements such as amplitude and interval measurements from all deflections in the ECG waveform (53 per lead and 13 overall) were automatically extracted using a clinical software (GE Muse™ Cardiology Information System, GE Healthcare). The data was split into 4 training (Str) and internal validation (Sv) sets [Str (1): Sv (1): 50:50; Str (2): Sv (2): 60:40; Str (3): Sv (3): 70:30; Str (4): Sv (4): 80:20], and the results were compared across all the subsets. We used the ECG features derived from Str to develop eRiS. A least absolute shrinkage and selection operator-Cox (LASSO-Cox) regularization model was used for data dimension reduction, feature selection, and eRiS construction. A Cox-proportional hazards model was used to assess the benefit of using an eRiS alone (Mecg), CAC alone (Mcac) and a combination of eRiS and CAC (Mecg+cac) for MACE prediction. A nomogram (Mnom) was further constructed by integrating eRiS with CAC and demographics (age and sex). The primary endpoint of the study was the assessment of the performance of Mecg, Mcac, Mecg+cac and Mnom in predicting CV disease-free survival in ASCVD. Findings Over a median follow-up of 14 months, 494 patients had MACE. The feature selection strategy preserved only about 18% of the features that were consistent across the various strata (Str). The Mecg model, comprising of eRiS alone was found to be significantly associated with MACE and had good discrimination of MACE (C-Index: 0.7, p = <2e-16). eRiS could predict time-to MACE (C-Index: 0.6, p = <2e-16 across all Sv). The Mecg+cac model was associated with MACE (C-index: 0.71). Model comparison showed that Mecg+cac was superior to Mecg (p = 1.8e-10) or Mcac (p < 2.2e-16) alone. The Mnom, comprising of eRiS, CAC, age and sex was associated with MACE (C-index 0.71). eRiS had the most significant contribution, followed by CAC score and other clinical variables. Further, Mnom was able to identify unique patient risk-groups based on eRiS, CAC and clinical variables. Conclusion The use of ECG features in conjunction with CAC may allow for improved prognostication and identification of populations at risk. Future directions will involve prospective validation of the risk score and the nomogram across diverse populations with a heterogeneity of treatment effects.
Collapse
Affiliation(s)
- Shruti Siva Kumar
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States,*Correspondence: Shruti Siva Kumar
| | - Sadeer Al-Kindi
- Harrington Heart and Vascular Institute, University Hospitals, Cleveland, OH, United States,School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Nour Tashtish
- Harrington Heart and Vascular Institute, University Hospitals, Cleveland, OH, United States,School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Varun Rajagopalan
- Harrington Heart and Vascular Institute, University Hospitals, Cleveland, OH, United States,School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Pingfu Fu
- Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH, United States
| | - Sanjay Rajagopalan
- Harrington Heart and Vascular Institute, University Hospitals, Cleveland, OH, United States,School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Anant Madabhushi
- Wallace H. Coulter Department of Biomedical Engineering, Radiology and Imaging Sciences, Biomedical Informatics (BMI) and Pathology, Georgia Institute of Technology and Emory University, Research Health Scientist, Atlanta Veterans Administration Medical Center, Atlanta, GA, United States
| |
Collapse
|
9
|
Kong NW, Upadhyay GA. Cardiac resynchronization considerations in left bundle branch block. Front Physiol 2022; 13:962042. [PMID: 36187776 PMCID: PMC9520457 DOI: 10.3389/fphys.2022.962042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2022] [Accepted: 08/30/2022] [Indexed: 11/18/2022] Open
Abstract
Cardiac resynchronization therapy (CRT) via biventricular pacing (BiVP) is an established treatment for patients with left ventricular systolic heart failure and intraventricular conduction delay resulting in wide QRS. Seminal trials demonstrating mortality benefit from CRT were conducted in patients with wide left bundle branch block (LBBB) pattern on electrocardiogram (ECG) and evidence of clinical heart failure. The presence of conduction block was assumed to correlate with commonly applied criteria for LBBB. More recent data has challenged this assertion, revealing that LBBB pattern may include distinct underlying pathophysiology, including patients with complete conduction block, either at the left-sided His fibers or the proximal left bundle, intact Purkinje activation with wide LBBB-like QRS, and patients demonstrating both proximal block and distal delay. Currently, BiVP-CRT is indicated for all QRS duration ≥150 ms and may be considered for BBB patterns from 130 to 149 ms with robust clinical data to support its use. Despite this, however, there remains a significant number of non-responders to BVP. Conduction system pacing (CSP) has emerged as an alternative approach to deliver CRT and correct QRS in patients with conduction block. Newer hybrid approaches which combine CSP and traditional BiVP-CRT and may hold promise for patients with IP or mixed-level block. As various approaches to CRT continue to be studied, physiologic phenotyping of the LBBB pattern remains an important consideration.
Collapse
Affiliation(s)
- Nathan W. Kong
- Department of Internal Medicine, University of Chicago Medicine, Chicago, IL, United States
| | - Gaurav A. Upadhyay
- Section of Cardiology, Center for Arrhythmia Care, University of Chicago Medicine, Chicago, IL, United States
- *Correspondence: Gaurav A. Upadhyay,
| |
Collapse
|
10
|
Gautam N, Ghanta SN, Clausen A, Saluja P, Sivakumar K, Dhar G, Chang Q, DeMazumder D, Rabbat MG, Greene SJ, Fudim M, Al'Aref SJ. Contemporary Applications of Machine Learning for Device Therapy in Heart Failure. JACC. HEART FAILURE 2022; 10:603-622. [PMID: 36049812 DOI: 10.1016/j.jchf.2022.06.011] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 05/31/2022] [Accepted: 06/16/2022] [Indexed: 06/15/2023]
Abstract
Despite a better understanding of the underlying pathogenesis of heart failure (HF), pharmacotherapy, surgical, and percutaneous interventions do not prevent disease progression in all patients, and a significant proportion of patients end up requiring advanced therapies. Machine learning (ML) is gaining wider acceptance in cardiovascular medicine because of its ability to incorporate large, complex, and multidimensional data and to potentially facilitate the creation of predictive models not constrained by many of the limitations of traditional statistical approaches. With the coexistence of "big data" and novel advanced analytic techniques using ML, there is ever-increasing research into applying ML in the context of HF with the goal of improving patient outcomes. Through this review, the authors describe the basics of ML and summarize the existing published reports regarding contemporary applications of ML in device therapy for HF while highlighting the limitations to widespread implementation and its future promises.
Collapse
Affiliation(s)
- Nitesh Gautam
- Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Sai Nikhila Ghanta
- Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Alex Clausen
- Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Prachi Saluja
- Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Kalai Sivakumar
- Division of Cardiology, Department of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Gaurav Dhar
- Division of Cardiology, Department of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Qi Chang
- Department of Computer Science, Rutgers University, The State University of New Jersey, Newark, New Jersey, USA
| | | | - Mark G Rabbat
- Department of Cardiology, Loyola University Medical Center, Maywood, Illinois, USA
| | - Stephen J Greene
- Department of Cardiology, Duke University Medical Center, Durham, North Carolina, USA; Duke Clinical Research Institute, Durham, North Carolina, USA
| | - Marat Fudim
- Department of Cardiology, Duke University Medical Center, Durham, North Carolina, USA; Duke Clinical Research Institute, Durham, North Carolina, USA
| | - Subhi J Al'Aref
- Division of Cardiology, Department of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA.
| |
Collapse
|
11
|
Park JW, Kwon OS, Shim J, Hwang I, Kim YG, Yu HT, Kim TH, Uhm JS, Kim JY, Choi JI, Joung B, Lee MH, Kim YH, Pak HN. Machine Learning-Predicted Progression to Permanent Atrial Fibrillation After Catheter Ablation. Front Cardiovasc Med 2022; 9:813914. [PMID: 35252393 PMCID: PMC8890475 DOI: 10.3389/fcvm.2022.813914] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2021] [Accepted: 01/25/2022] [Indexed: 11/13/2022] Open
Abstract
Introduction We developed a prediction model for atrial fibrillation (AF) progression and tested whether machine learning (ML) could reproduce the prediction power in an independent cohort using pre-procedural non-invasive variables alone. Methods Cohort 1 included 1,214 patients and cohort 2, 658, and all underwent AF catheter ablation (AFCA). AF progression to permanent AF was defined as sustained AF despite repeat AFCA or cardioversion under antiarrhythmic drugs. We developed a risk stratification model for AF progression (STAAR score) and stratified cohort 1 into three groups. We also developed an ML-prediction model to classify three STAAR risk groups without invasive parameters and validated the risk score in cohort 2. Results The STAAR score consisted of a stroke (2 points, p = 0.003), persistent AF (1 point, p = 0.049), left atrial (LA) dimension ≥43 mm (1 point, p = 0.010), LA voltage <1.109 mV (2 points, p = 0.004), and PR interval ≥196 ms (1 point, p = 0.001), based on multivariate Cox analyses, and it had a good discriminative power for progression to permanent AF [area under curve (AUC) 0.796, 95% confidence interval (CI): 0.753–0.838]. The ML prediction model calculated the risk for AF progression without invasive variables and achieved excellent risk stratification: AUC 0.935 for low-risk groups (score = 0), AUC 0.855 for intermediate-risk groups (score 1–3), and AUC 0.965 for high-risk groups (score ≥ 4) in cohort 1. The ML model successfully predicted the high-risk group for AF progression in cohort 2 (log-rank p < 0.001). Conclusions The ML-prediction model successfully classified the high-risk patients who will progress to permanent AF after AFCA without invasive variables but has a limited discrimination power for the intermediate-risk group.
Collapse
Affiliation(s)
- Je-Wook Park
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Oh-Seok Kwon
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jaemin Shim
- Department of Internal Medicine, Korea University Cardiovascular Center, Seoul, South Korea
- *Correspondence: Jaemin Shim
| | - Inseok Hwang
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Yun Gi Kim
- Department of Internal Medicine, Korea University Cardiovascular Center, Seoul, South Korea
| | - Hee Tae Yu
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Tae-Hoon Kim
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jae-Sun Uhm
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jong-Youn Kim
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jong Il Choi
- Department of Internal Medicine, Korea University Cardiovascular Center, Seoul, South Korea
| | - Boyoung Joung
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Moon-Hyoung Lee
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Young-Hoon Kim
- Department of Internal Medicine, Korea University Cardiovascular Center, Seoul, South Korea
| | - Hui-Nam Pak
- Division of Cardiology, Yonsei University Health System, Seoul, South Korea
- Hui-Nam Pak
| |
Collapse
|
12
|
Khamzin S, Dokuchaev A, Bazhutina A, Chumarnaya T, Zubarev S, Lyubimtseva T, Lebedeva V, Lebedev D, Gurev V, Solovyova O. Machine Learning Prediction of Cardiac Resynchronisation Therapy Response From Combination of Clinical and Model-Driven Data. Front Physiol 2022; 12:753282. [PMID: 34970154 PMCID: PMC8712879 DOI: 10.3389/fphys.2021.753282] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2021] [Accepted: 11/22/2021] [Indexed: 11/17/2022] Open
Abstract
Background: Up to 30–50% of chronic heart failure patients who underwent cardiac resynchronization therapy (CRT) do not respond to the treatment. Therefore, patient stratification for CRT and optimization of CRT device settings remain a challenge. Objective: The main goal of our study is to develop a predictive model of CRT outcome using a combination of clinical data recorded in patients before CRT and simulations of the response to biventricular (BiV) pacing in personalized computational models of the cardiac electrophysiology. Materials and Methods: Retrospective data from 57 patients who underwent CRT device implantation was utilized. Positive response to CRT was defined by a 10% increase in the left ventricular ejection fraction in a year after implantation. For each patient, an anatomical model of the heart and torso was reconstructed from MRI and CT images and tailored to ECG recorded in the participant. The models were used to compute ventricular activation time, ECG duration and electrical dyssynchrony indices during intrinsic rhythm and BiV pacing from the sites of implanted leads. For building a predictive model of CRT response, we used clinical data recorded before CRT device implantation together with model-derived biomarkers of ventricular excitation in the left bundle branch block mode of activation and under BiV stimulation. Several Machine Learning (ML) classifiers and feature selection algorithms were tested on the hybrid dataset, and the quality of predictors was assessed using the area under receiver operating curve (ROC AUC). The classifiers on the hybrid data were compared with ML models built on clinical data only. Results: The best ML classifier utilizing a hybrid set of clinical and model-driven data demonstrated ROC AUC of 0.82, an accuracy of 0.82, sensitivity of 0.85, and specificity of 0.78, improving quality over that of ML predictors built on clinical data from much larger datasets by more than 0.1. Distance from the LV pacing site to the post-infarction zone and ventricular activation characteristics under BiV pacing were shown as the most relevant model-driven features for CRT response classification. Conclusion: Our results suggest that combination of clinical and model-driven data increases the accuracy of classification models for CRT outcomes.
Collapse
Affiliation(s)
- Svyatoslav Khamzin
- Institute of Immunology and Physiology Ural Branch of the Russian Academy of Sciences, Yekaterinburg, Russia
| | - Arsenii Dokuchaev
- Institute of Immunology and Physiology Ural Branch of the Russian Academy of Sciences, Yekaterinburg, Russia
| | - Anastasia Bazhutina
- Institute of Immunology and Physiology Ural Branch of the Russian Academy of Sciences, Yekaterinburg, Russia.,Ural Federal University, Yekaterinburg, Russia
| | - Tatiana Chumarnaya
- Institute of Immunology and Physiology Ural Branch of the Russian Academy of Sciences, Yekaterinburg, Russia
| | - Stepan Zubarev
- Almazov National Medical Research Centre, Saint Petersburg, Russia
| | | | | | - Dmitry Lebedev
- Almazov National Medical Research Centre, Saint Petersburg, Russia
| | | | - Olga Solovyova
- Institute of Immunology and Physiology Ural Branch of the Russian Academy of Sciences, Yekaterinburg, Russia.,Ural Federal University, Yekaterinburg, Russia
| |
Collapse
|
13
|
Patient Selection for Biventricular Cardiac Resynchronization Therapy, His Bundle Pacing, and Left Bundle Branch Pacing. CURRENT CARDIOVASCULAR RISK REPORTS 2021. [DOI: 10.1007/s12170-021-00684-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
14
|
Vaid A, Johnson KW, Badgeley MA, Somani SS, Bicak M, Landi I, Russak A, Zhao S, Levin MA, Freeman RS, Charney AW, Kukar A, Kim B, Danilov T, Lerakis S, Argulian E, Narula J, Nadkarni GN, Glicksberg BS. Using Deep-Learning Algorithms to Simultaneously Identify Right and Left Ventricular Dysfunction From the Electrocardiogram. JACC Cardiovasc Imaging 2021; 15:395-410. [PMID: 34656465 PMCID: PMC8917975 DOI: 10.1016/j.jcmg.2021.08.004] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/01/2021] [Revised: 07/29/2021] [Accepted: 08/05/2021] [Indexed: 12/20/2022]
Abstract
OBJECTIVES This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population. BACKGROUND Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right- ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only. METHODS A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation. RESULTS We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% < LVEF ≤50%, and LVEF >50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation. CONCLUSIONS DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.
Collapse
Affiliation(s)
- Akhil Vaid
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Kipp W Johnson
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | | | - Sulaiman S Somani
- The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Mesude Bicak
- The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Isotta Landi
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Adam Russak
- Department of Anesthesiology, Perioperative and Pain Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Shan Zhao
- The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Matthew A Levin
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Robert S Freeman
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Pamela Sklar Division of Psychiatric Genomics, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Alexander W Charney
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Atul Kukar
- Department of Cardiology, Mount Sinai Queens Hospital, Astoria, New York, USA, and Icahn School of Medicine at Mount Sinai, New York, New York, USA; Division of Cardiology, Mount Sinai West Hospital and Icahn School of Medicine at Mount Sinai, New York, New York USA
| | - Bette Kim
- Mount Sinai Beth Israel Hospital, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Tatyana Danilov
- Department of Cardiology, Mount Sinai Morningside Hospital, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Stamatios Lerakis
- The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Edgar Argulian
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Jagat Narula
- The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Girish N Nadkarni
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Benjamin S Glicksberg
- Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
| |
Collapse
|
15
|
Cheng X, Manandhar I, Aryal S, Joe B. Application of Artificial Intelligence in Cardiovascular Medicine. Compr Physiol 2021; 11:2455-2466. [PMID: 34558666 DOI: 10.1002/cphy.c200034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
The advent of advances in machine learning (ML)-based techniques has popularized wide applications of artificial intelligence (AI) in various fields ranging from robotics to medicine. In recent years, there has been a surge in the application of AI to research in cardiovascular medicine, which is largely driven by the availability of large-scale clinical and multi-omics datasets. Such applications are providing a new perspective for a better understanding of cardiovascular disease (CVD), which could be used to develop novel diagnostic and therapeutic strategies. For example, studies have shown that ML has a substantial potential for early diagnosis of different types of CVD, prediction of adverse disease outcomes such as heart failure, and development of newer and personalized treatments. In this article, we provide an overview and discuss the current status of a wide range of AI applications, including machine learning, reinforcement learning, and deep learning, in cardiovascular medicine. © 2021 American Physiological Society. Compr Physiol 11:1-12, 2021.
Collapse
Affiliation(s)
- Xi Cheng
- Bioinformatics & Artificial Intelligence Laboratory, Center for Hypertension and Precision Medicine, Program in Physiological Genomics, Department of Physiology and Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, Ohio, USA
| | - Ishan Manandhar
- Bioinformatics & Artificial Intelligence Laboratory, Center for Hypertension and Precision Medicine, Program in Physiological Genomics, Department of Physiology and Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, Ohio, USA
| | - Sachin Aryal
- Bioinformatics & Artificial Intelligence Laboratory, Center for Hypertension and Precision Medicine, Program in Physiological Genomics, Department of Physiology and Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, Ohio, USA
| | - Bina Joe
- Bioinformatics & Artificial Intelligence Laboratory, Center for Hypertension and Precision Medicine, Program in Physiological Genomics, Department of Physiology and Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, Ohio, USA
| |
Collapse
|
16
|
Abstract
Arrhythmia management has been revolutionized by the ability to monitor the cardiac rhythm in a patient's home environment in real-time using high-fidelity prescription-grade and commercially available wearable electrodes. The vast amount of digitally acquired electrophysiological signals has generated the need for scalable and efficient data processing with actionable output that can be provided directly to clinicians and patients. In this setting, artificial intelligence applications are increasingly important in arrhythmia monitoring, ranging from conventional algorithmic analysis for rhythm determination to more complex deep machine learning methods that have led to the realization of fully automated humanlike rhythm determination in real-time.
Collapse
Affiliation(s)
- Konstantinos C Siontis
- Department of Cardiovascular Medicine, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA
| | - Paul A Friedman
- Department of Cardiovascular Medicine, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA.
| |
Collapse
|
17
|
The Role of Artificial Intelligence and Machine Learning in Clinical Cardiac Electrophysiology. Can J Cardiol 2021; 38:246-258. [PMID: 34333029 DOI: 10.1016/j.cjca.2021.07.016] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2021] [Revised: 07/11/2021] [Accepted: 07/25/2021] [Indexed: 11/21/2022] Open
Abstract
In recent years, artificial intelligence (AI) has found numerous applications in cardiology due in part to large digitized datasets and the evolution of high performance computing. In the discipline of cardiac electrophysiology (EP), a number of clinical, imaging, and electrical waveform data are considered in the diagnosis, prognostication and management of arrhythmias, which lend themselves well to automation through AI. But equally relevant, AI offers a unique opportunity to discover novel EP concepts and improve clinical care through its inherent, hierarchical tenets of self-learning. This review will focus on the application of AI in clinical EP and summarize state-of-the art, large, clinical studies in the following key domains: (1) ECG-based arrhythmia and disease classification, (2) atrial fibrillation source detection, (3) substrate and risk assessment for atrial fibrillation and ventricular tachyarrhythmias, and (4) predicting outcomes after cardiac resynchronization therapy. Many are small, single-center, proof-of-concept investigations, but they still demonstrate groundbreaking performance of deep learning, a subdomain of AI, which surpasses traditional statistical analysis. Larger studies, for instance classifying arrhythmias from ECG recordings, have further provided external validation of their high accuracy. Ultimately, the performance of AI is dependent on the quality of the input data and the rigor of algorithm development. The field is still nascent and several barriers will need to be overcome, including prospective validation in large, well-labelled datasets and more seamless information technology-based data collection/integration, before AI can be adopted into broader clinical EP practice. This review will conclude with a discussion of these challenges and future work.
Collapse
|
18
|
Lee JH, Kwon OS, Shim J, Lee J, Han HJ, Yu HT, Kim TH, Uhm JS, Joung B, Lee MH, Kim YH, Pak HN. Left Atrial Wall Stress and the Long-Term Outcome of Catheter Ablation of Atrial Fibrillation: An Artificial Intelligence-Based Prediction of Atrial Wall Stress. Front Physiol 2021; 12:686507. [PMID: 34276406 PMCID: PMC8285096 DOI: 10.3389/fphys.2021.686507] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2021] [Accepted: 05/11/2021] [Indexed: 12/19/2022] Open
Abstract
Atrial stretch may contribute to the mechanism of atrial fibrillation (AF) recurrence after atrial fibrillation catheter ablation (AFCA). We tested whether the left atrial (LA) wall stress (LAW-stress[measured]) could be predicted by artificial intelligence (AI) using non-invasive parameters (LAW-stress[AI]) and whether rhythm outcome after AFCA could be predicted by LAW-stress[AI] in an independent cohort. Cohort 1 included 2223 patients, and cohort 2 included 658 patients who underwent AFCA. LAW-stress[measured] was calculated using the Law of Laplace using LA diameter by echocardiography, peak LA pressure measured during procedure, and LA wall thickness measured by customized software (AMBER) using computed tomography. The highest quartile (Q4) LAW-stress[measured] was predicted and validated by AI using non-invasive clinical parameters, including non-paroxysmal type of AF, age, presence of hypertension, diabetes, vascular disease, and heart failure, left ventricular ejection fraction, and the ratio of the peak mitral flow velocity of the early rapid filling to the early diastolic velocity of the mitral annulus (E/Em). We tested the AF/atrial tachycardia recurrence 3 months after the blanking period after AFCA using the LAW-stress[measured] and LAW-stress[AI] in cohort 1 and LAW-stress[AI] in cohort 2. LAW-stress[measured] was independently associated with non-paroxysmal AF (p < 0.001), diabetes (p = 0.012), vascular disease (p = 0.002), body mass index (p < 0.001), E/Em (p < 0.001), and mean LA voltage measured by electrogram voltage mapping (p < 0.001). The best-performing AI model had acceptable prediction power for predicting Q4-LAW-stress[measured] (area under the receiver operating characteristic curve 0.734). During 26.0 (12.0–52.0) months of follow-up, AF recurrence was significantly higher in the Q4-LAW-stress[measured] group [log-rank p = 0.001, hazard ratio 2.43 (1.21–4.90), p = 0.013] and Q4-LAW-stress[AI] group (log-rank p = 0.039) in cohort 1. In cohort 2, the Q4-LAW-stress[AI] group consistently showed worse rhythm outcomes (log-rank p < 0.001). A higher LAW-stress was associated with poorer rhythm outcomes after AFCA. AI was able to predict this complex but useful prognostic parameter using non-invasive parameters with moderate accuracy.
Collapse
Affiliation(s)
- Jae-Hyuk Lee
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Oh-Seok Kwon
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jaemin Shim
- Department of Cardiology, Korea University Cardiovascular Center, Seoul, South Korea
| | - Jisu Lee
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Hee-Jin Han
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Hee Tae Yu
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Tae-Hoon Kim
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Jae-Sun Uhm
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Boyoung Joung
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Moon-Hyoung Lee
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| | - Young-Hoon Kim
- Department of Cardiology, Korea University Cardiovascular Center, Seoul, South Korea
| | - Hui-Nam Pak
- Department of Cardiology, Yonsei University Health System, Seoul, South Korea
| |
Collapse
|
19
|
Marcondes-Braga FG, Moura LAZ, Issa VS, Vieira JL, Rohde LE, Simões MV, Fernandes-Silva MM, Rassi S, Alves SMM, de Albuquerque DC, de Almeida DR, Bocchi EA, Ramires FJA, Bacal F, Rossi JM, Danzmann LC, Montera MW, de Oliveira MT, Clausell N, Silvestre OM, Bestetti RB, Bernadez-Pereira S, Freitas AF, Biolo A, Barretto ACP, Jorge AJL, Biselli B, Montenegro CEL, dos Santos EG, Figueiredo EL, Fernandes F, Silveira FS, Atik FA, Brito FDS, Souza GEC, Ribeiro GCDA, Villacorta H, de Souza JD, Goldraich LA, Beck-da-Silva L, Canesin MF, Bittencourt MI, Bonatto MG, Moreira MDCV, Avila MS, Coelho OR, Schwartzmann PV, Mourilhe-Rocha R, Mangini S, Ferreira SMA, de Figueiredo JA, Mesquita ET. Emerging Topics Update of the Brazilian Heart Failure Guideline - 2021. Arq Bras Cardiol 2021; 116:1174-1212. [PMID: 34133608 PMCID: PMC8288520 DOI: 10.36660/abc.20210367] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022] Open
Affiliation(s)
- Fabiana G. Marcondes-Braga
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Lídia Ana Zytynski Moura
- Pontifícia Universidade Católica de CuritibaCuritibaPRBrasilPontifícia Universidade Católica de Curitiba, Curitiba, PR – Brasil.
| | - Victor Sarli Issa
- Universidade da AntuérpiaBélgicaUniversidade da Antuérpia, – Bélgica
| | - Jefferson Luis Vieira
- Hospital do Coração de MessejanaFortalezaCEBrasilHospital do Coração de Messejana Dr. Carlos Alberto Studart Gomes, Fortaleza, CE – Brasil.
| | - Luis Eduardo Rohde
- Hospital de Clínicas de Porto AlegrePorto AlegeRSBrasilHospital de Clínicas de Porto Alegre, Porto Alege, RS – Brasil.
- Hospital Moinhos de VentoPorto AlegreRSBrasilHospital Moinhos de Vento, Porto Alegre, RS – Brasil.
- Universidade Federal do Rio Grande do SulPorto AlegreRSBrasilUniversidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS – Brasil.
| | - Marcus Vinícius Simões
- Universidade de São PauloFaculdade de Medicina de Ribeirão PretoSão PauloSPBrasilFaculdade de Medicina de Ribeirão Preto da Universidade de São Paulo, São Paulo, SP – Brasil.
| | - Miguel Morita Fernandes-Silva
- Universidade Federal do ParanáCuritibaPRBrasilUniversidade Federal do Paraná (UFPR), Curitiba, PR – Brasil.
- Quanta Diagnóstico por ImagemCuritibaPRBrasilQuanta Diagnóstico por Imagem, Curitiba, PR – Brasil.
| | - Salvador Rassi
- Universidade Federal de GoiásHospital das ClínicasGoiâniaGOBrasilHospital das Clínicas da Universidade Federal de Goiás (UFGO), Goiânia, GO – Brasil.
| | - Silvia Marinho Martins Alves
- Pronto Socorro Cardiológico de PernambucoRecifePEBrasilPronto Socorro Cardiológico de Pernambuco (PROCAPE), Recife, PE – Brasil.
- Universidade de PernambucoRecifePEBrasilUniversidade de Pernambuco (UPE), Recife, PE – Brasil.
| | - Denilson Campos de Albuquerque
- Universidade do Estado do Rio de JaneiroRio de JaneiroRJBrasilUniversidade do Estado do Rio de Janeiro (UERJ), Rio de Janeiro, RJ – Brasil.
| | - Dirceu Rodrigues de Almeida
- Universidade Federal de São PauloSão PauloSPBrasilUniversidade Federal de São Paulo (UNIFESP), São Paulo, SP – Brasil.
| | - Edimar Alcides Bocchi
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Felix José Alvarez Ramires
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
- Hospital Israelita Albert EinsteinSão PauloSPBrasilHospital Israelita Albert Einstein, São Paulo, SP – Brasil.
| | - Fernando Bacal
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - João Manoel Rossi
- Instituto Dante Pazzanese de CardiologiaSão PauloSPBrasilInstituto Dante Pazzanese de Cardiologia, São Paulo, SP – Brasil.
| | - Luiz Claudio Danzmann
- Universidade Luterana do BrasilCanoasRSBrasilUniversidade Luterana do Brasil, Canoas, RS – Brasil.
- Hospital São Lucas da PUC-RSPorto AlegreRSBrasilHospital São Lucas da PUC-RS, Porto Alegre, RS – Brasil.
| | | | - Mucio Tavares de Oliveira
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Nadine Clausell
- Hospital de Clínicas de Porto AlegrePorto AlegeRSBrasilHospital de Clínicas de Porto Alegre, Porto Alege, RS – Brasil.
| | - Odilson Marcos Silvestre
- Universidade Federal do AcreRio BrancoACBrasilUniversidade Federal do Acre, Rio Branco, AC – Brasil.
| | - Reinaldo Bulgarelli Bestetti
- Universidade de Ribeirão PretoDepartamento de MedicinaRibeirão PretoSPBrasilDepartamento de Medicina da Universidade de Ribeirão Preto (UNAERP), Ribeirão Preto, SP – Brasil.
| | | | - Aguinaldo F. Freitas
- Universidade Federal de GoiásHospital das ClínicasGoiâniaGOBrasilHospital das Clínicas da Universidade Federal de Goiás (UFGO), Goiânia, GO – Brasil.
| | - Andréia Biolo
- Hospital de Clínicas de Porto AlegrePorto AlegeRSBrasilHospital de Clínicas de Porto Alegre, Porto Alege, RS – Brasil.
| | - Antonio Carlos Pereira Barretto
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Antônio José Lagoeiro Jorge
- Universidade Federal FluminenseFaculdade de MedicinaNiteróiRJBrasilFaculdade de Medicina da Universidade Federal Fluminense (UFF), Niterói, RJ – Brasil.
| | - Bruno Biselli
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Carlos Eduardo Lucena Montenegro
- Pronto Socorro Cardiológico de PernambucoRecifePEBrasilPronto Socorro Cardiológico de Pernambuco (PROCAPE), Recife, PE – Brasil.
- Universidade de PernambucoRecifePEBrasilUniversidade de Pernambuco (UPE), Recife, PE – Brasil.
| | - Edval Gomes dos Santos
- Universidade Estadual de Feira de SantanaFeira de SantanaBABrasilUniversidade Estadual de Feira de Santana, Feira de Santana, BA – Brasil.
- Santa Casa de Misericórdia de Feira de SantanaFeira de SantanaBABrasilSanta Casa de Misericórdia de Feira de Santana, Feira de Santana, BA – Brasil.
| | - Estêvão Lanna Figueiredo
- Instituto OrizontiBelo HorizonteMGBrasilInstituto Orizonti, Belo Horizonte, MG – Brasil.
- Hospital Vera CruzBelo HorizonteMGBrasilHospital Vera Cruz, Belo Horizonte, MG – Brasil.
| | - Fábio Fernandes
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Fabio Serra Silveira
- Fundação Beneficência Hospital de CirurgiaAracajuSEBrasilFundação Beneficência Hospital de Cirurgia (FBHC-Ebserh), Aracaju, SE – Brasil.
- Centro de Pesquisa Clínica do CoraçãoAracajuSEBrasilCentro de Pesquisa Clínica do Coração, Aracaju, SE – Brasil.
| | - Fernando Antibas Atik
- Universidade de BrasíliaBrasíliaDFBrasilUniversidade de Brasília (UnB), Brasília, DF – Brasil.
| | - Flávio de Souza Brito
- Universidade Estadual Paulista Júlio de Mesquita FilhoSão PauloSPBrasilUniversidade Estadual Paulista Júlio de Mesquita Filho (UNESP), São Paulo, SP – Brasil.
| | - Germano Emílio Conceição Souza
- Hospital Alemão Oswaldo CruzSão PauloSPBrasilHospital Alemão Oswaldo Cruz, São Paulo, SP – Brasil.
- Hospital Regional de São José dos CamposSão PauloSPBrasilHospital Regional de São José dos Campos, São Paulo, SP – Brasil.
| | - Gustavo Calado de Aguiar Ribeiro
- Pontifícia Universidade Católica de CampinasCampinasSPBrasilPontifícia Universidade Católica de Campinas (PUCC), Campinas, SP – Brasil.
| | - Humberto Villacorta
- Universidade Federal FluminenseFaculdade de MedicinaNiteróiRJBrasilFaculdade de Medicina da Universidade Federal Fluminense (UFF), Niterói, RJ – Brasil.
| | - João David de Souza
- Hospital do Coração de MessejanaFortalezaCEBrasilHospital do Coração de Messejana Dr. Carlos Alberto Studart Gomes, Fortaleza, CE – Brasil.
| | - Livia Adams Goldraich
- Hospital de Clínicas de Porto AlegrePorto AlegeRSBrasilHospital de Clínicas de Porto Alegre, Porto Alege, RS – Brasil.
| | - Luís Beck-da-Silva
- Hospital de Clínicas de Porto AlegrePorto AlegeRSBrasilHospital de Clínicas de Porto Alegre, Porto Alege, RS – Brasil.
- Universidade Federal do Rio Grande do SulPorto AlegreRSBrasilUniversidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS – Brasil.
| | - Manoel Fernandes Canesin
- Universidade Estadual de LondrinaHospital UniversitárioLondrinaPRBrasilHospital Universitário da Universidade Estadual de Londrina, Londrina, PR – Brasil.
| | - Marcelo Imbroinise Bittencourt
- Universidade do Estado do Rio de JaneiroRio de JaneiroRJBrasilUniversidade do Estado do Rio de Janeiro (UERJ), Rio de Janeiro, RJ – Brasil.
- Hospital Universitário Pedro ErnestoRio de JaneiroRJBrasilHospital Universitário Pedro Ernesto, Rio de Janeiro, RJ – Brasil.
| | - Marcely Gimenes Bonatto
- Hospital Santa Casa de Misericórdia de CuritibaCuritibaPRBrasilHospital Santa Casa de Misericórdia de Curitiba, Curitiba, PR – Brasil.
| | | | - Mônica Samuel Avila
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Otavio Rizzi Coelho
- Universidade Estadual de CampinasFaculdade de Ciências MédicasCampinasSPBrasilFaculdade de Ciências Médicas da Universidade Estadual de Campinas (UNICAMP), Campinas, SP – Brasil.
| | - Pedro Vellosa Schwartzmann
- Hospital Unimed Ribeirão PretoRibeirão PretoSPBrasilHospital Unimed Ribeirão Preto, Ribeirão Preto, SP – Brasil.
- Centro Avançado de PesquisaEnsino e Diagnóstico (CAPED)Ribeirão PretoSPBrasilCentro Avançado de Pesquisa, Ensino e Diagnóstico (CAPED), Ribeirão Preto, SP – Brasil.
| | - Ricardo Mourilhe-Rocha
- Universidade do Estado do Rio de JaneiroRio de JaneiroRJBrasilUniversidade do Estado do Rio de Janeiro (UERJ), Rio de Janeiro, RJ – Brasil.
| | - Sandrigo Mangini
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | - Silvia Moreira Ayub Ferreira
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São PauloInstituto do CoraçãoSão PauloSPBrasilInstituto do Coração (InCor) do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), São Paulo, SP – Brasil.
| | | | - Evandro Tinoco Mesquita
- Universidade Federal FluminenseFaculdade de MedicinaNiteróiRJBrasilFaculdade de Medicina da Universidade Federal Fluminense (UFF), Niterói, RJ – Brasil.
- Treinamento Edson de Godoy Bueno / UHGCentro de EnsinoRio de JaneiroRJBrasilCentro de Ensino e Treinamento Edson de Godoy Bueno / UHG, Rio de Janeiro, RJ – Brasil.
| |
Collapse
|
20
|
Nejadeh M, Bayat P, Kheirkhah J, Moladoust H. Predicting the response to cardiac resynchronization therapy (CRT) using the deep learning approach. Biocybern Biomed Eng 2021. [DOI: 10.1016/j.bbe.2021.05.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
|
21
|
Freitas AF, Silveira FS, Conceição-Souza GE, Canesin MF, Schwartzmann PV, Bernardez-Pereira S, Bestetti RB. Emerging Topics in Heart Failure: The Future of Heart Failure: Telemonitoring, Wearables, Artificial Intelligence and Learning in the Post-Pandemic Era. Arq Bras Cardiol 2021; 115:1190-1192. [PMID: 33470323 PMCID: PMC8133716 DOI: 10.36660/abc.20201127] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Accepted: 10/20/2020] [Indexed: 11/28/2022] Open
Affiliation(s)
- Aguinaldo F Freitas
- Hospital das Clínicas da Universidade Federal de Goiás (HC-UFG), Goiânia, GO - Brasil
| | - Fábio S Silveira
- Fundação Beneficência Hospital de Cirurgia (FBHC-Ebserh), Aracaju, SE - Brasil.,Centro de Pesquisa Clínica do Coração, Aracaju, SE - Brasil
| | - Germano E Conceição-Souza
- Hospital Alemão Oswaldo Cruz, São Paulo, SP - Brasil.,Hospital Regional de São José dos Campos, São José dos Campos, SP - Brasil
| | - Manoel F Canesin
- Hospital Universitário - Universidade Estadual de Londrina (HU-UEL), Londrina, PR - Brasil.,ACTIVE - Metodologias Ativas de Ensino, São Paulo, SP - Brasil
| | - Pedro V Schwartzmann
- Hospital Unimed Ribeirão Preto, Ribeirão Preto, SP - Brasil.,Centro Avançado de Pesquisa, Ensino e Diagnóstico (Caped), Ribeirão Preto, SP - Brasil
| | | | - Reinaldo B Bestetti
- Departamento de Medicina, Universidade de Ribeirão Preto (Unaerp), Ribeirão Preto, SP - Brasil
| |
Collapse
|
22
|
Siontis KC, Noseworthy PA, Attia ZI, Friedman PA. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat Rev Cardiol 2021; 18:465-478. [PMID: 33526938 PMCID: PMC7848866 DOI: 10.1038/s41569-020-00503-2] [Citation(s) in RCA: 210] [Impact Index Per Article: 70.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/21/2020] [Indexed: 01/31/2023]
Abstract
The application of artificial intelligence (AI) to the electrocardiogram (ECG), a ubiquitous and standardized test, is an example of the ongoing transformative effect of AI on cardiovascular medicine. Although the ECG has long offered valuable insights into cardiac and non-cardiac health and disease, its interpretation requires considerable human expertise. Advanced AI methods, such as deep-learning convolutional neural networks, have enabled rapid, human-like interpretation of the ECG, while signals and patterns largely unrecognizable to human interpreters can be detected by multilayer AI networks with precision, making the ECG a powerful, non-invasive biomarker. Large sets of digital ECGs linked to rich clinical data have been used to develop AI models for the detection of left ventricular dysfunction, silent (previously undocumented and asymptomatic) atrial fibrillation and hypertrophic cardiomyopathy, as well as the determination of a person's age, sex and race, among other phenotypes. The clinical and population-level implications of AI-based ECG phenotyping continue to emerge, particularly with the rapid rise in the availability of mobile and wearable ECG technologies. In this Review, we summarize the current and future state of the AI-enhanced ECG in the detection of cardiovascular disease in at-risk populations, discuss its implications for clinical decision-making in patients with cardiovascular disease and critically appraise potential limitations and unknowns.
Collapse
Affiliation(s)
- Konstantinos C. Siontis
- grid.66875.3a0000 0004 0459 167XDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MN USA
| | - Peter A. Noseworthy
- grid.66875.3a0000 0004 0459 167XDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MN USA
| | - Zachi I. Attia
- grid.66875.3a0000 0004 0459 167XDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MN USA
| | - Paul A. Friedman
- grid.66875.3a0000 0004 0459 167XDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MN USA
| |
Collapse
|
23
|
Feeny AK, Chung MK, Madabhushi A, Attia ZI, Cikes M, Firouznia M, Friedman PA, Kalscheur MM, Kapa S, Narayan SM, Noseworthy PA, Passman RS, Perez MV, Peters NS, Piccini JP, Tarakji KG, Thomas SA, Trayanova NA, Turakhia MP, Wang PJ. Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology. Circ Arrhythm Electrophysiol 2020; 13:e007952. [PMID: 32628863 PMCID: PMC7808396 DOI: 10.1161/circep.119.007952] [Citation(s) in RCA: 74] [Impact Index Per Article: 18.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Artificial intelligence (AI) and machine learning (ML) in medicine are currently areas of intense exploration, showing potential to automate human tasks and even perform tasks beyond human capabilities. Literacy and understanding of AI/ML methods are becoming increasingly important to researchers and clinicians. The first objective of this review is to provide the novice reader with literacy of AI/ML methods and provide a foundation for how one might conduct an ML study. We provide a technical overview of some of the most commonly used terms, techniques, and challenges in AI/ML studies, with reference to recent studies in cardiac electrophysiology to illustrate key points. The second objective of this review is to use examples from recent literature to discuss how AI and ML are changing clinical practice and research in cardiac electrophysiology, with emphasis on disease detection and diagnosis, prediction of patient outcomes, and novel characterization of disease. The final objective is to highlight important considerations and challenges for appropriate validation, adoption, and deployment of AI technologies into clinical practice.
Collapse
Affiliation(s)
- Albert K Feeny
- Cleveland Clinic Lerner College of Medicine (A.K.F., M.K.C.), Case Western Reserve University, OH
| | - Mina K Chung
- Cleveland Clinic Lerner College of Medicine (A.K.F., M.K.C.), Case Western Reserve University, OH
- Department of Cardiovascular Medicine, Cleveland Clinic, OH (M.K.C., K.G.T., S.A.T.)
| | - Anant Madabhushi
- Department of Biomedical Engineering (A.M., M.F.), Case Western Reserve University, OH
- Louis Stokes Cleveland Veterans Affairs Medical Center, Cleveland, OH (A.M.)
| | - Zachi I Attia
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN (Z.I.A., P.A.F., S.K., P.A.N., )
| | - Maja Cikes
- Department of Cardiovascular Diseases, University of Zagreb School of Medicine & University Hospital Center Zagreb, Croatia (M.C.)
| | - Marjan Firouznia
- Department of Biomedical Engineering (A.M., M.F.), Case Western Reserve University, OH
| | - Paul A Friedman
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN (Z.I.A., P.A.F., S.K., P.A.N., )
| | - Matthew M Kalscheur
- Division of Cardiovascular Medicine, Department of Medicine, School of Medicine & Public Health, University of Wisconsin (M.M.K.)
- William S. Middleton Veterans Hospital, Madison, WI (M.M.K.)
| | - Suraj Kapa
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN (Z.I.A., P.A.F., S.K., P.A.N., )
| | - Sanjiv M Narayan
- Division of Cardiovascular Medicine, Stanford University, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
- Veterans Affairs Palo Alto Health Care System, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
| | - Peter A Noseworthy
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN (Z.I.A., P.A.F., S.K., P.A.N., )
| | - Rod S Passman
- Division of Cardiology, Northwestern University, Feinberg School of Medicine, Chicago, IL (R.S.P.)
| | - Marco V Perez
- Division of Cardiovascular Medicine, Stanford University, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
- Veterans Affairs Palo Alto Health Care System, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
| | - Nicholas S Peters
- National Heart Lung Institute & Centre for Cardiac Engineering, Imperial College London, United Kingdom (N.S.P.)
| | - Jonathan P Piccini
- Duke Clinical Research Institute, Duke University Medical Center, Durham, NC (J.P.P.)
| | - Khaldoun G Tarakji
- Department of Cardiovascular Medicine, Cleveland Clinic, OH (M.K.C., K.G.T., S.A.T.)
| | - Suma A Thomas
- Department of Cardiovascular Medicine, Cleveland Clinic, OH (M.K.C., K.G.T., S.A.T.)
| | - Natalia A Trayanova
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD (N.A.T.)
| | - Mintu P Turakhia
- Division of Cardiovascular Medicine, Stanford University, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
- Veterans Affairs Palo Alto Health Care System, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
- Center for Digital Health, Stanford University School of Medicine, CA (M.P.T.)
| | - Paul J Wang
- Division of Cardiovascular Medicine, Stanford University, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
- Veterans Affairs Palo Alto Health Care System, CA (S.M.N., M.V.P., M.P.T., P.J.W.)
| |
Collapse
|