1
|
Deng Y, Cheng S, Huang H, Liu X, Yu Y, Gu M, Cai C, Chen X, Niu H, Hua W. Machine Learning-Based Phenomapping in Patients with Heart Failure and Secondary Prevention Implantable Cardioverter-Defibrillator Implantation: A Proof-of-Concept Study. Rev Cardiovasc Med 2023; 24:37. [PMID: 39077407 PMCID: PMC11273156 DOI: 10.31083/j.rcm2402037] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2022] [Revised: 11/22/2022] [Accepted: 11/29/2022] [Indexed: 07/31/2024] Open
Abstract
Background Previous studies have failed to implement risk stratification in patients with heart failure (HF) who are eligible for secondary implantable cardioverter-defibrillator (ICD) implantation. We aimed to evaluate whether machine learning-based phenomapping using routinely available clinical data can identify subgroups that differ in characteristics and prognoses. Methods A total of 389 patients with chronic HF implanted with an ICD were included, and forty-four baseline variables were collected. Phenomapping was performed using hierarchical k-means clustering based on factor analysis of mixed data (FAMD). The utility of phenomapping was validated by comparing the baseline features and outcomes of the first appropriate shock and all-cause death among the phenogroups. Results During a median follow-up of 2.7 years for device interrogation and 5.1 years for survival status, 142 (36.5%) first appropriate shocks and 113 (29.0%) all-cause deaths occurred. The first 12 principal components extracted using the FAMD, explaining 60.5% of the total variability, were left for phenomapping. Three mutually exclusive phenogroups were identified. Phenogroup 1 comprised the oldest patients with ischemic cardiomyopathy; had the highest proportion of diabetes mellitus, hypertension, and hyperlipidemia; and had the most favorable cardiac structure and function among the phenogroups. Phenogroup 2 included the youngest patients, mostly those with non-ischemic cardiomyopathy, who had intermediate heart dimensions and function, and the fewest comorbidities. Phenogroup 3 had the worst HF progression. Kaplan-Meier curves revealed significant differences in the first appropriate shock (p = 0.002) and all-cause death (p < 0.001) across the phenogroups. After adjusting for medications in Cox regression, phenogroups 2 and 3 displayed a graded increase in appropriate shock risk (hazard ratio [HR] 1.54, 95% confidence interval [CI] 1.03-2.28, p = 0.033; HR 2.21, 95% CI 1.42-3.43, p < 0.001, respectively; p for trend < 0.001) compared to phenogroup 1. Regarding mortality risk, phenogroup 3 was associated with an increased risk (HR 2.25, 95% CI 1.45-3.49, p < 0.001). In contrast, phenogroup 2 had a risk (p = 0.124) comparable with phenogroup 1. Conclusions Machine-learning-based phenomapping can identify distinct phenotype subgroups in patients with clinically heterogeneous HF with secondary prophylactic ICD therapy. This novel strategy may aid personalized medicine for these patients.
Collapse
Affiliation(s)
- Yu Deng
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Sijing Cheng
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Hao Huang
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Xi Liu
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Yu Yu
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Min Gu
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Chi Cai
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Xuhua Chen
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Hongxia Niu
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| | - Wei Hua
- Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China
| |
Collapse
|
2
|
Payne T, Waller J, Kheda M, Nahman NS, Maalouf J, Gopal A, Hreibe H. Efficacy of Implantable Cardioverter-defibrillators for Secondary Prevention of Sudden Cardiac Death in Patients with End-stage Renal Disease. J Innov Card Rhythm Manag 2020; 11:4199-4208. [PMID: 32874746 PMCID: PMC7452739 DOI: 10.19102/icrm.2020.110803] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2020] [Accepted: 04/06/2020] [Indexed: 01/07/2023] Open
Abstract
End-stage renal disease (ESRD) constitutes a major burden on the health-care system in the United States, with more than 300,000 patients nationwide being treated with renal replacement therapy. Very few studies to date have evaluated the benefit of implantable cardioverter-defibrillator (ICD) implantation for secondary prevention in patients with ESRD. In this study, we evaluated the efficacy of secondary-prevention ICDs in reducing all-cause mortality in patients on dialysis using the United States Renal Data System (USRDS) database. We queried the USRDS for relevant data between 2004 and 2010. Patients with diagnoses of ventricular fibrillation (VF), ventricular tachycardia (VT), or sudden cardiac arrest (SCA) were included in the study. Patients were excluded from the analysis if they were younger than 18 years; had missing age, sex, or race/ethnicity information; had experienced myocardial infarction; or had an ICD in situ at the time of VF, VT, or SCA diagnosis. The primary endpoint of this study was to determine the efficacy of secondary-prevention ICDs in reducing all-cause mortality in patients on dialysis. A total of 1,442 patients (3.4%) with ESRD had ICD insertion. Patients who received an ICD were predominantly younger, white males with lower Charlson Comorbidity Index and with fewer cardiovascular events. Survival at two years was 53% among those with an ICD relative to 27% among those without an ICD. In this study, we observed a substantial decrease in mortality in patients receiving an ICD for secondary prevention when compared with a cohort of similar patients with a history of VF, VT, or SCA.
Collapse
Affiliation(s)
- Taylor Payne
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - Jennifer Waller
- Department of Population Health, Medicine Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - Mufaddal Kheda
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - N Stanley Nahman
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - Joyce Maalouf
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - Aaron Gopal
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| | - Haitham Hreibe
- Department of Medicine, Medical College of Georgia at Augusta University, Augusta, GA, USA
| |
Collapse
|
3
|
Wuest S, Twerenbold R, Kühne M, Reichlin T, Sticherling C, Osswald S, Schaer B. Reassessment of cardiovascular parameters and comorbidities in implantable cardioverter-defibrillator patients at the time of first replacement. Clin Cardiol 2018; 41:57-62. [PMID: 29355999 DOI: 10.1002/clc.22849] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2017] [Revised: 10/24/2017] [Accepted: 10/25/2017] [Indexed: 11/07/2022] Open
Abstract
BACKGROUND Guidelines provide extensive recommendations regarding implantable cardioverter-defibrillator (ICD) implantation. However, ICD replacement at the time of battery depletion is rarely studied. HYPOTHESIS Our objectives were to identify patients at high-risk of death after ICD replacement, with a reassessment of changes in risk factors and comorbidities at the time of replacement, and to determine predictors for subsequent mortality. METHODS Patients undergoing ICD replacement for regular battery depletion were selected from a prospective single-center ICD registry. Both at implant and replacement, 3 demographic parameters, 9 cardiovascular parameters, 5 comorbidities, and 4 laboratory parameters were collected. Cox proportional hazard analyses were used. RESULTS We included 308 patients who were predominantly male (86%) with a median age at ICD replacement of 66 years. Replacement was performed 65 months (interquartile range, 52-91) after implantation. Median follow-up after replacement was 41 months, during which 82 patients (27%) died. Multivariable analysis revealed 4 independent predictors of mortality after ICD replacement: age/year (hazard ratio [HR]: 1.05, 95% confidence interval [CI]: 1.03-1.08, P = 0.01), worsening heart failure by 1 class (HR: 1.53, 95% CI: 1.15-2.03, P = 0.003), presence of left bundle branch block (HR: 1.98, 95% CI: 1.22-3.23, P = 0.006), and ICD therapy prior to replacement (HR: 2.22, 95% CI: 1.37-3.58, P = 0.001). Incorporated into a dichotomous score, they strongly correlated with mortality at 5 years after replacement (5% with 0 parameters, 15% with 1 parameter, and 30%-55% with >2 parameters). CONCLUSIONS Focused reassessment of selected patient characteristics at the time of ICD replacement correlates with subsequent mortality and can impact decision making at this point in time.
Collapse
Affiliation(s)
- Sandra Wuest
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | | | - Michael Kühne
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | - Tobias Reichlin
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | | | - Stefan Osswald
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | - Beat Schaer
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| |
Collapse
|
4
|
Vandenberk B, Robyns T, Garweg C, Floré V, Foulon S, Voros G, Ector J, Willems R. The impact of changes in LVEF and renal function on the prognosis of ICD patients after elective device replacement. Pacing Clin Electrophysiol 2017; 40:1147-1159. [DOI: 10.1111/pace.13176] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/04/2017] [Revised: 08/01/2017] [Accepted: 08/14/2017] [Indexed: 11/28/2022]
Affiliation(s)
- Bert Vandenberk
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
- Cardiology; University Hospitals Leuven; Leuven Belgium
| | - Tomas Robyns
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
- Cardiology; University Hospitals Leuven; Leuven Belgium
| | | | - Vincent Floré
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
| | - Stefaan Foulon
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
| | - Gabor Voros
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
| | - Joris Ector
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
- Cardiology; University Hospitals Leuven; Leuven Belgium
| | - Rik Willems
- Department of Cardiovascular Sciences; University of Leuven; Leuven Belgium
- Cardiology; University Hospitals Leuven; Leuven Belgium
| |
Collapse
|
5
|
Bansal N, Szpiro A, Masoudi F, Greenlee RT, Smith DH, Magid DJ, Gurwitz JH, Reynolds K, Tabada GH, Sung SH, Dighe A, Cassidy-Bushrow A, Garcia-Montilla R, Hammill S, Hayes J, Kadish A, Sharma P, Varosy P, Vidaillet H, Go AS. Kidney function and appropriateness of device therapies in adults with implantable cardioverter defibrillators. Heart 2016; 103:529-537. [PMID: 27742796 DOI: 10.1136/heartjnl-2016-309842] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/20/2016] [Revised: 09/08/2016] [Accepted: 09/18/2016] [Indexed: 11/03/2022] Open
Abstract
OBJECTIVE Patients with chronic kidney disease (CKD) have higher risk of sudden cardiac death; however, they may not receive implantable cardioverter defibrillators (ICDs), in part due to higher risk of complications. We evaluated whether CKD is associated with greater risk of device-delivered shocks/antitachycardia pacing (ATP) therapies among patients receiving a primary prevention ICD. METHODS We studied participants in the observational Cardiovascular Research Network Longitudinal Study of Implantable Cardioverter Defibrillators. CKD was defined as estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2. Outcomes included all delivered shocks/ATPs therapies and type of shock/ATP therapies (inappropriate or appropriate, determined by physician adjudication) within the 3 years. We evaluated the associations between CKD and time to first device therapy, burden of device therapy, and inappropriate versus appropriate device therapy, adjusting for demographics, comorbidity, laboratory values and medication use. RESULTS Among 2161 participants, 1066 (49.3%) had CKD (eGFR 44±11 mL/min/1.73 m2) at ICD implantation. During mean of 2.26±0.89 years, 9.8% and 18.5% of participants had at least one inappropriate and appropriate shock/ATP therapies, respectively. CKD was not associated with time to first shock/ATP therapies (adjusted HR 0.87, 95% CI 0.73 to 1.05), overall burden of shock/ATP therapies (adjusted relative rate 0.93, 95% CI 0.74 to 1.17) or inappropriate versus appropriate shock/ATP therapies (adjusted relative risk 0.88, 95% CI 0.68 to 1.14) compared with not having CKD. CONCLUSIONS In adults receiving a primary prevention ICD, mild-to-moderate CKD was not associated with the timing, burden or appropriateness of subsequent device therapy. Potential concern for inappropriate ICD-delivered therapies should not preclude ICDs among eligible patients with CKD.
Collapse
Affiliation(s)
- Nisha Bansal
- Division of Nephrology, Kidney Research Institute, University of Washington, Seattle, Washington, USA
| | - Adam Szpiro
- Department of Biostatistics, University of Washington, Seattle, Washington, USA
| | | | | | - David H Smith
- Kaiser Permanente Northwest Center for Health Research, Portland, Oregon, USA
| | - David J Magid
- Kaiser Permanente Colorado Institute for Health Research, Oakland, California, USA
| | - Jerry H Gurwitz
- Meyers Primary Care Institute, Worcester, Massachusetts, USA
| | - Kristi Reynolds
- Kaiser Permanente Southern California Department of Research and Evaluation, Pasadena, California, USA
| | - Grace H Tabada
- Kaiser Permanente Northern California Division of Research, Oakland, California, USA
| | - Sue Hee Sung
- Kaiser Permanente Northern California Division of Research, Oakland, California, USA
| | - Ashveena Dighe
- Division of Nephrology, Kidney Research Institute, University of Washington, Seattle, Washington, USA
| | | | | | | | - John Hayes
- Marshfield Clinic Research Foundation, Wisconsin, USA
| | | | - Param Sharma
- Marshfield Clinic Research Foundation, Wisconsin, USA
| | - Paul Varosy
- University of Colorado Hospital, Aurora, Colorado, USA
| | | | - Alan S Go
- Kaiser Permanente Northern California Division of Research, Oakland, California, USA
| |
Collapse
|