TY - JOUR
T1 - Artificial Intelligence–Enabled Electrocardiogram for Atrial Fibrillation Identifies Cognitive Decline Risk and Cerebral Infarcts
AU - Weil, Erika L.
AU - Noseworthy, Peter A.
AU - Lopez, Camden L.
AU - Rabinstein, Alejandro A.
AU - Friedman, Paul A.
AU - Attia, Zachi I.
AU - Yao, Xiaoxi
AU - Siontis, Konstantinos C.
AU - Kremers, Walter K.
AU - Christopoulos, Georgios
AU - Mielke, Michelle M.
AU - Vemuri, Prashanthi
AU - Jack, Clifford R.
AU - Gersh, Bernard J.
AU - Machulda, Mary M.
AU - Knopman, David S.
AU - Petersen, Ronald C.
AU - Graff-Radford, Jonathan
N1 - Funding Information:
Grant Support: Research reported in this publication was supported by the National Institute on Aging of the National Institutes of Health (NIH) under Award Number K76AG057015 and the NIH Grants R01 AG011378 (Dr Jack) Evaluating and Extending Our Hypothetical Model of Alzheimer's Biomarkers; R01 AG041851 (Drs Jack and Knopman) Validating the New Criteria for Preclinical Alzheimer's disease; U01 AG006786 (Dr Petersen) ? Mayo Clinic Study of Aging (MCSA); R01 NS097495 (Dr Vemuri) Development, Validation, and Application of an Imaging based CVD Scale; P30 AG062677 (Dr Petersen) Alzheimer's Disease Research Center (ADRC), and the GHR Foundation. This study was made possible by the Rochester Epidemiology Project (grant number R01-AG034676). The funders had no role in the conception or preparation of this manuscript. Potential Competing Interests: Dr Noseworthy has received grants from the National Institute on Aging of the National Institutes of Health (NIH) under Award Number R01AG 062436, the National Heart, Lung, and Blood Institute [NHLBI], the Agency for Healthcare Research and Quality (AHRQ), US Food and Drug Administration (FDA), and the American Heart Association (AHA); is a study investigator in an ablation trial sponsored by Medtronic; with Mayo Clinic is involved in a potential equity/royalty relationship with AliveCor; has served on an expert advisory panel for Optum; and with Mayo Clinic has filed patents related to the application of AI to the ECG for diagnosis and risk stratification. Drs Noseworthy, Friedman, and Attia are co-inventors of the AI ECG algorithm described in this manuscript which has been licensed to Anumana whereby they and Mayo Clinic may receive financial benefit from its use in the future. Dr Kremers has received grants from AstraZeneca, Biogen, and Roche. Dr Mielke has received consulting fees from Biogen and Brain Protection Company; and has received grants from the NIH and DOD. Dr Vemuri has received grants from the NIH; and has received speaking fees from Miller Medical Communications LLC. Dr Jack serves on an independent data monitoring board for Roche and has consulted for Eisai and Lily, but he receives no personal compensation from any commercial entity; and he has received grants from NIH and the Alexander Family Alzheimer's Disease Research Professorship of the Mayo Clinic. Dr Machulda has received grants from the NIH. Dr Knopman has served on a Data Safety Monitoring Board for the DIAN study; serves on a Data Safety monitoring Board for a tau therapeutic for Biogen, but receives no personal compensation; is a site investigator in Biogen aducanumab trials; is an investigator in a clinical trial sponsored by Lilly Pharmaceuticals and the University of Southern California; he serves as a consultant for Samus Therapeutics, Third Rock, Roche, and Alzeca Biosciences but receives no personal compensation; and he has received research support from the NIH. Dr Petersen has received consulting fees from Merck Inc, Roche Inc, Biogen Inc, Eli Lilly and Company, and Genentech Inc; has received publishing royalties for Mild Cognitive Impairment (Oxford University Press, 2003); and has received research support from the NIH and the Robert H. and Clarice Smith and Abigail Van Buren Alzheimer's Disease Research Program of the Mayo Foundation. Dr Graff-Radford has received grants from the National Institute on Aging of the National Institutes of Health (NIH) under Award Number K76AG057015 and serves on the editorial board of Neurology. The remaining authors report no potential competing interests.
Funding Information:
Grant Support : Research reported in this publication was supported by the National Institute on Aging of the National Institutes of Health (NIH) under Award Number K76AG057015 and the NIH Grants R01 AG011378 (Dr Jack) Evaluating and Extending Our Hypothetical Model of Alzheimer’s Biomarkers; R01 AG041851 (Drs Jack and Knopman) Validating the New Criteria for Preclinical Alzheimer’s disease; U01 AG006786 (Dr Petersen) — Mayo Clinic Study of Aging (MCSA); R01 NS097495 (Dr Vemuri) Development, Validation, and Application of an Imaging based CVD Scale; P30 AG062677 (Dr Petersen) Alzheimer’s Disease Research Center (ADRC), and the GHR Foundation. This study was made possible by the Rochester Epidemiology Project (grant number R01-AG034676). The funders had no role in the conception or preparation of this manuscript.
Publisher Copyright:
© 2022 Mayo Foundation for Medical Education and Research
PY - 2022/5
Y1 - 2022/5
N2 - Objective: To investigate whether artificial intelligence–enabled electrocardiogram (AI-ECG) assessment of atrial fibrillation (AF) risk predicts cognitive decline and cerebral infarcts. Patients and Methods: This population-based study included sinus-rhythm ECG participants seen from November 29, 2004 through July 13, 2020, and a subset with brain magnetic resonance imaging (MRI) (October 10, 2011, through November 2, 2017). The AI-ECG score of AF risk calculated for participants was 0-1. To determine the AI-ECG-AF relationship with baseline cognitive dysfunction, we compared linear mixed-effects models with global and domain-specific cognitive z-scores from longitudinal neuropsychological assessments. The AI-ECG-AF score was logit transformed and modeled with cubic splines. For the brain-MRI subset, logistic regression evaluated correlation of the AI-ECG-AF score and the high-threshold, dichotomized AI-ECG-AF score with infarcts. Results: Participants (N=3729; median age, 74.1 years) underwent cognitive analysis. Adjusting for age, sex, education, and APOE ɛ4-carrier status, the AI-ECG-AF score correlated with lower baseline and faster decline in global-cognitive z-scores (P=.009 and P=.01, respectively, non–linear-based spline-models tests) and attention z-scores (P<.001 and P=.01, respectively). Sinus-rhythm-ECG participants (n=1373) underwent MRI. As a continuous measure, the AI-ECG-AF score correlated with infarcts but not after age and sex adjustment (P=.52). For dichotomized analysis, an AI-ECG-AF score greater than 0.5 correlated with infarcts (OR, 4.61; 95% CI, 2.45-8.55; P<.001); even after age and sex adjustment (OR, 2.09; 95% CI, 1.06-4.07; P=.03). Conclusion: The AI-ECG-AF score correlated with worse baseline cognition and gradual global cognition and attention decline. High AF probability by AI-ECG-AF score correlated with MRI cerebral infarcts. However, most infarcts observed in our cohort were subcortical, suggesting that AI-ECG not only predicts AF but also detects other non-AF cardiac disease markers and correlates with small vessel cerebrovascular disease and cognitive decline.
AB - Objective: To investigate whether artificial intelligence–enabled electrocardiogram (AI-ECG) assessment of atrial fibrillation (AF) risk predicts cognitive decline and cerebral infarcts. Patients and Methods: This population-based study included sinus-rhythm ECG participants seen from November 29, 2004 through July 13, 2020, and a subset with brain magnetic resonance imaging (MRI) (October 10, 2011, through November 2, 2017). The AI-ECG score of AF risk calculated for participants was 0-1. To determine the AI-ECG-AF relationship with baseline cognitive dysfunction, we compared linear mixed-effects models with global and domain-specific cognitive z-scores from longitudinal neuropsychological assessments. The AI-ECG-AF score was logit transformed and modeled with cubic splines. For the brain-MRI subset, logistic regression evaluated correlation of the AI-ECG-AF score and the high-threshold, dichotomized AI-ECG-AF score with infarcts. Results: Participants (N=3729; median age, 74.1 years) underwent cognitive analysis. Adjusting for age, sex, education, and APOE ɛ4-carrier status, the AI-ECG-AF score correlated with lower baseline and faster decline in global-cognitive z-scores (P=.009 and P=.01, respectively, non–linear-based spline-models tests) and attention z-scores (P<.001 and P=.01, respectively). Sinus-rhythm-ECG participants (n=1373) underwent MRI. As a continuous measure, the AI-ECG-AF score correlated with infarcts but not after age and sex adjustment (P=.52). For dichotomized analysis, an AI-ECG-AF score greater than 0.5 correlated with infarcts (OR, 4.61; 95% CI, 2.45-8.55; P<.001); even after age and sex adjustment (OR, 2.09; 95% CI, 1.06-4.07; P=.03). Conclusion: The AI-ECG-AF score correlated with worse baseline cognition and gradual global cognition and attention decline. High AF probability by AI-ECG-AF score correlated with MRI cerebral infarcts. However, most infarcts observed in our cohort were subcortical, suggesting that AI-ECG not only predicts AF but also detects other non-AF cardiac disease markers and correlates with small vessel cerebrovascular disease and cognitive decline.
UR - http://www.scopus.com/inward/record.url?scp=85129374898&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129374898&partnerID=8YFLogxK
U2 - 10.1016/j.mayocp.2022.01.026
DO - 10.1016/j.mayocp.2022.01.026
M3 - Article
C2 - 35512882
AN - SCOPUS:85129374898
SN - 0025-6196
VL - 97
SP - 871
EP - 880
JO - Mayo Clinic Proceedings
JF - Mayo Clinic Proceedings
IS - 5
ER -