Aims: Heart failure (HF) is a leading cause of death. Early intervention is the key to reduce HF-related morbidity and mortality. This study assesses the utility of electrocardiograms (ECGs) in HF risk prediction.Methods and results: Data from the baseline visits (1987–89) of the Atherosclerosis Risk in Communities (ARIC) study was used. Incident hospitalized HF events were ascertained by ICD codes. Participants with good quality baseline ECGs were included. Participants with prevalent HF were excluded. ECG-artificial intelligence (AI) model to predict HF was created as a deep residual convolutional neural network (CNN) utilizing standard 12-lead ECG. The area under the receiver operating characteristic curve (AUC) was used to evaluate prediction models including (CNN), light gradient boosting machines (LGBM), and Cox proportional hazards regression. A total of 14 613 (45% male, 73% of white, mean age ± standard deviation of 54 ± 5) participants were eligible. A total of 803 (5.5%) participants developed HF within 10 years from baseline. Convolutional neural network utilizing solely ECG achieved an AUC of 0.756 (0.717–0.795) on the hold-out test data. ARIC and Framingham Heart Study (FHS) HF risk calculators yielded AUC of 0.802 (0.750–0.850) and 0.780 (0.740–0.830). The highest AUC of 0.818 (0.778–0.859) was obtained when ECG-AI model output, age, gender, race, body mass index, smoking status, prevalent coronary heart disease, diabetes mellitus, systolic blood pressure, and heart rate were used as predictors of HF within LGBM. The ECG-AI model output was the most important predictor of HF.Conclusions: ECG-AI model based solely on information extracted from ECG independently predicts HF with accuracy comparable to existing FHS and ARIC risk calculators.

Heart failure (HF) is a progressive condition with high global incidence. HF has two main subtypes: HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF). There is an inherent need for simple yet effective electrocardiogram (ECG)-based artificial intelligence (AI; ECG-AI) models that can predict HF risk early to allow for risk modification. The main objectives were to validate HF risk prediction models using Multi-Ethnic Study of Atherosclerosis (MESA) data and assess performance on HFpEF and HFrEF classification. There were six models in comparision derived using ARIC data. 1) The ECG-AI model predicting HF risk was developed using raw 12-lead ECGs with a convolutional neural network. The clinical models from 2) ARIC (ARIC-HF) and 3) Framingham Heart Study (FHS-HF) used 9 and 8 variables, respectively. 4) Cox proportional hazards (CPH) model developed using the clinical risk factors in ARIC-HF or FHS-HF. 5) CPH model using the outcome of ECG-AI and the clinical risk factors used in CPH model (ECG-AI-Cox) and 6) A Light Gradient Boosting Machine model using 288 ECG Characteristics (ECG-Chars). All the models were validated on MESA. The performances of these models were evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. ECG-AI, ECG-Chars, and ECG-AI-Cox resulted in validation AUCs of 0.77, 0.73, and 0.84, respectively. ARIC-HF and FHS-HF yielded AUCs of 0.76 and 0.74, respectively, and CPH resulted in AUC = 0.78. ECG-AI-Cox outperformed all other models. ECG-AI-Cox provided an AUC of 0.85 for HFrEF and 0.83 for HFpEF. ECG-AI using ECGs provides better-validated predictions when compared to HF risk calculators, and the ECG feature model and also works well with HFpEF and HFrEF classification.

Fatal coronary heart disease (FCHD) is often described as sudden cardiac death (affects >4 million people/year), where coronary artery disease is the only identified condition. Electrocardiographic artificial intelligence (ECG-AI) models for FCHD risk prediction using ECG data from wearable devices could enable wider screening/monitoring efforts. To develop a single-lead ECG–based deep learning model for FCHD risk prediction and assess concordance between clinical and Apple Watch ECGs. An FCHD single-lead (“lead I” from 12-lead ECGs) ECG-AI model was developed using 167,662 ECGs (50,132 patients) from the University of Tennessee Health Sciences Center. Eighty percent of the data (5-fold cross-validation) was used for training and 20% as a holdout. Cox proportional hazards (CPH) models incorporating ECG-AI predictions with age, sex, and race were also developed. The models were tested on paired clinical single-lead and Apple Watch ECGs from 243 St. Jude Lifetime Cohort Study participants. The correlation and concordance of the predictions were assessed using Pearson correlation (R), Spearman correlation (ρ), and Cohen’s kappa. The ECG-AI and CPH models resulted in AUC = 0.76 and 0.79, respectively, on the 20% holdout and AUC = 0.85 and 0.87 on the Atrium Health Wake Forest Baptist external validation data. There was moderate-strong positive correlation between predictions (R = 0.74, ρ = 0.67, and κ = 0.58) when tested on the 243 paired ECGs. The clinical (lead I) and Apple Watch predictions led to the same low/high-risk FCHD classification for 99% of the participants. CPH prediction correlation resulted in an R = 0.81, ρ = 0.76, and κ = 0.78. Risk of FCHD can be predicted from single-lead ECGs obtained from wearable devices and are statistically concordant with lead I of a 12-lead ECG.

Background: Parkinson’s disease (PD) is a chronic, disabling neurodegenerative disorder. Objective: To predict a future diagnosis of PD using questionnaires and simple non-invasive clinical tests. Methods: Participants in the prospective Kuakini Honolulu-Asia Aging Study (HAAS) were evaluated biannually between 1995–2017 by PD experts using standard diagnostic criteria. Autopsies were sought on all deaths. We input simple clinical and risk factor variables into an ensemble-tree based machine learning algorithm and derived models to predict the probability of developing PD. We also investigated relationships of predictive models and neuropathologic features such as nigral neuron density. Results: The study sample included 292 subjects, 25 of whom developed PD within 3 years and 41 by 5 years. 116 (46%) of 251 subjects not diagnosed with PD underwent autopsy. Light Gradient Boosting Machine modeling of 12 predictors correctly classified a high proportion of individuals who developed PD within 3 years (area under the curve (AUC) 0.82, 95%CI 0.76–0.89) or 5 years (AUC 0.77, 95%CI 0.71–0.84). A large proportion of controls who were misclassified as PD had Lewy pathology at autopsy, including 79%of those who died within 3 years. PD probability estimates correlated inversely with nigral neuron density and were strongest in autopsies conducted within 3 years of index date (r = –0.57, p < 0.01). Conclusion: Machine learning can identify persons likely to develop PD during the prodromal period using questionnaires and simple non-invasive tests. Correlation with neuropathology suggests that true model accuracy may be considerably higher than estimates based solely on clinical diagnosis.