What is the clinical evidence from this study?

Study design: Observational. Population: Aging-related diseases (n=48783). Intervention: ECG-enabled biological age (ECG-BA) combined with chronological age (CA) vs. Chronological age (CA) alone. Primary outcome: Net reclassification improvement (NRI) for aging-related diseases (21.0%).

February 6, 2025Open Access

Reclassification of the conventional risk assessment for aging-related diseases by electrocardiogram-enabled biological age

Key Result

Combining AI-enabled electrocardiogram biological age with chronological age improved risk classification for aging-related diseases by an average of 21% compared to chronological age alone.

Study Design

Type

Observational (n=48,783)

Multicenter

Structured PICO

Does an AI-enabled ECG biological age model improve the prediction of aging-related diseases compared to chronological age alone in adults?

Population

Healthy adults and adults with subclinical diseases

Intervention

Artificial intelligence (AI)-enabled electrocardiogram (ECG) model predicting ECG biological age (ECG-BA) combined with chronological age (CA)

Comparator

Chronological age (CA) alone

Outcome

Diagnostic accuracy and risk classification for aging-related diseases' onset (including stroke, coronary artery disease, peripheral arterial occlusive disease, myocardial infarction, Alzheimer's disease, osteoarthritis, and cancers)surrogate

An AI-enabled ECG biological age model significantly improves diagnostic accuracy and risk classification for aging-related diseases by 21% compared to chronological age alone.

Main Result

Effect estimate: 21.0%

Limitations

ECG data were collected from a single tertiary center, requiring multi-center validation across a more diverse population.
Database did not include data on systolic/diastolic blood pressure, total cholesterol, or smoking status, preventing calculation of conventional risk scores.
Reliance on ICD diagnostic codes may miss patients with mild symptoms or minor ECG abnormalities.
AI model was generated using a specific Philips ECG machine, which may require validation for other systems.

Abstract

An artificial intelligence (AI)-enabled electrocardiogram (ECG) model has been developed in a healthy adult population to predict ECG biological age (ECG-BA). This ECG-BA exhibited a robust correlation with chronological age (CA) in healthy adults and additionally significantly enhanced the prediction of aging-related diseases' onset in adults with subclinical diseases. The model showed particularly strong predictive power for cardiovascular and non-cardiovascular diseases such as stroke, coronary artery disease, peripheral arterial occlusive disease, myocardial infarction, Alzheimer's disease, osteoarthritis, and cancers. When combined with CA, ECG-BA improved diagnostic accuracy and risk classification by 21% over using CA alone, notably offering the greatest improvements in cancer prediction. The net reclassification improvement significantly reduced misclassification rates for disease onset predictions. This comprehensive study validates ECG-BA as an effective supplement to CA, advancing the precision of risk assessments for aging-related conditions and suggesting broad implications for enhancing preventive healthcare strategies, potentially leading to better patient outcomes.

Mark Helpful

Bookmark

Relay

View Full Paper