Accelerated Aging in LMNA Mutations Detected by Artificial Intelligence ECG-Derived Age

Area of Science:

• Genetics and Aging Research
• Cardiology
• Artificial Intelligence in Medicine

Background:

• Lamin A/C (LMNA) gene mutations are associated with various aging phenotypes.
• Hypothesis that LMNA mutation carriers exhibit biological age exceeding their chronological age.
• Impact of accelerated aging on patient care and management.

Purpose of the Study:

• To investigate whether patients with LMNA gene mutations have a biological age older than their chronological age.
• To utilize Artificial Intelligence-Electrocardiogram (AI-ECG) to assess biological age.
• To identify potential early biomarkers for aging in LMNA patients.

Main Methods:

• Application of a trained convolutional neural network model to predict biological age from electrocardiograms (ECGs).
• Analysis of ECGs from LMNA patients and age-/sex-matched controls.
• Calculation of the age gap (chronological age - AI-ECG age) for comparison.

Main Results:

• LMNA patients, including asymptomatic carriers, demonstrated an AI-ECG age approximately 16 years older than non-carriers.
• A significant age gap of over 10 years was observed in most LMNA patients compared to controls (P<.001).
• Consecutive AI-ECG analysis revealed accelerated aging in the LMNA group (P<.0001).

Conclusions:

• AI-ECG accurately predicts a biological age older than chronological age in LMNA patients.
• Accelerated aging is indicated by AI-ECG even in the absence of traditional cardiac abnormalities.
• This AI-ECG approach may enable early medical intervention and serve as a disease biomarker for LMNA-related conditions.