BackgroundHandgrip strength (HGS) is a significant biomarker for overall health, offering a simple, cost-effective method for assessing muscle function. Lower HGS is linked to higher mortality, functional decline, cognitive impairments, and chronic diseases. Considering the influence of anthropometrics and demographics on HGS, this study aims to develop a corrected HGS score using machine learning (ML) models to enhance its utility in understanding brain health and disease.MethodsUsing UK Biobank data, sex-specific ML models were developed to predict HGS based on three anthropometric variables and age. A novel biomarker, ΔHGS, was introduced as the difference between true HGS (i.e., directly measured HGS) and bias-free predicted HGS. The neural basis of true HGS and ΔHGSwas investigated by correlating them to regional gray matter volume (GMV). Statistical analyses were performed to test their sensitivity to longitudinal changes in stroke and major depressive disorder (MDD) patients compared to matched healthy controls (HC).ResultsHGS could be accurately predicted using anthropometric and demographic features, with linear support vector machine (SVM) demonstrating high accuracy. Compared to true HGS, ΔHGSshowed high reassessment reliability and stronger, widespread associations with GMV, especially in motor-related regions. Longitudinal analysis revealed that neither HGS nor ΔHGSeffectively differentiated patients from matched HC at post time-point.ConclusionThe proposed ΔHGSscore exhibited stronger correlations with GMV compared to true HGS, suggesting it better represents the relationship between muscle strength and brain structure. While not effective in differentiating patients from HC at post time-point, the increase in ΔHGSfrom pre to post time-points in patient cohorts may indicate improved utility for monitoring disease progression, treatment efficacy, or rehabilitation effects, warranting further longitudinal validation.