Machine learning approaches based on fibroblast morphometry do not predict ALS

Abstract

Amyotrophic lateral sclerosis (ALS) is a devastating neuromuscular disease with limited therapeutic options. Biomarkers are needed for early disease detection, clinical trial design, and personalized medicine. Early evidence suggests that specific morphometric features in ALS primary skin fibroblasts may be used as biomarkers; however, this hypothesis has not been rigorously tested in conclusively large fibroblast populations. Here, we imaged ALS-relevant organelles (mitochondria, endoplasmic reticulum, lysosomes) and proteins (TAR DNA-binding protein 43, Ras GTPase-activating protein-binding protein 1, heat-shock protein 60) at baseline and under stress perturbations and tested their predictive power on a total set of 443 human fibroblast lines from ALS and healthy individuals. Machine learning approaches were able to confidently predict stress perturbation states (ROC-AUC ∼0.99) but not disease groups or clinical features (ROC-AUC 0.58-0.64). Our findings indicate that multivariate models using patient-derived fibroblast morphometry can accurately predict different stressors but are insufficient to develop viable ALS biomarkers.

Keywords: Amyotrophic lateral sclerosis; Biomarker; Fibroblast; Immunocytochemistry; Live Imaging; Machine learning; Morphometry.