Work

Intrinsic dimensionality of deep learning representations reveals cell death-associated heterogeneity in Parkinson’s disease iPSC-derived neurons

Year: 2026

Type: preprint

Abstract: As AI is increasingly used to stratify heterogeneous Parkinson’s disease, it is essential to determine whether learned representations preserve disease-relevant variation within diagnostic or genetic groups. In iPSC-derived neurons from three familial PD cases, deep learning representations encoded an independent measure of cell death, and their intrinsic dimensionality increased with death burden. Latent dimensionality offers a way to examine heterogeneity before AI-derived clusters are interpreted as disease subtypes.

Source: bioRxiv (Cold Spring Harbor Laboratory)

DOI: 10.64898/2026.10.02.756370

Authors: Seohyeon Kang, Jisung Park, Minee L. Choi

Institutions: Korea Advanced Institute of Science and Technology, Chang Gung University

Language: English

Topic: Parkinson's Disease Mechanisms and Treatments

Subfield: Clinical Neurology

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

Funders: Nagoya City University, National Institutes of Health, College of Life Sciences and Agriculture, University of New Hampshire, Japan Society for the Promotion of Science