Response to: Significance and stability of deep learning-based identification of subtypes within major psychiatric disorders. Molecular Psychiatry (2022)

TL;DR

This paper responds to critiques of a machine learning approach for identifying psychiatric disorder subtypes, clarifying misconceptions and discussing issues of generalizability, significance, and stability.

Contribution

The authors clarify misconceptions about their previous work and discuss key issues in applying machine learning to psychiatric subtype identification.

Findings

Clarification of misconceptions about machine learning concepts

Discussion on the importance of statistical significance and stability

Addressing overfitting concerns in neurobiological subtype classification

Abstract

Recently, Winter and Hahn [1] commented on our work on identifying subtypes of major psychiatry disorders (MPDs) based on neurobiological features using machine learning [2]. They questioned the generalizability of our methods and the statistical significance, stability, and overfitting of the results, and proposed a pipeline for disease subtyping. We appreciate their earnest consideration of our work, however, we need to point out their misconceptions of basic machine-learning concepts and delineate some key issues involved.