# Precise diagnosis of Alzheimer’s disease based on sex-specific gray matter characteristics

## TL;DR

The paper shows that using sex-specific brain characteristics improves the diagnosis of Alzheimer’s disease.

## Contribution

The study introduces sex-specific gray matter features for Alzheimer’s diagnosis using machine learning.

## Key findings

- Eleven brain regions showed sex differences, with eight being significant in both female and male AD patients.
- Sex-specific gray matter networks showed distinct alterations in female and male AD patients.
- Machine learning models using sex-specific features improved diagnostic performance for Alzheimer’s.

## Abstract

There are notable sex differences in the gray matter of Alzheimer’s disease(AD) patients’ brains, but current evidence is insufficient to prove these differences aid diagnosis effectively.

Multivariate analysis of variance was performed on the preprocessed gray matter of healthy female and healthy male groups to identify the gray matter clusters with significant intergroup differences. Subsequently, multiple machine learning models were employed to develop sex-specific diagnostic models for AD.

We identified 11 brain regions showing sex differences, of which 8 were sex-specific in both female and male AD patients, exhibiting significant atrophy. Graph theory analysis demonstrated that the sex-specific gray matter structural brain networks in female and male AD patients exhibited distinct network alterations. We subsequently employed five advanced machine learning algorithms to develop diagnostic models for AD based on these sex-specific gray matter clusters, resulting in a notable improvement in performance.

Sex-specific gray matter characteristics can facilitate more accurate diagnosis of AD.