# Limitations of MMSE in Cognitive Assessment: Revealing Latent Risk via Structural Brain Atrophy

## TL;DR

This study shows that combining the MMSE with brain atrophy indicators improves cognitive risk assessment, especially for identifying early decline in people with normal MMSE scores.

## Contribution

The study introduces an explainable deep-learning framework integrating MMSE and nWBV to improve cognitive stage classification and detect latent risk.

## Key findings

- The MMSE alone has strong discriminative power, but adding nWBV improves classification performance.
- nWBV provides complementary structural risk signals in the MMSE-normal subgroup.
- Interpretability analysis confirms MMSE and nWBV as key features with stable contributions across models.

## Abstract

The primary objective of this study was to evaluate the relative contributions of the MMSE and nWBV in three-class cognitive stage classification, with a secondary objective of conducting a subgroup analysis to investigate latent risk within the MMSE-normal population. To achieve this, we proposed an explainable deep-learning-based analytical framework integrating the MMSE with nWBV, a structural brain atrophy indicator, and systematically assessed the relative contributions of each variable in cognitive impairment stage classification and potential risk screening. Although the MMSE is widely used in clinical practice as a cognitive screening tool, it has limited sensitivity to early or subtle cognitive decline and may not adequately reflect structural brain changes due to the ceiling effect. To address this limitation, we compared four tabular deep learning models—MLP, Tab ResNet, Tab Transformer, and FT Transformer—under identical fivefold cross-validation conditions. Age and sex were fixed as covariates, and feature ablation analysis was conducted to examine the independent and combined effects of the MMSE and nWBV. The results showed no statistically significant differences in classification performance among model architectures, indicating that predictive performance was primarily determined by the informational content of the input variables rather than model complexity. In the feature ablation analysis, the MMSE alone demonstrated strong discriminative power, whereas nWBV alone showed relatively limited performance; however, when combined with the MMSE, nWBV consistently improved classification performance. Furthermore, for interpretability analysis, both Integrated Gradients (IG) and SHAP were applied to validate variable contributions from complementary perspectives. Across both methods, the MMSE and nWBV were repeatedly identified as key contributing features, and interpretability stability was maintained throughout cross-validation folds, supporting the robustness and reliability of the explanatory results. Beyond simple model performance comparisons, this study provides evidence supporting the complementary integration of structural brain atrophy information into MMSE-centered traditional cognitive assessment by jointly considering variable contribution and interpretability stability. This approach is expected to contribute to precision risk screening and clinical decision support in the early stages of cognitive decline. Although the MMSE exhibited strong discriminative performance, nWBV provided complementary structural risk signals within the MMSE-normal subgroup, suggesting that integrating cognitive assessment with structural biomarkers may enhance early risk identification.