An AI-driven model for risk stratification and prototype intervention mapping in motoric cognitive risk syndrome and subjective cognitive decline
- 1epartment of Neurology, Chest Hospital of Shenyang Pharmaceutical University, Shenyang, Liaoning, China
Abstract
As Alzheimer's disease and other dementias continue their global rise, there is a compelling need for early identification of pre-clinical cognitive decline. Motoric Cognitive Risk Syndrome and Subjective Cognitive Decline represent crucial transition phases to facilitate targeted intervention, and existing unimodal approaches are neither sensitive nor sufficiently multimodal for appropriate risk classification and individualized intervention mapping (prototype). This study introduces a hybrid multimodal CNN fusion framework based on an improved version of light spectrum optimizer as metaheuristic optimizer to address this challenge. The framework fuses multiple modality-specific information through parallel three-dimensional convolutional neural network branches (MRI and PET) and encoders of motor, cognitive, and biomarker information followed by a combination of intermediate and late fusion layers with parameters tuned by the optimized framework. The framework is meticulously assessed on the BIOCARD longitudinally dataset and achieved an accuracy of 93.7% and an area under the ROC curve (AUC) of 0.965. It significantly surpassed seven state-of-the-art methods and revealed clinical interpretability through longitudinal risk trajectories and SHAP attribution of features.
Related
- Rehabilitative efficacy of cognitive behavioral therapy-based intervention for chronic fatigue syndrome : A systematic review and meta-analysis
- Effect of an educational indoor air quality intervention on cognitive status, sleep quality, balance, and sick building syndrome in older adults: a randomized controlled trial
- Controlled deep breathing technique intervention effects on resting EEG, subjective psychological distress, and executive function performance in young adults
- Effects of cognitive-motor dual-task walking exercise versus walking-only exercise on cognitive function and patient-centred outcomes in older adults with subjective brain fog: a randomised controlled trial.
- Age at Menopause and Subjective Cognitive Symptoms Predict Digital Cognitive Outcomes at the Gynecological Well-Woman Visit
BibTeX
@article{wang2026aidriven,
title = {{An AI-driven model for risk stratification and prototype intervention mapping in motoric cognitive risk syndrome and subjective cognitive decline}},
author = {Zhihan Wang and Dingying Liu and Bosi Zhou and Shuo Chen and Qing Xu and Haonan Ding and Bing Xu and Xue Qin},
journal = {Frontiers in Aging Neuroscience},
year = {2026},
month = oct,
doi = {10.3389/fnagi.2026.1878389},
url = {https://doi.org/10.3389/fnagi.2026.1878389},
note = {CC BY},
}
RIS
TY - JOUR
TI - An AI-driven model for risk stratification and prototype intervention mapping in motoric cognitive risk syndrome and subjective cognitive decline
AU - Zhihan Wang
AU - Dingying Liu
AU - Bosi Zhou
AU - Shuo Chen
AU - Qing Xu
AU - Haonan Ding
AU - Bing Xu
AU - Xue Qin
PY - 2026
DA - 2026/10/23
JO - Frontiers in Aging Neuroscience
DO - 10.3389/fnagi.2026.1878389
UR - https://doi.org/10.3389/fnagi.2026.1878389
AB - As Alzheimer's disease and other dementias continue their global rise, there is a compelling need for early identification of pre-clinical cognitive decline. Motoric Cognitive Risk Syndrome and Subjective Cognitive Decline represent crucial transition phases to facilitate targeted intervention, and existing unimodal approaches are neither sensitive nor sufficiently multimodal for appropriate risk classification and individualized intervention mapping (prototype). This study introduces a hybrid multimodal CNN fusion framework based on an improved version of light spectrum optimizer as metaheuristic optimizer to address this challenge. The framework fuses multiple modality-specific information through parallel three-dimensional convolutional neural network branches (MRI and PET) and encoders of motor, cognitive, and biomarker information followed by a combination of intermediate and late fusion layers with parameters tuned by the optimized framework. The framework is meticulously assessed on the BIOCARD longitudinally dataset and achieved an accuracy of 93.7% and an area under the ROC curve (AUC) of 0.965. It significantly surpassed seven state-of-the-art methods and revealed clinical interpretability through longitudinal risk trajectories and SHAP attribution of features.
SN - 1663-4365
ER -