Scholarlink

Background <p>Timely prediction of cognitive decline in patients with Mild Cognitive Impairment (MCI) is crucial for guiding optimal therapeutic interventions. In this study, we aimed to develop a deep survival analysis model that leverages longitudinal, multi-modal data to estimate the probability of dementia conversion, thereby facilitating personalized treatment planning in clinical practice.</p> Methods <p>We employed a deep neural network model specifically designed for survival analysis to predict the progression from MCI to Alzheimer’s Disease (AD). The model integrated longitudinal biomarkers, including neuropsychological assessments and neuroimaging measures, along with baseline demographic characteristics and genetic risk factors, using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.</p> Results <p>This study enrolled 922 baseline MCI patients for analysis. The predictive performance was evaluated using a test set at time intervals <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\Delta t\)</EquationSource> </InlineEquation> = 1, 2, 3, 4 years from the landmark time s = 1. The prognostic model exhibited outstanding predictive capability, attaining cdAUC values of 0.9089 ± 0.01 alongside BS of 0.1651 ± 0.01 with <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\Delta t\)</EquationSource> </InlineEquation> = 1 year on the test set, when all variable sets were incorporated into the time-dependent Cox survival neural network (tdCoxSNN) model. Through feature significance evaluation, the Functional Activities Questionnaire (FAQ) emerged as the most influential predictive element.</p> Conclusions <p>By systematically integrating diverse longitudinal biomarkers, we developed a dynamic prediction model for MCI using deep survival analysis. This approach enables accurate individual risk stratification, facilitates the early identification of high-risk individuals, and supports informed, personalized clinical decision-making.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Longitudinal multi-modal data prediction model for mild cognitive impairment by deep survival analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月16日

查看全文
  • Rong Zhang,
  • Durong Chen,
  • Yao Qin,
  • Hongjuan Han,
  • Hongmei Yu

摘要

Background

Timely prediction of cognitive decline in patients with Mild Cognitive Impairment (MCI) is crucial for guiding optimal therapeutic interventions. In this study, we aimed to develop a deep survival analysis model that leverages longitudinal, multi-modal data to estimate the probability of dementia conversion, thereby facilitating personalized treatment planning in clinical practice.

Methods

We employed a deep neural network model specifically designed for survival analysis to predict the progression from MCI to Alzheimer’s Disease (AD). The model integrated longitudinal biomarkers, including neuropsychological assessments and neuroimaging measures, along with baseline demographic characteristics and genetic risk factors, using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.

Results

This study enrolled 922 baseline MCI patients for analysis. The predictive performance was evaluated using a test set at time intervals \(\Delta t\)  = 1, 2, 3, 4 years from the landmark time s = 1. The prognostic model exhibited outstanding predictive capability, attaining cdAUC values of 0.9089 ± 0.01 alongside BS of 0.1651 ± 0.01 with \(\Delta t\)  = 1 year on the test set, when all variable sets were incorporated into the time-dependent Cox survival neural network (tdCoxSNN) model. Through feature significance evaluation, the Functional Activities Questionnaire (FAQ) emerged as the most influential predictive element.

Conclusions

By systematically integrating diverse longitudinal biomarkers, we developed a dynamic prediction model for MCI using deep survival analysis. This approach enables accurate individual risk stratification, facilitates the early identification of high-risk individuals, and supports informed, personalized clinical decision-making.