Affiliations: [a] Department of Biology and General Genetics, I.M. Sechenov First Moscow State Medical University, Moscow, Russia
| [b] Department of Statistics, Florida State University, Tallahassee, FL, USA
| [c] Department of Polyclinic Therapy, I.M. Sechenov First Moscow State Medical University, Moscow, Russia
Correspondence:
[*]
Correspondence to: Siqi Mao, Department of Statistics, Florida State University, Tallahassee, FL, USA. E-mail: siqimao@gmx.com.
Abstract: Background:In recent years, researchers have focused on developing precise models for the progression of Alzheimer’s disease (AD) using deep neural networks. Forecasting the progression of AD through the analysis of time series data represents a promising approach. Objective:The primary objective of this research is to formulate an effective methodology for forecasting the progression of AD through the integration of multi-task learning techniques and the analysis of pertinent medical data. Methods:This study primarily utilized volumetric measurements obtained through magnetic resonance imaging (MRI), trajectories of cognitive assessments, and clinical status indicators. The research encompassed 150 patients diagnosed with AD who underwent examination between 2020 and 2022 in Beijing, China. A multi-task learning approach was employed to train forecasting models using MRI data, trajectories of cognitive assessments, and clinical status. Correlation analysis was conducted at various time points. Results:At the baseline, a robust correlation was observed among the forecasting tasks: 0.75 for volumetric MRI measurements, 0.62 for trajectories of cognitive assessment, and 0.48 for clinical status. The implementation of a multi-task learning framework enhanced performance by 12.7% for imputing missing values and 14.8% for prediction accuracy. Conclusions:The findings of our study, indicate that multi-task learning can effectively predict the progression of AD. However, it is important to note that the study’s generalizability may be limited due to the restricted dataset and the specific population under examination. These conclusions represent a significant stride toward more precise diagnosis and treatment of this neurological disorder.
