Comparison of multiple linear regression and machine learning methods in predicting cognitive function in older Chinese type 2 diabetes patients

• Published in: BMC neurology Vol. 24; no. 1; p. 11
• Main Authors: Liu, Chi-Hao, Peng, Chung-Hsin, Huang, Li-Ying, Chen, Fang-Yu, Kuo, Chun-Heng, Wu, Chung-Ze, Cheng, Yu-Fang
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 02.01.2024; BioMed Central; BMC
• Subjects: Aged; Aged, 80 and over; Alzheimer's disease; Biochemistry; Blood Glucose; Blood pressure; Body fat; Body mass index; China - epidemiology; Cholesterol; Cognition; Cognition disorders in old age; Cognitive ability; Cognitive function; Comorbidity; Comparative analysis; Complications and side effects; Dementia; Dementia disorders; Demographic aspects; Diabetes; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2 - complications; Diabetes Mellitus, Type 2 - epidemiology; Disease; Fasting; Female; Forecasts and trends; Frailty; Glucose; Hemoglobin; Humans; Insulin resistance; Laboratory testing; Learning algorithms; Linear Models; Machine Learning; Male; Medical records; Medical research; Mental depression; Methods; Middle Aged; Regression analysis; Risk factors; Stochasticity; Type 2 diabetes; Variables; China; Canada; Montreal Quebec Canada; United States > US; Taiwan; Type 2 diabetes; Cognitive function; Machine learning

The prevalence of type 2 diabetes (T2D) has increased dramatically in recent decades, and there are increasing indications that dementia is related to T2D. Previous attempts to analyze such relationships principally relied on traditional multiple linear regression (MLR). However, recently developed...