Machine-Based Learning Shifting to Prediction Model of Deteriorative MCI Due to Alzheimer’s Disease - A Two-Year Follow-Up Investigation

作者：Xiaohui Zhao, Haijing Sui, Chengong Yan, Min Zhang, Haihan Song, Xueyuan Liu, Juan Yang · 发表于：Current Alzheimer Research · 年份：2022 · DOI：10.2174/1567205020666221019122049 · 被引用次数：15 · 研究领域：Dementia and Cognitive Impairment Research、Neurological Disease Mechanisms and Treatments、Intracerebral and Subarachnoid Hemorrhage Research

OBJECTIVE: The aim of the present work was to investigate the features of the elderly population aged ≥65 yrs and with deteriorative mild cognitive impairment (MCI) due to Alzheimer's disease (AD) to establish a prediction model. METHODS: A total of 105 patients aged ≥65 yrs and with MCI were followed up, with a collection of 357 features, which were derived from the demographic characteristics, hematological indicators (serum Aβ1-40, Aβ1-42, P-tau and MCP-1 levels, APOE gene), and multimodal brain Magnetic Resonance Imaging (MRI) imaging indicators of 116 brain regions (ADC, FA and CBF values). Cognitive function was followed up for 2 yrs. Based on the Python platform Anaconda, 105 patients were randomly divided into a training set (70%) and a test set (30%) by analyzing all features through a random forest algorithm, and a prediction model was established for the form of rapidly deteriorating MCI. RESULTS: Of the 105 patients enrolled, 41 deteriorated, and 64 did not come within 2 yrs. Model 1 was established based on demographic characteristics, hematological indicators and multi-modal MRI image features, the accuracy of the training set being 100%, the accuracy of the test set 64%, sensitivity 50%, specificity 67%, and AUC 0.72. Model 2 was based on the first five features (APOE4 gene, FA value of left fusiform gyrus, FA value of left inferior temporal gyrus, FA value of left parahippocampal gyrus, ADC value of right calcarine fissure as surrounding cortex), the accuracy ...