Association Between Gait Assessed by Intelligent System and Cognitive Function in Silent Cerebrovascular Disease

Overview

This study is a multi-center prospective cohort study. We will continuously recruit subjects with silent cerebrovascular disease aged 60 to 85 years from Shanghai and Guizhou. Data including demographic characteristics, medical history, other concomitant diseases, neurological function assessments, laboratory examinations, imaging examinations, and other clinical data and health economics survey responses will be collected from all subjects. At baseline, all subjects will undergo gait assessment using the intelligent system and cognitive function scale assessment by clinicians. According to the intelligent gait results, the subjects will be divided into normal and abnormal gait groups. All subjects will be observed naturally for 1 year, and all medical behaviors will be recorded. All subjects will be interviewed by telephone for the occurrence of vascular events and changes in medical behaviors at half a year after enrollment and followed up at 1 year after enrollment, including gait evaluation using the intelligent system and cognitive function scale evaluation by clinicians. During the follow-up period, patients can visit the hospital for follow-up at any time when their condition changes.

The neurological function of all subjects was assessed based on the following tests under the guidance of a physician. The timed up-and-go test was used to evaluate the subjects' gait function, requiring them to stand up from their seat and walk straight forward for 3 meters, turn around, walk straight back to the chair, and then sit down again. Using simple cognitive evaluation (Mini-Cognitive Assessment) screening of the subjects' memory and executive function, the participants will first be asked to remember three unrelated words and immediately repeat the three words; they will then be asked to draw a clock marked with the numbers and pointers, and eventually recall the three words. The verbal function of the subjects will be assessed using the verbal retelling items in the MMSE and Montreal Cognitive Assessment, asking the subjects to clearly repeat "44 stone lions," "I only know Zhang Liang came to help today," and "the cat always hid under the sofa when the dog was in the room." Through the camera image data record, the intelligent system uses the built-in intelligent algorithm for intelligent video gait recognition and neural networks based on depth interpretation automation and automatic access to the subjects' gait characteristics (stand-up time, turnaround time, stride length, step velocity, stride length, step width, etc.), language features (pronunciation, intonation, word order, language accuracy, language fluency, etc.), and clock features.