A Study on Validation of Gait Analysis Wireless Small Inertial Sensor and Diagnostic Machine Learning Model for Classification of Elderly Fall Risk Group
A Study on Validation of Gait Analysis Wireless Small Inertial Sensor and Diagnostic Machine Learning Model for Classification of Elderly Fall Risk Group
The walking status of elderly patients over 65 years of age in the hospital will be verified through political analysis and objective fall risk assessment through wireless inertial sensors and diagnostic machine learning models, and based on the results, As investigators, providing a foundation for the objective evaluation of the risk of falling patients by nurses in general wards in the future.
Currently, in the case of general clinical wards in Korea, the evaluator who assesses the risk of falling during the patient's hospitalization changes every time, and the evaluation of fall risk differs for the same patient depending on the subjectivity of the evaluator. Hence, evaluating falls requires assessing the patient's walking based on consistent criteria. Through walking analysis with a wireless small inertial sensor, there is an expectation that the incidence of fall risk will decrease. When analyzing walking to classify fall risk groups, quantitative evaluation should be applied for stride length, gait speed, step width, cadence, and gait cycle, but currently, fall assessments taking this into account are not properly conducted. Therefore, it is necessary to prepare and apply quantitative standards for fall evaluation through walking analysis through wireless small inertial sensors and data machine learning to classify the risk of falling in elderly hospitalized patients.
Inclusion Criteria:
Exclusion Criteria: