Identifying factors associated with locomotive syndrome using machine learning methods: The third survey of the research on osteoarthritis/osteoporosis against disability study.

AIM: To identify factors associated with locomotive syndrome (LS) using medical questionnaire data and machine learning.

METHODS

A total of 1575 participants underwent the LS risk tests from the third survey of the research on osteoarthritis/osteoporosis against disability study (ROAD) study. LS was defined as stage 1 or higher based on clinical decision limits of the Japanese Orthopaedic Association. A total of 1335 items of medical questionnaire data came from this study. The number of medical questionnaire items was reduced from 1335 to 331 in data cleaning. From the 331 items, identify factors associated with LS use by light gradient boosting machine-based recursive feature elimination with cross-validation. The performance of each set was evaluated using an average of seven performance metrics, including 95% confidence intervals, using a bootstrapping method. The smallest set of items is determined with the highest average of receiver operating characteristic area under the curve (ROC-AUC) under 20 items as association factors of LS. Additionally, the performance of the selected items was compared with the LS risk tests and Loco-check.

RESULTS

The nine items have the best average ROC-AUC under 20 items. The nine items show an average ROC-AUC of 0.858 (95% confidence interval 0.816-0.898). Age and back pain during walking were strongly associated with the prevalence of LS. The ROC-AUC of nine items is higher than that of existing questionnaire-based LS assessments, including the 25-question Geriatric Locomotor Scale and Loco-check.

CONCLUSIONS

The identified nine items could aid early LS detection, enhancing understanding and prevention. Geriatr Gerontol Int 2024; 24: 806-813.