Ligan Jia’s research while affiliated with Xinjiang University and other places

Background Hip fracture (HF) is one of the most prevalent orthopedic conditions among the elderly, with falls being the primary risk factor for HF. With the surge of aged population, China is facing great challenges from HF and falls. However, a comprehensive long-term observation of risk factors affecting HF and falls and their association are little reported at a national level. Methods The longitudinal cohort was established using the China Health and Retirement Longitudinal Study (CHARLS) data from 2011 to 2018. The incidence density and multi-risk-stratified lifetime risk (up to 90 years of age) of falls and HF were studied at index ages of 50, 60, and 70, as well as the lifetime risk stratified by six regions in China, based on the modified Kaplan–Meier method with Statistical Analysis System (SAS). Results This study identified 17 705 subjects aged 50–89. The incidence density of falls was 65.07 and 47.53 per 1000 person-years in women and men, respectively. The incidence density of HF was also higher in women at 5.58 per 1000 person-years than in men at 4.88. By age 50, the lifetime risk of experiencing a HF was 18.58 % for women and 13.72 % for men. Vision and hearing abilities were significantly related to the lifetime risk of both falls and HF. Obesity-related factors presented age-relevant relationships with lifelong risks. Lack of naps, poor lower limb strength, and physical capabilities were indicative of HF risk. The north-western region of China had the lowest lifetime risk of falls but highest risk of HF, while other regions showed a consistent trend between falls and HF. Conclusion The aging population worldwide faces a considerable risk of falls and HF. Several risk factors were identified in this study using a Chinese population, relating to disease history, lifestyle habits, health status and physical function, and the risks differed among six regions in China. Future precautionary management programs, as well as patient self-awareness are necessary for improving the prevention of falls and HF to reduce their incidence in the aging population. The translational potential of this article With the greatest aged population worldwide, China faces the unparalleled challenge on public health. The study poses the lifetime risk of hip fracture and falls stratified by multiple risk factors in people from 45 to 90 in a national scale, which would shed a light on the early and continuous prevention of such injury.

Objective To use routine demographic and clinical data to develop an interpretable individual-level machine learning (ML) model to diagnose knee osteoarthritis (KOA) and to identify highly ranked features. Methods In this retrospective, population-based cohort study, anonymized questionnaire data was retrieved from the Wu Chuan KOA Study, Inner Mongolia, China. After feature selections, participants were divided in a 7:3 ratio into training and test sets. Class balancing was applied to the training set for data augmentation. Four ML classifiers were compared by cross-validation within the training set and their performance was further analyzed with an unseen test set. Classifications were evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the curve(AUC), G-means, and F1 scores. The best model was explained using Shapley values to extract highly ranked features. Results A total of 1188 participants were investigated in this study, among whom 26.3% were diagnosed with KOA. Comparatively, XGBoost with Boruta exhibited the highest classification performance among the four models, with an AUC of 0.758, G-means of 0.800, and F1 scores of 0.703. The SHAP method reveals the top 17 features of KOA according to the importance ranking, and the average of the experience of joint pain was recognized as the most important features. Conclusions Our study highlights the usefulness of machine learning in unveiling important factors that influence the diagnosis of KOA to guide new prevention strategies. Further work is needed to validate this approach.