Combining principal component analysis and logistic regression for multifactorial fall risk prediction among community-dwelling older adults

•Developed a framework combining PCA and logistic regression to predict fall risks in older adults.•Selected hospitalization due to falls as outcome measure for model development.•PCA with full variables showed best prediction performance (AUC=0.78, sensitivity=74 %).•Provided practical suggestions for community health promotion and fall prevention.•Compared feature selection between traditional statistics and machine learning. Falls require comprehensive assessment in older adults due to their diverse risk factors. This study aimed to develop an effective fall risk prediction model for community-dwelling older adults by integrating principal component analysis (PCA) with machine learning. Data were collected for 45 fall-related variables from 1630 older adults in Taiwan, and models were developed using PCA and logistic regression. The optimal model, PCA with stepwise logistic regression, had an area under the receiver operating characteristic curve of 0.78, sensitivity of 74 %, specificity of 70 %, and accuracy of 71 %. While dimensionality reduction via PCA is not essential, it aids practicality. Our framework combines PCA and logistic regression, providing a reliable method for fall risk prediction to support consistent screening and targeted health promotion. The key innovation is using PCA prior to logistic regression, overcoming conventional limitations. This offers an effective community-based fall screening tool for older adults.