Abstract: Objective: To establish the prediction model of the acceptance of smart care for the elderly in the community based on the Unified Theory of Acceptance and Use of Technology, and provide reference for predicting the acceptance of smart care for elderly people. Methods: From May to December 2022, a total of 1031 elderly from 4 communities in Beijing, the Community Health Service Center of Shandong provincial Third Hospital and the Community Health Service Center of Liaocheng were recruited. Data were collected using a general information questionnaire, a questionnaire on influencing factors of the acceptance of smart care for the elderly, and Technophobia Scale. The variables were screened by LASSO regression, and the sample was randomly divided into training group (n=723) and test group (n=308) according to the ratio of 7:3. A decision tree model was established in the training group, and the accuracy, sensitivity, specificity and Receiver Operating Characteristic (ROC) curve were used to test the model in the test group. Results: Performance expectancy, effort expectancy, social factors, occupation, health management needs, and experience in using smart elderly care products were the influencing factors of the acceptance of smart care for the elderly in the community. The depth of the decision tree containing 7 layers and a total of 10 leaf nodes. The accuracy, sensitivity, specificity and AUC of the decision tree were 80.2%, 80.2%, 77.7% and 0.812. Conclusion: The decision tree of the acceptance of smart care for the elderly in the community has good prediction efficiency, which can provide scientific guidance for evaluating and promoting the acceptance of smart care for the elderly.

Key words: smart care for the elderly; acceptance; decision tree; Unified Theory of Acceptance and Use of Technology; community-dwelling elderly