Evaluating the quality of home care in community health service centres: A machine learning approach.

Autor: Xia Q; School of Nursing, Xuzhou Medical University, Xuzhou, Jiangsu, China., Huang Q; School of Nursing, Fujian Medical University, Fuzhou, Fujian, China., Li J; School of Nursing, Xuzhou Medical University, Xuzhou, Jiangsu, China., Xu Y; School of Nursing, Xuzhou Medical University, Xuzhou, Jiangsu, China.; Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China., Ge S; Department of Natural Sciences, University of Houston-Downtown, Houston, Texas, USA., Zhang X; School of Information & Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, China., Li M; The People's Hospital of Pizhou, Xuzhou, Jiangsu, China., Yu D; The People's Hospital of Pizhou, Xuzhou, Jiangsu, China., Tang X; School of Nursing, Xuzhou Medical University, Xuzhou, Jiangsu, China., Xia Y; School of Nursing, Xuzhou Medical University, Xuzhou, Jiangsu, China.
Jazyk: angličtina
Zdroj: Journal of advanced nursing [J Adv Nurs] 2024 May 29. Date of Electronic Publication: 2024 May 29.
DOI: 10.1111/jan.16234
Abstrakt: Aims: The aim of the study is to develop a model using a machine learning approach that can effectively identify the quality of home care in communities.
Design: A cross-sectional design.
Methods: In this study, we evaluated the quality of home care in 170 community health service centres between October 2022 and February 2023. The Home Care Service Quality Questionnaire was used to collect information on home care structure, process and outcome quality. Then, an intelligent and comprehensive evaluation model was developed using a convolutional neural network, and its performance was compared with random forest and logistic regression models through various performance indicators.
Results: The convolutional neural network model was built upon seven variables, which encompassed the qualification of home nursing staff, developing and practicing emergency plan to cope with different emergency rescues in home environment, being equipped with medication and supplies for first aid according to specific situations, assessing nutrition condition of home patients, allocation of the number of home nursing staff, cases of new pressure ulcers and patient satisfaction rate. Remarkably, the convolutional neural network model demonstrated superior performance, outperforming both the random forest and regression models.
Conclusion: The successful development and application of the convolutional neural network model highlight its ability to leverage data from community health service centres for rapid and accurate grading of home care quality. This research points the way to home care quality improvement.
Impact: The model proposed in this study, coupled with the aforementioned factors, is expected to enhance the accuracy and efficiency of a comprehensive evaluation of home care quality. It will also help managers to take purposeful measures to improve the quality of home care.
Reporting Method: The reporting of this study (Observational, cross-sectional study) conforms to the STROBE statement.
Patient or Public Contribution: No patient or public contribution.
Implications for the Profession And/or Patient Care: The application of this model has the potential to contribute to the advancement of high-quality home care, particularly in lower-middle-income communities.
(© 2024 John Wiley & Sons Ltd.)
Databáze: MEDLINE
Externí odkaz: