Effective Analysis of Inpatient Satisfaction: The Random Forest Algorithm

Abstract

Purpose To identify the factors influencing inpatient satisfaction by fitting the optimal discriminant model. Patients and Methods A cross-sectional survey of inpatient satisfaction was conducted with 3888 patients in 16 large public hospitals in Zhejiang Province. Independent variables were screened by single-factor analysis, and the importance of all variables was comprehensively evaluated. The relationship between patients’ overall satisfaction and influencing factors was established, the relative risk was evaluated by marginal benefit, and the optimal model was fitted using the receiver operating characteristic curve. Results Patients’ overall satisfaction was 79.73%. The five most influential factors on inpatient satisfaction, in this order, were: patients’ right to know, timely nursing response, satisfaction with medical staff service, integrity of medical staff, and accuracy of diagnosis. The prediction accuracy of the random forest model was higher than that of the multiple logistic regression and naive Bayesian models. Conclusion Inpatient satisfaction is related to healthcare quality, diagnosis, and treatment process. Rapid identification and active improvement of the factors affecting patient satisfaction can reduce public hospital operating costs and improve patient experiences and the efficiency of health resource allocation. Public hospitals should strengthen the exchange of medical information between doctors and patients, shorten waiting time, and improve the level of medical technology, service attitude, and transparency of information disclosure.

Association between hospital legal constructions and medical disputes: A multi-center analysis of 130 tertiary hospitals in Hunan Province, China

“…Two thousand twenty saw the development of a prediction model to measure patient satisfaction after incorporating sixteen different factors, including location, facility, sex, and age ( 19 ). A study that was conducted in 2021 also developed a prediction model to assess inpatient satisfaction in 16 large public hospitals ( 20 ). These predictive models are a clear and useful resource for clinical decision makers, hospital managers, and healthcare professionals.…”

“…Therefore, our goal was to determine the relationship between hospital legal constructions and medical disputes and to further develop a model to estimate the likelihood of medical disputes specifically among hospital administrators. Due to its individualized forecasts and user-friendly interface, nomogram, which combines multiple variables into a straightforward graphical representation, is frequently utilized in a range of sectors, such as the prediction of patient satisfaction for hospital management (18)(19)(20). Thus, to accurately and individually assess the possibility of encountering medical disputes, particularly among administrators, the prediction model was presented as the format of nomogram.…”

Influencing Factors of Outpatients’ Satisfaction in China a Cross-Sectional Study of 16 Public Tertiary Hospitals

“…Existing studies also show that patients subjectively have expectations of high-level hospitals when choosing a hospital and that patients have a good service experience process that will satisfy them more than the results. 39 While high-level hospitals are generally better than lower-level hospitals in terms of service quality, more attention should be paid to patients' medical experience at the level of tertiary hospitals. And combined with the scores of different social demographic characteristics, it can be seen that women, civil servant/institutional personnel, Postgraduate, Registered category etc.…”

“…Existing research can also show that such groups are more sensitive. 39,40 Therefore, hospital managers and policy makers should shift lower-level medical needs to community medical care to disperse the pressure on hospitals and attach importance to personalized services of high-quality medical care.…”

Machine Learning to Predict the Antimicrobial Activity of Cold Atmospheric Plasma-Activated Liquids

“…Due to their efficient operation on highly dimensional data and their excellent accuracy, RF models are a prominent data analysis tool in research for medical and biomedical applications [85]. RF models are typically applied to highdimensional data sets without a linear relationship between the variables used as inputs and outputs [86]. Because the characterization of the data used in this study is highdimensional and non-linear it is appropriate for the RF model.…”