Analysis of Value Dimensions in Public Satisfaction with Primary Health Care: Prospective Observational Study

Abstract

Background. Artificial neural network models can be used to analyze and predict structural components within the value dimension of the main processes in an outpatient clinic as indicators of patient satisfaction.Objective — to form and test the methodology for analyzing and predicting structural components within the value dimension of the main processes in an outpatient clinic, as indicators of patient satisfaction with availability and quality of medical care, using artificial intelligence.Methods. The results of questionnaires administered to 525 patients were used to analyze their satisfaction with GP appointments. A network ensemble consisting of radial basis network and multilayer perceptron was chosen as the basis for a neural network model. The model testing involved five outpatient clinics in Kirov. The total number of respondents comprised 217 patients. Statistical processing included data description and analysis. Qualitative attributes were represented by relative values (P, %). The statistical significance of differences in qualitative data was assessed using the Chi-square test. The correlation between the observed and predicted data was assessed by means of nonparametric Spearman correlation analysis. The value of p <0.05 was chosen as the significance level ( p). Statistical data processing was performed using Statistica 13.0.Results. Analysis of the value dimensions of satisfaction showed a predominance of “pre-appointment” stage: work of a registrar (85.29% significance in the receiving medical services), waiting time for an appointment with a doctor (66.76% respondents noted its significance), duration of waiting directly at the office (important for 69.11% of respondents). “Appointment” stage was formed according to the common procedure of a GP appointment (interview, examination, recommendations) and was assessed from the value perspective of the patient. The priority components included sufficiency of appointment duration (significant in 88.27% of cases), satisfaction with examination (significant in 85.14% of cases), as well as completeness and informativeness of consultation (significant in 89.9% of cases). A strong direct correlation between the observed and predicted data (ρxy = 0.9; p < 0.05) was found out. Statistically significant differences between the observed and predicted levels of general patient satisfaction were not revealed in all medical organizations.Conclusion. The suggested neural network models can be used as the basis when creating information management systems that monitor meeting the effectiveness criteria for a new model of a medical organization; as well as an essential support for administrative decisions related to organizing the optimal patient management.