Resilience engineering, job satisfaction and patient satisfaction were evaluated and analyzed in one Tehran emergency department (ED) to determine ED strengths, weaknesses and opportunities to improve safety, performance, staff and patient satisfaction. The paper aims to discuss these issues.
The algorithm included data envelopment analysis (DEA), two artificial neural networks: multilayer perceptron and radial basis function. Data were based on integrated resilience engineering (IRE) and satisfaction indicators. IRE indicators are considered inputs and job and patient satisfaction indicators are considered output variables. Methods were based on mean absolute percentage error analysis. Subsequently, the algorithm was employed for measuring staff and patient satisfaction separately. Each indicator is also identified through sensitivity analysis.
The results showed that salary, wage, patient admission and discharge are the crucial factors influencing job and patient satisfaction. The results obtained by the algorithm were validated by comparing them with DEA.
The approach is a decision-making tool that helps health managers to assess and improve performance and take corrective action.
This study presents an IRE and intelligent algorithm for analyzing ED job and patient satisfaction – the first study to present an integrated IRE, neural network and mathematical programming approach for optimizing job and patient satisfaction, which simultaneously optimizes job and patient satisfaction, and IRE. The results are validated by DEA through statistical methods.
