Performance assessment and improvement of a care unit for COVID-19 patients with resilience engineering and motivational factors: An artificial neural network method

Abstract

The global conflict with the new coronavirus disease (COVID-19) has led to frequent visits to hospitals and medical centers. This significant increase in visits can be severely detrimental to the body of the healthcare system and society if the physical space and hospital staff are not prepared. Given the significance of this issue, this study investigated the performance of a hospital COVID-19 care unit (COCU) in terms of the resilience and motivation of healthcare providers. This paper used a combination of artificial neural networks and statistical methods, in which resilience engineering (RE) and work motivational factors (WMF) were the input and output data of the network, respectively. To collect the required data, we asked the COCU staff to complete a standard questionnaire, after which the best neural network configuration was determined. According to each indicator, sensitivity analysis and statistical tests were performed to evaluate the center's performance. The results indicated that the COCU had the best and worst performance with respect to self-organization and teamwork indicators, respectively. A data envelopment analysis (DEA) method was also used to validate the algorithm, and the SWOT (strengths, weaknesses, opportunities, threats) matrix was eventually presented to recommend appropriate strategies and improve the performance of the studied COCU.

Keywords: Artificial neural network; COVID-19; Data envelopment analysis; Job satisfaction; Performance evaluation; Resilience engineering.