An intelligent algorithm for optimizing emergency department job and patient satisfaction

Area of Science:

• Healthcare Management
• Artificial Intelligence in Medicine
• Patient Safety

Background:

• Emergency departments (EDs) face challenges in balancing operational efficiency with staff and patient satisfaction.
• Resilience engineering principles offer a framework for understanding and improving system robustness in healthcare.
• Job and patient satisfaction are key indicators of ED performance and quality of care.

Purpose of the Study:

• To evaluate and analyze resilience engineering, job satisfaction, and patient satisfaction in a Tehran ED.
• To identify ED strengths, weaknesses, and opportunities for improving safety, performance, and satisfaction.
• To develop an integrated approach for optimizing staff and patient satisfaction using intelligent algorithms.

Main Methods:

• Utilized data envelopment analysis (DEA) and artificial neural networks (multilayer perceptron, radial basis function).
• Integrated resilience engineering (IRE) indicators as inputs and job/patient satisfaction as outputs.
• Employed mean absolute percentage error analysis and sensitivity analysis for indicator identification.

Main Results:

• Salary, wages, patient admission, and discharge were identified as crucial factors influencing satisfaction.
• The developed algorithm effectively measured and analyzed staff and patient satisfaction.
• Results were validated against DEA, demonstrating the algorithm's reliability.

Conclusions:

• The integrated resilience engineering and intelligent algorithm approach provides a novel method for optimizing ED satisfaction.
• This decision-making tool aids health managers in assessing performance and implementing corrective actions.
• The study is the first to integrate IRE, neural networks, and mathematical programming for simultaneous optimization of satisfaction and resilience.