A smart model for hospital performance evaluation based on balanced scorecard approach and machine learning

Articles in Press

Authors

1 Department of Industrial Engineering, Alborz Campus, University of Tehran, Tehran, Iran

2 School of Industrial Engineering, College of Engineering, University of Tehran

3 UniversSchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iranity of Tehran

10.22059/aie.2026.409978.1967

Abstract

Performance evaluation in complex service systems is a central concern in industrial engineering, particularly in regulated environments such as healthcare. This study develops a data-driven industrial engineering framework for hospital performance evaluation structured through the Balanced Scorecard (BSC) and supported by exploratory predictive modelling. A structured evidence-based screening process was conducted to identify operationally measurable performance indicators, which were subsequently organised within the four BSC perspectives and aggregated into composite performance dimensions using standardised equal-weight scoring. Quarterly organisational data (2018–2024) from a tertiary hospital were used to examine structural relationships among indicators through a multilayer perceptron neural network. The predictive component is intended as exploratory validation rather than universal forecasting. Results indicate strong alignment between predicted and observed composite performance scores (R = 0.84), suggesting that the selected indicators collectively explain substantial variation within the studied organisational context. Importance and sensitivity analyses further identify cost-efficiency and operational-process variables as influential drivers, while safety, workforce, and patient-related indicators demonstrate meaningful associations. The proposed framework enhances transparency in indicator selection, clarifies multidimensional performance structuring, and provides analytically informed decision support for complex service systems.

Keywords

Main Subjects

Advances in Industrial Engineering

Articles in Press, Accepted Manuscript
Available Online from 15 March 2026

Files

Share

How to cite

Statistics