Integrating Learning Algorithms for Efficient Hospital Maintenance

The significance of keeping the hospital buildings in a completely functional state has been acknowledged by the recent worldwide spread of COVID-19, where hospitals are playing a vital role in ensuring the population's safety and wellbeing. This necessitates an efficient maintenance management mechanism for all hospital building components in order to reduce possible downtimes pertaining to asset failures. Accordingly, the current study presents an assessment framework for hospital building assets where their relative criticality and performance levels are evaluated on a Neutrosophic ANP basis, followed by the derivation of their corresponding priority level using an automated Decision Tree model. The developed model was validated by testing the relative level of agreeability between the model-predicted values and the actual values derived by inspectors using historical records from 3 hospital case studies, and the performance of the model exceeded 90% which verifies its capability in predicting a suitable priority level for hospital building assets.