Abstract
Healthcare facilities are constantly deteriorating due to tight budgets allocated to the upkeep of building assets. This entails the need for improved deterioration modeling of such buildings in order to enforce a predictive maintenance approach that decreases the unexpected occurrence of failures and the corresponding downtime elapsed to repair or replace the faulty asset components. Currently, hospitals utilize subjective deterioration prediction methodologies that mostly rely on age as the sole indicator of degradation to forecast the useful lives of the building components. Thus, this paper aims at formulating a more efficient stochastic deterioration prediction model that integrates the latest observed condition into the forecasting procedure to overcome the subjectivity and uncertainties associated with the currently employed methods. This is achieved by means of developing a hybrid genetic algorithm-based fuzzy Markovian model that simulates the deterioration process given the scarcity of available data demonstrating the condition assessment and evaluation for such critical facilities. A nonhomogeneous transition probability matrix (TPM) based on fuzzy membership functions representing the condition, age and relative deterioration rate of the hospital systems is utilized to address the inherited uncertainties. The TPM is further calibrated by means of a genetic algorithm to circumvent the drawbacks of the expert-based models. A sensitivity analysis was carried out to analyze the possible changes in the output resulting from predefined modifications to the input parameters in order to ensure the robustness of the model. The performance of the deterioration prediction model developed is then validated through a comparison with a state-of-art stochastic model in contrast to real hospital datasets, and the results obtained from the developed model significantly outperformed the long-established Weibull distribution-based deterioration prediction methodology with mean absolute errors of 1.405 and 9.852, respectively. Therefore, the developed model is expected to assist decision-makers in creating more efficient maintenance programs as well as more data-driven capital renewal plans.
Highlights
Aging healthcare facilities often experience complications regarding the estimation and quantification of the probable deterioration within asset components due to a number of reasons.First, the scarcity of condition assessments and rating data made available for research and analysis purposes imposes a difficulty in producing more relatable models and frameworks to the actual hospital building environments, and obscures the process of making rational renewal decisions [1]
Separate matrices were initiated for every age group available for the oxygen gas systems to allow for a distinction between their behavioral changes demonstrated by the transition probabilities of the system condition levels from each initial condition level to the lower condition
The model validation procedure is implemented by using Equations (10)–(12) applied to the validation set of hospital condition ratings and inspection records to measure the performance of the Weibull distribution-based deterioration against the proposed fuzzy genetic algorithm (GA)-based Markov model and their respective capabilities to predict and model the actual deterioration attainable in a real healthcare facility setting
Summary
Aging healthcare facilities often experience complications regarding the estimation and quantification of the probable deterioration within asset components due to a number of reasons.First, the scarcity of condition assessments and rating data made available for research and analysis purposes imposes a difficulty in producing more relatable models and frameworks to the actual hospital building environments, and obscures the process of making rational renewal decisions [1]. Algorithms 2020, 13, 210 or delayed due to the dynamic nature of healthcare environments, the high cost associated with performing such activities as well as the shortage in nonmedical-related funding allowances, which in turn contribute to unexpected asset failures that end up costing the hospital extensive amounts of time and funding necessary to reactively respond to the occurring failures as opposed to the original values required to proactively upkeep the assets [2] This entails the need for formulating a more efficient deterioration model and prediction framework that represent the actual condition progression of assets within healthcare facilities over time to aid decision-makers in achieving more sound maintenance and renewal verdicts [3]. This is mainly achieved by involving experts and trained personnel to evaluate the condition and performance levels achieved by building assets over a certain planning horizon [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
