Patient no-show behavior is a critical factor complicating hospital resource optimization and causing waste. The inefficiency caused by patients' no-shows and the resulting increased operating costs negatively affect the hospitals' financial structure and service quality. For this reason, health managers must make accurate predictions about whether patients will attend an appointment and plan the appointment system within the framework of these predictions. This research aims to optimize the hospital appointment system by making accurate predictions regarding the no-show behavior of the patients, based on recorded data. An artificial intelligence-based appointment system has been developed according to patients' demographics and past behavior patterns. The forecast results and realized performance results were compared. The artificial intelligence we have developed continuously improves appointment assignments by learning from past and current data. According to the findings, the artificial intelligence-based appointment system increased the rate of patients attending appointments by 10% per month. Likewise, the hospital capacity utilization rate increased by 6%. Findings from the study confirmed that no-show risks could be managed in the appointment process through artificial intelligence. This artificial intelligence-based design for appointment systems significantly decreases hospital costs and improves service quality performance.
Read full abstract