Leveraging Machine Learning to Predict Hospital Porter Task Completion Time

Porters play a crucial role in hospitals because they ensure the efficient transportation of patients, medical equipment, and vital documents. Despite its importance, there is a lack of research addressing the prediction of completion times for porter tasks. To address this gap, we utilized real-world porter delivery data from National Taiwan University Hospital, Yunlin Branch, Taiwan. We first identified key features that can influence the duration of porter tasks. We then employed three widely-used machine learning algorithms: decision tree, random forest, and gradient boosting. To leverage the strengths of each algorithm, we finally adopted an ensemble modeling approach that aggregates their individual predictions. Our experimental results show that the proposed ensemble model can achieve a mean absolute error of 3 min in predicting task response time and 4.42 min in task completion time. The prediction error is around 50% lower compared to using only the historical average. These results demonstrate that our method significantly improves the accuracy of porter task time prediction, supporting better resource planning and patient care. It helps ward staff streamline workflows by reducing delays, enables porter managers to allocate resources more effectively, and shortens patient waiting times, contributing to a better care experience.