RESUMEN
BACKGROUND: Predicting the bed occupancy rate (BOR) is essential for efficient hospital resource management, long-term budget planning, and patient care planning. Although macro-level BOR prediction for the entire hospital is crucial, predicting occupancy at a detailed level, such as specific wards and rooms, is more practical and useful for hospital scheduling. OBJECTIVE: The aim of this study was to develop a web-based support tool that allows hospital administrators to grasp the BOR for each ward and room according to different time periods. METHODS: We trained time-series models based on long short-term memory (LSTM) using individual bed data aggregated hourly each day to predict the BOR for each ward and room in the hospital. Ward training involved 2 models with 7- and 30-day time windows, and room training involved models with 3- and 7-day time windows for shorter-term planning. To further improve prediction performance, we added 2 models trained by concatenating dynamic data with static data representing room-specific details. RESULTS: We confirmed the results of a total of 12 models using bidirectional long short-term memory (Bi-LSTM) and LSTM, and the model based on Bi-LSTM showed better performance. The ward-level prediction model had a mean absolute error (MAE) of 0.067, mean square error (MSE) of 0.009, root mean square error (RMSE) of 0.094, and R2 score of 0.544. Among the room-level prediction models, the model that combined static data exhibited superior performance, with a MAE of 0.129, MSE of 0.050, RMSE of 0.227, and R2 score of 0.600. Model results can be displayed on an electronic dashboard for easy access via the web. CONCLUSIONS: We have proposed predictive BOR models for individual wards and rooms that demonstrate high performance. The results can be visualized through a web-based dashboard, aiding hospital administrators in bed operation planning. This contributes to resource optimization and the reduction of hospital resource use.
RESUMEN
This paper presents a novel principle for intraocular pressure (IOP)-sensing (monitoring) based on a pressure-sensitive soft composite in which a dual optical signal is produced in response to impulsive pressure input. For the initial assessment of the new IOP sensing principle, a human eye is modeled as the spherically shaped shell structure filled with the pressurized fluid, including cornea, sclera, lens and zonular fiber, and a fluid-structure interaction (FSI) analysis was performed to determine the correlation between the internal pressure and deformation (i.e., strain) rate of the spherical shell structure filled with fluid by formulating the finite element model. The FSI analysis results for human eye model are experimentally validated using a proof-of-conceptual experimental model consisting of a pressurized spherical shell structure filled with fluid and a simple air-puff actuation system. In this study, a mechanoluminescent ZnS:Cu- polydimethylsiloxane (PDMS)-based soft composite is fabricated and used to generate the dual optical signal because mechanically driven ZnS:Cu/PDMS soft composite can emit strong luminescence, suitable for soft sensor applications. Similar to the corneal behavior of the human eye, inward and outward deformations occur on the soft composite attached to the spherical shell structure in response to air puffing, resulting in a dual optical signal in the mechnoluminescence (ML) soft composite.
