Data-driven decision-support for process improvement through predictions of bed occupancy rates

• Main Authors: TAN, Kar Way, NG, Qi You, NGUYEN, Francis Ngoc Hoang Long, LAM, Sean Shao Wei
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: process improvement; predictive analytics; heterogeneous data; Computer Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/4718
• Institution: Singapore Management University

Duplicate record, see https://ink.library.smu.edu.sg/sis_research/4684/. Managing bed utilization and ensuring the supply keeps up with the demand is not an easy task in a large public hospital with many medical disciplines. The bed managers who makes decisions on reserving and allocating beds centrally require high-dimensional data from several hospital information systems supporting emergency room, specialized clinics and bed management processes. In this work, we put together an automated process for cleaning, consolidating and integrating data from several hospital information systems to several reports required by the bed managers to analyse the bed occupancy situations across more than thirty medical disciplines. To prevent bed crunch situations when patients wait more than ten hours for beds, we also built two predictive models based on the high-dimension data which provide the hospital with the foreknowledge of the bed occupancy. Our aim was to move the hospital from reactive mode to proactive bed management. Our analytics solution focuses on consistent and accurate reporting, co-created with the bed management users, and approach enables business-as-usual for seamlessly transition towards proactive processes in the daily bed management decision-making. The solution was implemented in a large public general hospital in Asia. The solution provides high value to stakeholders in hospital by reducing the time taken to get the information on hand for decision-making from at least four days to at most half a day. The prediction model for bed occupancy rate achieved 80% accuracy (at an error tolerance of 5%). We hope our results will encourage and benefit hospitals with a similar setting to adopt data-driven methods to tackle high bed occupancy situations in their premises.