Efficient hospital resource allocation is a persistent operational challenge because demand for beds, staff, equipment, diagnostics, and patient movement changes rapidly. Predictive analytics offers a way to anticipate demand and support more proactive operational decisions. This systematic review synthesised machine learning models applied to hospital resource allocation from 2017 to 2023. The review focused on bed management, staffing demand, equipment use, diagnostic capacity, and patient throughput. A PRISMA 2020-compliant review process was used, including structured searches of PubMed, Scopus, IEEE Xplore, and Web of Science. Screening, extraction, risk-of-bias assessment, and narrative synthesis were conducted to compare model targets, data sources, validation approaches, and implementation maturity. The evidence base was dominated by retrospective studies of patient throughput, emergency department admission prediction, bed demand, and length of stay. Staffing, equipment, and diagnostic capacity forecasting were less frequently represented, while integrated multi-resource command centre models remained uncommon. Machine learning for hospital resource allocation has become technically advanced, but operational translation remains uneven. Most models remained retrospective or locally validated, with limited evidence of prospective deployment, workflow integration, or measurable operational impact.
Emergency admissions frequently wait for inpatient bed placement when hospital capacity, infection control needs, staffing limitations, and specialty-bed requirements collide. These delays can prolong emergency department boarding and disrupt hospital-wide patient flow. Current bed management is often reactive, relying on bed coordinators, charge nurses, manual communication, and local escalation routines. Without a prospective warning system, teams may recognize an impending placement delay only after the admission queue has already stalled. The objective is to develop a machine learning model that predicts, at the time of admission decision, whether a patient is likely to experience delayed placement beyond a defined operational threshold. The model would use bed assignment logs, isolation requirements, unit census, nurse staffing levels, and specialty service availability as core predictors. A supervised classification model based on gradient-boosted trees would be trained on historical emergency admissions and linked operational data. The model would generate a placement delay risk score that can be refreshed as bed status, staffing, and unit conditions change. Conceptually, the model would identify admissions at elevated risk for delayed placement and attribute risk to operational constraints such as limited isolation rooms, high census, low staffing, or unavailable specialty beds. These explanations would give bed managers lead time to intervene before the delay becomes entrenched. This predictive model could shift hospital bed management from a reactive queue-based process to proactive, data-driven placement coordination. It would support earlier escalation, more targeted resource allocation, and improved alignment between emergency admissions and inpatient capacity.