Prospective Validation of Multiweek Inpatient Census Forecasting for Pediatric HSCT and Cellular Therapy

Accurate inpatient census forecasting is important for cell therapy and blood and marrow transplantation (BMT) programs because bed capacity, staffing, and coordination of transplantion care depend on anticipating occupancy several weeks in advance. Forecasting BMT census is challenging because the service combines planned admissions, including scheduled transplantations, with less predictable admissions related to treatment complications. Existing literature has focused on shorter-term prediction, leaving limited evidence for forecasting over the 15- to 30-day horizons most relevant to BMT operational planning. We developed and prospectively validated a component-based model for forecasting pediatric hematopoietic cell transplantation and cellular therapy inpatient census 15 to 30 days in advance. The model decomposed future census into expected admissions and discharges. Admissions forecasts combined known, planned transplantation schedules with predicted, unplanned admissions estimated from historical admission patterns. Discharge probabilities for currently hospitalized patients were estimated using gradient-boosted decision trees. These components were combined to generate daily census forecasts over 15-, 30-, and longer-range horizons. Performance was assessed using mean absolute percentage error (MAPE) and root mean squared error (RMSE). The model performed well across clinically relevant forecast horizons, achieving MAPE of 13% at 15 days and 16% at 30 days. Performance remained stable in prospective validation, confirming feasibility of routine operational forecasting and reducing concern for retrospective information leakage. These findings demonstrate that accurate 15- to 30-day inpatient census forecasting for pediatric hematopoietic stem cell transplantation (HSCT) and cellular therapy programs is achievable when models are integrated with transplantion operational data and aligned with the mechanisms that drive occupancy. This framework can support more reliable capacity planning for HSCT and cellular therapy programs and may be adaptable to other complex inpatient services with both planned and unplanned utilization.