Demand Forecasting for Platelet Usage: from Univariate Time Series to Multivariate Models
This research provides improved platelet demand forecasting for blood distribution centers, potentially reducing waste and improving supply chain efficiency for healthcare providers.
This paper addresses the challenge of forecasting platelet demand at Canadian Blood Services (CBS) due to their high cost and short shelf life. The study evaluated ARIMA, Prophet, lasso regression, and LSTM models using a large clinical dataset from 2010-2018, finding that multivariate approaches generally offer the highest accuracy, though simpler time series models like ARIMA suffice with sufficient data.
Platelet products are both expensive and have very short shelf lives. As usage rates for platelets are highly variable, the effective management of platelet demand and supply is very important yet challenging. The primary goal of this paper is to present an efficient forecasting model for platelet demand at Canadian Blood Services (CBS). To accomplish this goal, four different demand forecasting methods, ARIMA (Auto Regressive Moving Average), Prophet, lasso regression (least absolute shrinkage and selection operator) and LSTM (Long Short-Term Memory) networks are utilized and evaluated. We use a large clinical dataset for a centralized blood distribution centre for four hospitals in Hamilton, Ontario, spanning from 2010 to 2018 and consisting of daily platelet transfusions along with information such as the product specifications, the recipients' characteristics, and the recipients' laboratory test results. This study is the first to utilize different methods from statistical time series models to data-driven regression and a machine learning technique for platelet transfusion using clinical predictors and with different amounts of data. We find that the multivariate approaches have the highest accuracy in general, however, if sufficient data are available, a simpler time series approach such as ARIMA appears to be sufficient. We also comment on the approach to choose clinical indicators (inputs) for the multivariate models.