Machine learning based forecast for the prediction of inpatient bed demand

Abstract

Background Overcrowding is a serious problem that impacts the ability to provide optimal level of care in a timely manner. High patient volume is known to increase the boarding time at the emergency department (ED), as well as at post-anesthesia care unit (PACU). Furthermore, the same high volume increases inpatient bed transfer times, which causes delays in elective surgeries, increases the probability of near misses, patient safety incidents, and adverse events. Objective The purpose of this study is to develop a Machine Learning (ML) based strategy to predict weekly forecasts of the inpatient bed demand in order to assist the resource planning for the ED and PACU, resulting in a more efficient utilization. Methods The data utilized included all adult inpatient encounters at Geisinger Medical Center (GMC) for the last 5 years. The variables considered were class of inpatient encounter, observation, or surgical overnight recovery (SORU) at the time of their discharge. The ML based strategy is built using the K-means clustering method and the Support Vector Machine Regression technique (K-SVR). Results The performance obtained by the K-SVR strategy in the retrospective cohort amounts to a mean absolute percentage error (MAPE) that ranges between 0.49 and 4.10% based on the test period. Additionally, results present a reduced variability, which translates into more stable forecasting results. Conclusions The results from this study demonstrate the capacity of ML techniques to forecast inpatient bed demand, particularly using K-SVR. It is expected that the implementation of this model in the workflow of bed capacity management will create efficiencies, which will translate in a more reliable, inexpensive and timely care for patients.

Effective Survival Prediction and Evaluation for Cancer Patients

“…In this context, we want to answer a question concerning "How long?". This situation (including our research objective) primarily concerns the time until the event, making the MAE-PO a proper evaluation metric [40,41]. In some cases of this scenario, predictions are targeted up to a specific time, such as 10 years, without considering or trusting further forecasts.…”

Forecasting ICU Census by Combining Time Series and Survival Models

“…Other papers have attempted to forecast patient census (9,(42)(43)(44)(45)(46). We are not able to directly compare algorithms (e.g., by using another algorithm with our data set) because either the setting is different (e.g., NICU vs ICU) or the independent variables are different.…”

“…Many tools using scoring systems have been proposed to help ICU practitioners predict patient length of stay (LOS) or for benchmarking purposes (7)(8)(9). These rely predominantly on the Acute Physiology and Chronic Health Evaluation score, the Simplified Acute Physiology Score, and the Sequential Organ Function Assessment score (10)(11)(12).…”

Enhancing emergency department patient arrival forecasting: a study using feature engineering and advanced machine learning algorithms

“…More recently, ML algorithms have been employed to overcome limitations of causal and time series models. For example, MLP [3], [27], LSTM [24], [48], KNN [21], [38], XGBoost [5], [45], RF [41], [45], SVR [38], [49], and DNN-based algorithms [7], [46], such as RNNs [5], [24], and CNNs [7], [48], have been reported in studies. In addition to these three groups, hybrid approaches have also been used [5], [21], [24], [27].…”