Accurate prediction of Length of Stay (LOS) in hospitals is crucial for improving healthcare services, resource management, and cost efficiency. This paper presents StayLTC, a multimodal deep learning framework developed to forecast real-time hospital LOS using Liquid Time-Constant Networks (LTCs). LTCs, with their continuous-time recurrent dynamics, are evaluated against traditional models using structured data from Electronic Health Records (EHRs) and clinical notes. Our evaluation, conducted on the MIMIC-III dataset, demonstrated that LTCs significantly outperform most of the other time series models, offering enhanced accuracy, robustness, and efficiency in resource utilization. Additionally, LTCs demonstrate a comparable performance in LOS prediction compared to time series large language models, while requiring significantly less computational power and memory, underscoring their potential to advance Natural Language Processing (NLP) tasks in healthcare.

Predicting hospital length of stay (LOS) reliably is an essential need for efficient resource allocation at hospitals. Traditional predictive modeling tools frequently have difficulty acquiring sufficient and diverse data because healthcare institutions have privacy rules in place. In our study, we modeled this problem as an empirical graph where nodes are the hospitals. This modeling approach facilitates collaborative model training by modeling decentralized data sources from different hospitals without extracting sensitive data outside of hospitals. A local model is trained on a node (hospital) by aiming the generalized total variation minimization (GTVMin). Moreover, we implemented and compared two different federated learning optimization algorithms named federated stochastic gradient descent (FedSGD) and federated averaging (FedAVG). Our results show that federated learning enables accurate prediction of hospital LOS while addressing privacy concerns without extracting data outside healthcare institutions.

Recognizing the need to support shorter lengths of stay, Dr. John Fahrenbach, a data scientist at the University of Chicago Medicine (UCM), developed a machine learning model that used clinical characteristics to identify patients most suitable for discharge after 48 hours. Using this tool, the hospital could ensure the timely release of specific patients by allocating and prioritizing care management resources, including discharge planning, home health services, and clinician or patient administrative assistance. During the development process, Dr. Fahrenbach's team determined that including zip codes as a feature increased the model's predictive accuracy. After introducing zip codes into the model, however, a team member who reviewed the output raised concerns. "We know Chicago's patient population and knew something was off when stratifying the model by race," said Dr. Fahrenbach.

Last week, my Microsoft colleagues Bharath Sankaranarayan and Carl Saroufim presented a live webinar showing how you can predict a patient's length of stay at a hospital using SQL Server R Services. The recorded webinar is available for on-demand viewing now. The webinar is based on the Machine Learning Solution Template Predicting Length of Stay in Hospitals, which we covered here on the blog back in March. The solution is based on an instance of the Data Science Virtual Machine, which makes it easy to try it yourself. Just click the "Deploy" button to create your own instance in Azure with all of the data and scripts preloaded.

Length of Stay (LOS) is a critical factor in managing hospital quality & economic outcomes in Healthcare. The metric is calculated by summing the total number of days for all discharges & dividing it by the total number of discharges. Insurance programs such as Medicare are moving to a model where they are compensating Hospitals the same amount for a specific surgery (e.g. Joint replacement) regardless of the number of days spent in the hospital. Therefore, hospitals & the overall healthcare ecosystem are motivated to reduce LOS.