StayLTC: A Cost-Effective Multimodal Framework for Hospital Length of Stay Forecasting
This addresses resource management in healthcare, but it is incremental as it applies an existing neural network type to a known problem.
The paper tackled hospital length of stay prediction by developing StayLTC, a multimodal framework using Liquid Time-Constant Networks, which outperformed most time series models on the MIMIC-III dataset and matched large language models with less computational cost.
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.