Multi-modal learning for inpatient length of stay prediction

• Published in: Computers in biology and medicine 2024-03, Vol.171, p.108121, Article 108121
• Main Authors: Chen, Junde, Wen, Yuxin, Pokojovy, Michael, Tseng, Tzu-Liang (Bill), McCaffrey, Peter, Vo, Alexander, Walser, Eric, Moen, Scott
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Chest X-ray images; Classification; Clinical medicine; COVID-19; Critical Care; Data integration; Data-fusion model; Datasets; Electronic health records; Health care industry; Heterogeneity; Hospital costs; Hospitalization; Hospitals; Humans; Information processing; Inpatients; Laboratories; Laboratory tests; Learning; Length of Stay; Length of stay prediction; Long short-term memory; Medical imaging; Medical records; Modal data; Mortality; Multi-modal learning; Neural networks; Pandemics; Prediction models; Predictions; Vital signs
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108121

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS. To address the challenge, this study aims to establish a novel data-fusion model, termed as DF-Mdl, to integrate heterogeneous clinical data for predicting the LoS of inpatients between hospital discharge and admission. Multi-modal data such as demographic data, clinical notes, laboratory test results, and medical images are utilized in our proposed methodology with individual “basic” sub-models separately applied to each different data modality. Specifically, a convolutional neural network (CNN) model, which we termed CRXMDL, is designed for chest X-ray (CXR) image data, two long short-term memory networks are used to extract features from long text data, and a novel attention-embedded 1D convolutional neural network is developed to extract useful information from numerical data. Finally, these basic models are integrated to form a new data-fusion model (DF-Mdl) for inpatient LoS prediction. The proposed method attains the best R2 and EVAR values of 0.6039 and 0.6042 among competitors for the LoS prediction on the Medical Information Mart for Intensive Care (MIMIC)-IV test dataset. Empirical evidence suggests better performance compared with other state-of-the-art (SOTA) methods, which demonstrates the effectiveness and feasibility of the proposed approach. •Combine multiple predictive models using various data modalities.•Attention-embedded 1D convolutional neural network is proposed for LoS prediction.•A customized loss function is used to address LoS data skewness.•LoS prediction task is approached as a regression problem.