Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV

TL;DR

This study benchmarks classical machine learning and neural network models for predicting ICU length of stay in neurological patients using MIMIC-IV data, providing insights into their effectiveness for ICU resource management.

Contribution

It is the first ML-based study specifically predicting ICU LOS for neurological patients, comparing multiple models including classic ML and neural networks.

Findings

Random Forest achieved 0.68 accuracy on static data.

BERT outperformed LSTM with 0.80 accuracy on time-series data.

Models show potential for improving ICU resource planning.

Abstract

Intensive care unit (ICU) is a crucial hospital department that handles life-threatening cases. Nowadays machine learning (ML) is being leveraged in healthcare ubiquitously. In recent years, management of ICU became one of the most significant parts of the hospital functionality (largely but not only due to the worldwide COVID-19 pandemic). This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset. The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer). Given that LOS prediction is often framed as a classification task, this study categorizes LOS into three groups: less than two days, less than a week, and a week or more. As the first ML-based approach targeting LOS prediction for neurological disorder patients, this study does not aim to outperform existing methods but rather to assess their effectiveness in this specific context. The findings provide insights into the applicability of ML techniques for improving ICU resource management and patient care. According to the results, Random Forest model proved to outperform others on static, achieving an accuracy of 0.68, a precision of 0.68, a recall of 0.68, and F1-score of 0.67. While BERT model outperformed LSTM model on time-series data with an accuracy of 0.80, a precision of 0.80, a recall of 0.80 and F1-score 0.80.