Early Intensive Care Unit Length of Stay Prediction on MIMIC-IV: A Dual Approach With Clinical Features and Textual Notes

基于MIMIC-IV的早期重症监护病房住院时长预测:结合临床特征和文字记录的双重方法

阅读:2

Abstract

Predicting intensive care unit (ICU) length of stay (LOS) within the first 24 h of admission can improve bed management, staffing and care planning. While prior studies have used structured electronic health record (EHR) data, including demographics, vitals, labs and ICD codes, recent advances in transformer-based language models enable the use of unstructured clinical notes. In this study, we compare structured and unstructured modelling approaches for early ICU LOS prediction within a unified experimental framework. We developed two parallel pipelines using MIMIC-IV data: (1) a structured pipeline using conventional machine learning models (logistic regression, random forest, XGBoost and SVM) trained on day-one EHR features with ICD-derived embeddings and (2) an unstructured pipeline fine-tuning transformers (ClinicalBERT, Bio+ClinicalBERT and BlueBERT) on discharge notes. We evaluated binary classification (short [  ≤ 4 days] vs. long [  >  4 days] stay) and regression of exact LOS in days. Our results show XGBoost with ICD embeddings achieved the best results (AUROC = 0.805) with minimal training time; XGBoost without ICD embeddings still achieved strong performance (AUROC = 0.732), providing a baseline without delayed codes. Transformer models performed comparably (AUROC = 0.766) but required more computation. Overall, both pipelines offer valuable early signals, but differ in efficiency and integration, highlighting trade-offs.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。