Prediction of mortality and resource utilization in critical care: a deep learning approach using multimodal electronic health records with natural language processing techniques

2025-08-28

AI Summary

This study addresses the limited predictive accuracy of mortality and resource utilization in intensive care units (ICUs). We propose a novel deep learning framework that integrates multimodal electronic health records (EHRs). Methodologically, we innovatively combine medical domain–specific prompt learning, free-text natural language processing, and a pre-trained sentence encoder to explicitly model textual fields within structured EHR data—such as diagnosis descriptions and procedure notes—for the first time. A Transformer-based architecture enables joint representation learning from both structured and unstructured data, while demonstrating strong robustness to missing values and noise. Evaluated on two real-world ICU datasets across three tasks—mortality prediction, length of stay estimation, and surgical duration forecasting—our model significantly outperforms state-of-the-art baselines: mortality prediction achieves +1.6% balanced accuracy (BACC) and +0.8% AUROC; continuous-variable prediction errors are substantially reduced.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Background Predicting mortality and resource utilization from electronic health records (EHRs) is challenging yet crucial for optimizing patient outcomes and managing costs in intensive care unit (ICU). Existing approaches predominantly focus on structured EHRs, often ignoring the valuable clinical insights in free-text notes. Additionally, the potential of textual information within structured data is not fully leveraged. This study aimed to introduce and assess a deep learning framework using natural language processing techniques that integrates multimodal EHRs to predict mortality and resource utilization in critical care settings. Methods Utilizing two real-world EHR datasets, we developed and evaluated our model on three clinical tasks with leading existing methods. We also performed an ablation study on three key components in our framework: medical prompts, free-texts, and pre-trained sentence encoder. Furthermore, we assessed the model's robustness against the corruption in structured EHRs. Results Our experiments on two real-world datasets across three clinical tasks showed that our proposed model improved performance metrics by 1.6%/0.8% on BACC/AUROC for mortality prediction, 0.5%/2.2% on RMSE/MAE for LOS prediction, 10.9%/11.0% on RMSE/MAE for surgical duration estimation compared to the best existing methods. It consistently demonstrated superior performance compared to other baselines across three tasks at different corruption rates. Conclusions The proposed framework is an effective and accurate deep learning approach for predicting mortality and resource utilization in critical care. The study also highlights the success of using prompt learning with a transformer encoder in analyzing multimodal EHRs. Importantly, the model showed strong resilience to data corruption within structured data, especially at high corruption levels.

Problem

• Predicting ICU mortality and resource use from EHRs
• Integrating structured data and free-text clinical notes
• Improving prediction accuracy with deep learning and NLP

Innovation

• Deep learning framework with multimodal EHR integration
• Natural language processing for free-text clinical notes
• Transformer encoder with prompt learning resilience