ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes

2020/05/19 by William Caicedo-Torres, Caicedo-Torres, William, Jairo Gutiérrez +1
Computer Science · Health Professions · Medicine · #Artificial Intelligence in Healthcare #COVID-19 diagnosis using AI #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2005.09284

openalex publication_date 2020/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Accurate mortality prediction allows Intensive Care Units (ICUs) to adequately benchmark clinical practice and identify patients with unexpected outcomes. Traditionally, simple statistical models have been used to assess patient death risk, many times with sub-optimal performance. On the other hand deep learning holds promise to positively impact clinical practice by leveraging medical data to assist diagnosis and prediction, including mortality prediction. However, as the question of whether powerful Deep Learning models attend correlations backed by sound medical knowledge when generating predictions remains open, additional interpretability tools are needed to foster trust and encourage the use of AI by clinicians. In this work we show a Deep Learning model trained on MIMIC-III to predict mortality using raw nursing notes, together with visual explanations for word importance. Our model reaches a ROC of 0.8629 (+/-0.0058), outperforming the traditional SAPS-II score and providing enhanced interpretability when compared with similar Deep Learning approaches.

Citations

• Adam: A Method for Stochastic Optimization
• Long Short-Term Memory
• Gradient-based learning applied to document recognition
• Model-Agnostic Interpretability of Machine Learning
• Combining LSTM and Latent Topic Modeling for Mortality Prediction
• The MIMIC Code Repository: enabling reproducibility in critical care research
• Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
• Fair Allocation of Scarce Medical Resources in the Time of Covid-19

Related

• Translating Machine Learning Interpretability into Clinical Insights for ICU Mortality Prediction
• All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III)
• Development and external validation of a multimodal artificial intelligence mortality prediction model of critically ill patients using multicenter data
• Prediction of mortality and resource utilization in critical care: a deep learning approach using multimodal electronic health records with natural language processing techniques
• Integrating Physiological Time Series and Clinical Notes with Deep\n Learning for Improved ICU Mortality Prediction