Outcome Prediction in Critically-Ill Patients with Venous Thromboembolism and/or Cancer Using Machine Learning Algorithms: External Validation and Comparison with Scoring Systems

Abstract

Intensive care unit (ICU) patients with venous thromboembolism (VTE) and/or cancer suffer from high mortality rates. Mortality prediction in the ICU has been a major medical challenge for which several scoring systems exist but lack in specificity. This study focuses on two target groups, namely patients with thrombosis or cancer. The main goal is to develop and validate interpretable machine learning (ML) models to predict early and late mortality, while exploiting all available data stored in the medical record. To this end, retrospective data from two freely accessible databases, MIMIC-III and eICU, were used. Well-established ML algorithms were implemented utilizing automated and purposely built ML frameworks for addressing class imbalance. Prediction of early mortality showed excellent performance in both disease categories, in terms of the area under the receiver operating characteristic curve (AUC−ROC): VTE-MIMIC-III 0.93, eICU 0.87, cancer-MIMIC-III 0.94. On the other hand, late mortality prediction showed lower performance, i.e., AUC−ROC: VTE 0.82, cancer 0.74–0.88. The predictive model of early mortality developed from 1651 VTE patients (MIMIC-III) ended up with a signature of 35 features and was externally validated in 2659 patients from the eICU dataset. Our model outperformed traditional scoring systems in predicting early as well as late mortality. Novel biomarkers, such as red cell distribution width, were identified.

Machine learning-based predictive models for patients with venous thromboembolism: A Systematic Review

“…Similarly, Herrin et al 75 showed that XGB outperformed traditional risk score HAS-BLED in predicting gastrointestinal bleeding 6 and 12 months after initiating anticoagulation treatment. One study in ICU patients reported in detail and clearly preprocessing steps, splitting/cross-validation, other performance metrics besides AUC and hyperparameter, performed external validation and compared ML-based models with traditional medical scores 72 . PESI score was outperformed by XGB and RF models in 77 and 76 respectively.…”

Self-supervised predictive coding and multimodal fusion advance patient deterioration prediction in fine-grained time resolution

“…Our main contributions are as follows; 1) to predict the mortality and vasopressor need of urgent patients, we propose a fine-grained time deterioration prediction method for the first time in the literature; 2) we explore various future encoding methods and losses for self-supervised learning (SSL) predictive coding for deterioration prediction (Fig. 2); 3) through an extensive experiment, we show that both multimodal fusion and SSL predictive coding regularization using L 2 loss and normalized context vector improve the predictive performance, especially far-future prediction, which is crucial but more challenging than near-future prediction [2,8].…”