Development and Temporal Validation of a Machine Learning Model to Predict Clinical Deterioration.

OBJECTIVES: Early warning scores detecting clinical deterioration in pediatric inpatients have wide-ranging performance and use a limited number of clinical features. This study developed a machine learning model leveraging multiple static and dynamic clinical features from the electronic health record to predict the composite outcome of unplanned transfer to the ICU within 24 hours and inpatient mortality within 48 hours in hospitalized children. METHODS: Using a retrospective development cohort of 17 630 encounters across 10 388 patients, 2 machine learning models (light gradient boosting machine [LGBM] and random forest) were trained on 542 features and compared with our institutional Pediatric Early Warning Score (I-PEWS). RESULTS: The LGBM model significantly outperformed I-PEWS based on receiver operating characteristic curve (AUROC) for the composite outcome of ICU transfer or mortality for both internal validation and temporal validation cohorts (AUROC 0.785 95% confidence interval [0.780-0.791] vs 0.708 [0.701-0.715] for temporal validation) as well as lead-time before deterioration events (median 11 hours vs 3 hours; P = .004). However, LGBM performance as evaluated by precision recall curve was lesser in the temporal validation cohort with associated decreased positive predictive value (6% vs 29%) and increased number needed to evaluate (17 vs 3) compared with I-PEWS. CONCLUSIONS: Our electronic health record based machine learning model demonstrated improved AUROC and lead-time in predicting clinical deterioration in pediatric inpatients 24 to 48 hours in advance compared with I-PEWS. Further work is needed to optimize model positive predictive value to allow for integration into clinical practice.

The Role of Immersion for Improving Extended Reality Analysis of Personalized Flow Simulations.

PURPOSE: Computational models of flow in patient-derived arterial geometries have become a key paradigm of biomedical research. These fluid models are often challenging to visualize due to high spatial heterogeneity and visual complexity. Virtual immersive environments can offer advantageous visualization of spatially heterogeneous and complex systems. However, as different VR devices offer varying levels of immersion, there remains a crucial lack of understanding regarding what level of immersion is best suited for interactions with patient-specific flow models. METHODS: We conducted a quantitative user evaluation with multiple VR devices testing an important use of hemodynamic simulations-analysis of surface parameters within complex patient-specific geometries. This task was compared for the semi-immersive zSpace 3D monitor and the fully immersive HTC Vive system. RESULTS: The semi-immersive device was more accurate than the fully immersive device. The two devices showed similar results for task duration and performance (accuracy/duration). The accuracy of the semi-immersive device was also higher for arterial geometries of greater complexity and branching. CONCLUSION: This assessment demonstrates that the level of immersion plays a significant role in the accuracy of assessing arterial flow models. We found that the semi-immersive VR device was a generally optimal choice for arterial visualization.