Validation of a Machine Learning Model for Early Shock Detection

ABSTRACT Objectives The objectives of this study were to test in real time a Trauma Triage, Treatment, and Training Decision Support (4TDS) machine learning (ML) model of shock detection in a prospective silent trial, and to evaluate specificity, sensitivity, and other estimates of diagnostic performance compared to the gold standard of electronic medical records (EMRs) review. Design We performed a single-center diagnostic performance study. Patients and setting A prospective cohort consisted of consecutive patients aged 18 years and older who were admitted from May 1 through September 30, 2020 to six Mayo Clinic intensive care units (ICUs) and five progressive care units. Measurements and main results During the study time, 5,384 out of 6,630 hospital admissions were eligible. During the same period, the 4TDS shock model sent 825 alerts and 632 were eligible. Among 632 hospital admissions with alerts, 287 were screened positive and 345 were negative. Among 4,752 hospital admissions without alerts, 78 were screened positive and 4,674 were negative. The area under the receiver operating characteristics curve for the 4TDS shock model was 0.86 (95% CI 0.85-0.87%). The 4TDS shock model demonstrated a sensitivity of 78.6% (95% CI 74.1-82.7%) and a specificity of 93.1% (95% CI 92.4-93.8%). The model showed a positive predictive value of 45.4% (95% CI 42.6-48.3%) and a negative predictive value of 98.4% (95% CI 98-98.6%). Conclusions We successfully validated an ML model to detect circulatory shock in a prospective observational study. The model used only vital signs and showed moderate performance compared to the gold standard of clinician EMR review when applied to an ICU patient cohort.

Experimental Digital Animation in Fluid Dynamics

Digital imaging became one of the main tools for studying unsteady flows. Modern high-speed cameras support video recording at high frame rates which makes it possible to study extended high-speed processes. We demonstrate here different animations: water temperature field evolution with a frame rate of 115 Hz; high-speed shadowgraph visualisation of different flows - water jet formation process (100 000 frames / s), shadowgraph animations of the shock waves created by the pulsed discharges (124 000 frames / s). Also, as an example of plasma flow visualization technique, we offer 9 sequential images of the shock wave - pulse gas discharge visualization obtained by the high-speed CCD camera with the 100 ns delay between frames. We developed in-house software based on the machine vision and learning techniques for automatic flow animations processing. The examples of the automatic oblique shock detection using Canny edge detection and Hough transform and thermal plume detection based on the pre-trained convolutional neural network are provided and discussed.