Predicting blood loss volume in a canine model of hemorrhagic shock using arterial waveform machine learning analysis

To determine if the compensatory reserve algorithm validated in humans can be applied to canines. Our secondary objective was to determine if a simpler waveform analysis could predict the percentage of blood loss volume.

6 purpose-bred, anesthetized dogs underwent 5 rounds of controlled hemorrhage and resuscitation while continuously recording invasive arterial blood pressure waveforms in this prospective, experimental study. We calculated human compensatory reserve using deep learning (hCRM-DL) and machine learning (hCRM-ML) models previously developed with human data. We trained a metric to track blood loss volume using features extracted from canine (c) arterial waveforms as an input.

When applied to the 6 dogs, the hCRM-DL model (R2 = 0.38) more poorly fit a linear regression model against mean arterial pressure and had lower area under the receiver operating characteristic (AUROC; 0.60) compared to the hCRM-ML model (R2 = 0.61; AUROC, 0.73). Conversely, the arterial waveform analysis for canine blood loss volume metric (cBLVM) predicted blood loss in dogs experiencing controlled hemorrhagic shock more accurately (R2 = 0.74). The cBLVM model for predicting blood loss volume had the highest AUROC score (0.81) and was the earliest indicator of hemorrhage onset.

The hCRM-ML and hCRM-DL algorithms did not translate to accurate prediction of the onset of hemorrhagic shock in dogs. However, the arterial waveform feature analysis-derived cBLVM might provide decision support to resuscitate dogs with hemorrhagic shock.

Canine BLVM may be useful in estimating blood loss in dogs, which can guide resuscitation strategies for these patients.