AI-Enabled Advanced Development for Assessing Low Circulating Blood Volume for Emergency Medical Care: Comparison of Compensatory Reserve Machine-Learning Algorithms

Convertino, Víctor A.; Techentin, Robert W.; Poole, Ruth; Dacy, Ashley C.; Carlson, Ashli N.; Cardin, Sylvain; Haider, Clifton R.; Holmes, David R.; Wiggins, Chad C.; Joyner, Michael J.; Curry, Timothy B.; Inan, Omer T.

doi:10.3390/s22072642

Cited by 6 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the first day, negative chamber pressure was applied (i.e., the chamber was depressurized) in a linear ramp at a randomly assigned rate of −3, −6, or −9 mmHg/min to simulate a relatively slow, medium, or fast rate of bleeding. This was consistent with previous experiments demonstrating that −30, −60, and −90 mmHg LBNP approximate average blood losses of 450, 1000, and 1600 mL, respectively in a 70 kg human [ 22 ]. Pressure was quickly released (within 2 s) when subjects reached their hemodynamic decompensation point (indicated by a systolic blood pressure (SBP) of 80 mmHg or less, a sudden drop in heart rate (HR), symptoms consistent with clinical criteria of class III shock [ 15 ], or sustained an LBNP of −100 mmHg).…”

Section: Methodssupporting

confidence: 93%

“…We expect that this would improve with a larger data set. While the data set analyzed in this paper was limited to 13 subjects with 52 LBNP collections compared to 191 subjects in the study by Convertino et al [ 22 ], our work underscores the ability to track both hemorrhage and resuscitation and demonstrates that the models presented in this current investigation track both with comparable accuracy, even when using only HRDN as a feature.…”

Section: Discussionsupporting

confidence: 52%

“…Recent work by Convertino et al [ 22 ] demonstrated accurate tracking of reductions in central blood volume similar to those produced by hemorrhage induced by a stepped-LBNP model with a cohort of 191 healthy human volunteers using CRM and CRI. The algorithms estimated the onset of hemodynamic decompensation with a CRI AUC of 0.9164 (0.0066, 95% CI = 0.903–0.92) with an R 2 = 0.978 and a CRM AUC of 0.9268 (0.0059, 95% CI = 0.915–0.93) with an R 2 = 0.958.…”

Section: Discussionmentioning

confidence: 99%

“…The Compensatory Reserve Index (CRI) uses a proprietary machine learning method [ 21 ] and estimates compensatory reserve on a scale of 1 to 0, with 1 corresponding to normovolemia and 0 to a state of decompensation. The second algorithm, termed Compensatory Reserve Metric (CRM), uses a convolutional neural network (CNN) [ 22 ] and is reported on a scale of 100% to 0% for normovolemia and decompensation, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Noninvasive Monitoring of Simulated Hemorrhage and Whole Blood Resuscitation

et al. 2022

Self Cite

View full text Add to dashboard Cite

Hemorrhage is the leading cause of preventable death from trauma. Accurate monitoring of hemorrhage and resuscitation can significantly reduce mortality and morbidity but remains a challenge due to the low sensitivity of traditional vital signs in detecting blood loss and possible hemorrhagic shock. Vital signs are not reliable early indicators because of physiological mechanisms that compensate for blood loss and thus do not provide an accurate assessment of volume status. As an alternative, machine learning (ML) algorithms that operate on an arterial blood pressure (ABP) waveform have been shown to provide an effective early indicator. However, these ML approaches lack physiological interpretability. In this paper, we evaluate and compare the performance of ML models trained on nine ABP-derived features that provide physiological insight, using a database of 13 human subjects from a lower-body negative pressure (LBNP) model of progressive central hypovolemia and subsequent progressive restoration to normovolemia (i.e., simulated hemorrhage and whole blood resuscitation). Data were acquired at multiple repressurization rates for each subject to simulate varying resuscitation rates, resulting in 52 total LBNP collections. This work is the first to use a single ABP-based algorithm to monitor both simulated hemorrhage and resuscitation. A gradient-boosted regression tree model trained on only the half-rise to dicrotic notch (HRDN) feature achieved a root-mean-square error (RMSE) of 13%, an R2 of 0.82, and area under the receiver operating characteristic curve of 0.97 for detecting decompensation. This single-feature model’s performance compares favorably to previously reported results from more-complex black box machine learning models. This model further provides physiological insight because HRDN represents an approximate measure of the delay between the ABP ejected and reflected wave and therefore is an indication of cardiac and peripheral vascular mechanisms that contribute to the compensatory response to blood loss and replacement.

show abstract

Section: Methodssupporting

confidence: 93%

Section: Discussionsupporting

confidence: 52%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Noninvasive Monitoring of Simulated Hemorrhage and Whole Blood Resuscitation

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, end-point data could also be translated to develop a temporal solution (which is significant considering that majority of the included studies utilized end-point data). Indeed, the use of real-time data is already evident in several studies that aim to utilize non-invasive techniques in measuring pulse arterial waveform to develop a real-time tracking solution [ 51 , 52 , 121 , 122 ]. Work by Convertino et al [ 123 ] highlights the sensitive nature and monitoring approach that arterial waveform feature analysis may provide for earlier and individualized assessment of blood loss and resuscitation in trauma patients.…”

Section: Application Of ML Algorithms For Hemorrhagic Traumamentioning

confidence: 99%

Artificial intelligence and machine learning for hemorrhagic trauma care

et al. 2023

View full text Add to dashboard Cite

Artificial intelligence (AI), a branch of machine learning (ML) has been increasingly employed in the research of trauma in various aspects. Hemorrhage is the most common cause of trauma-related death. To better elucidate the current role of AI and contribute to future development of ML in trauma care, we conducted a review focused on the use of ML in the diagnosis or treatment strategy of traumatic hemorrhage. A literature search was carried out on PubMed and Google scholar. Titles and abstracts were screened and, if deemed appropriate, the full articles were reviewed. We included 89 studies in the review. These studies could be grouped into five areas: (1) prediction of outcomes; (2) risk assessment and injury severity for triage; (3) prediction of transfusions; (4) detection of hemorrhage; and (5) prediction of coagulopathy. Performance analysis of ML in comparison with current standards for trauma care showed that most studies demonstrated the benefits of ML models. However, most studies were retrospective, focused on prediction of mortality, and development of patient outcome scoring systems. Few studies performed model assessment via test datasets obtained from different sources. Prediction models for transfusions and coagulopathy have been developed, but none is in widespread use. AI-enabled ML-driven technology is becoming integral part of the whole course of trauma care. Comparison and application of ML algorithms using different datasets from initial training, testing and validation in prospective and randomized controlled trials are warranted for provision of decision support for individualized patient care as far forward as possible.

show abstract