Use of Advanced Machine-Learning Techniques for Noninvasive Monitoring of Hemorrhage

Convertino, Víctor A.; Moulton, Steven L.; Grudić, Gregory Z.; Rickards, Caroline A.; Hinojosa‐Laborde, Carmen; Gerhardt, Robert T.; Blackbourne, Lorne H.; Ryan, Kathy L.

doi:10.1097/ta.0b013e3182211601

Cited by 98 publications

(103 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since stroke volume is associated with features of the arterial pulse waveform (5,20,24), it is not surprising that stroke volume showed a high correlation with blood loss similar to that of CRI. However, the rate of change in stroke volume during blood loss is similar in individuals regardless of their tolerance to hypovolemia (8,21). This is demonstrated in the present study by the similar rate of stroke volume decrease (slope) in Fig.…”

Section: Discussionsupporting

confidence: 83%

“…This approach has resulted in the identification of individuals with high and low tolerance to central hypovolemia (6, 8 -10, 26). On the basis of our large database of more than 200 human LBNP experiments, a machine-learning algorithm based on analysis of arterial waveform features was developed to detect the reserve to compensate for reductions in central blood volume (8). We call this physiological measurement the compensatory reserve; the algorithm calculates a compensatory reserve index (CRI), which reflects the proportion of intravascular volume remaining before the onset of decompensation (21) and can distinguish those individuals with low tolerance to central hypovolemia (6).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of compensatory reserve during lower-body negative pressure and hemorrhage in nonhuman primates

Hinojosa‐Laborde

Howard

Mulligan

et al. 2016

American Journal of Physiology-Regulatory, Integrative and Comp

Self Cite

View full text Add to dashboard Cite

Hinojosa-Laborde C, Howard JT, Mulligan J, Grudic GZ, Convertino VA. Comparison of compensatory reserve during lowerbody negative pressure and hemorrhage in nonhuman primates. Am J Physiol Regul Integr Comp Physiol 310: R1154 -R1159, 2016. First published March 30, 2016 doi:10.1152/ajpregu.00304.2015.-Compensatory reserve was measured in baboons (n ϭ 13) during hemorrhage (Hem) and lower-body negative pressure (LBNP) using a machine-learning algorithm developed to estimate compensatory reserve by detecting reductions in central blood volume during LBNP. The algorithm calculates compensatory reserve index (CRI) from normovolemia (CRI ϭ 1) to cardiovascular decompensation (CRI ϭ 0). The hypothesis was that Hem and LBNP will elicit similar CRI values and that CRI would have higher specificity than stroke volume (SV) in predicting decompensation. Blood was removed in four steps: 6.25%, 12.5%, 18.75%, and 25% of total blood volume. Four weeks after Hem, the same animals were subjected to four levels of LBNP that was matched on the basis of their central venous pressure. Data These data support the hypothesis that Hem and LBNP elicited the same CRI response, suggesting that measurement of compensatory reserve is superior to SV as a predictor of cardiovascular decompensation blood loss; central hypovolemia; stroke volume; blood pressure; compensatory mechanisms

show abstract

Section: Discussionsupporting

confidence: 83%

mentioning

confidence: 99%

Comparison of compensatory reserve during lower-body negative pressure and hemorrhage in nonhuman primates

Hinojosa‐Laborde

Howard

Mulligan

et al. 2016

American Journal of Physiology-Regulatory, Integrative and Comp

Self Cite

View full text Add to dashboard Cite

show abstract

“…The removal of PPG waveform artifact is an open area of research [14], [20]. Consistent with [8], [12], [25] we observe that without artifacts, the dominant non-DC frequencies of the PPG waveform correspond to the fundamental frequency of the heart rate and its harmonic frequencies. As test in (7) only requires the sampled average PPG waveform, PPG, we can employ this observation to generate the sampled average PPG waveform at each time step k, PPG(k), corresponding to a T second time window by dividing the T second window into J sub-windows of equal length.…”

Section: Ppg Waveform Preprocessingsupporting

confidence: 82%

“…[3], [7], [8], [9], [10]. Patient fluid inputs and outputs are closely monitored for changes [11], as common medical practice holds that these changes may reflect changes in blood volume.…”

Section: Introductionmentioning

confidence: 99%

Robust monitoring of hypovolemia in intensive care patients using photoplethysmogram signals

Roederer

Weimer

Dimartino

et al. 2015

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

The paper presents a fingertip photoplethysmography based technique to assess patient fluid status that is robust to waveform artifacts and health variability in the underlying patient population. The technique is intended for use in intensive care units, where patients are at risk for hypovolemia, and signal artifacts and inter-patient variations in health are common. Input signals are preprocessed to remove artifact, then a parameter-invariant statistic is calculated to remove effects of patient-specific physiology. Patient data from the Physionet MIMICII database was used to evaluate the performance of this technique. The proposed method was able to detect hypovolemia within 24 hours of onset in all hypovolemic patients tested, while producing minimal false alarms over non-hypovolemic patients. Abstract-The paper presents a fingertip photoplethysmography based technique to assess patient fluid status that is robust to waveform artifacts and health variability in the underlying patient population. The technique is intended for use in intensive care units, where patients are at risk for hypovolemia, and signal artifacts and inter-patient variations in health are common. Input signals are preprocessed to remove artifact, then a parameter-invariant statistic is calculated to remove effects of patient-specific physiology. Patient data from the Physionet MIMICII database was used to evaluate the performance of this technique. The proposed method was able to detect hypovolemia within 24 hours of onset in all hypovolemic patients tested, while producing minimal false alarms over non-hypovolemic patients.

show abstract

“…An intermediate group of patients, who show no alarming symptoms on presentation, however, do deteriorate later, represents a real diagnostic challenge. Traditional vital sign parameters are not sensitive enough for reliable classification (7). Refinement of the traditional tools, as well as search for new parameters, is badly needed (2).…”

mentioning

confidence: 99%

Noninvasive continuous arterial pressure measurements in the assessment of acute, severe central hypovolemia

Simon¹,

Farkas²,

Gingl³

et al. 2015

Acta Physiologica Hungarica

View full text Add to dashboard Cite

Acute, severe hypovolemia is a medical emergency. Traditional vital sign parameters allow no optimal triage. High predictive power of finger plethysmography-based stroke volume (SV) and pulse pressure (PP) was recently suggested. To assess the performance of the PP and SV parameters, lower body negative pressure of -40 mmHg, than -60 mmHg -corresponding to moderate and severe central hypovolemia -was applied in 22 healthy males (age 35 ± 7 years). Slow breathing induced fluctuations in the above indices, characterized by stroke volume variability (SVV), and pulse pressure variability (PPV), were assessed. Responses in heart rate (HR) and shock index (SI) were also studied. Discriminative capacity of these parameters was characterized by the area under the ROC (receiver operating characteristic) curves (AUC). Results: In comparison of baseline to severe central hypovolemia SV, PP, HR and SI showed good discriminating capacity (AUC 99%, 88%, 87% and 93%, respectively). The discriminating capacity of SVV and PPV was poor (77% and 70%, respectively). In comparison of moderate and severe hypovolemia, the discriminating capacity of the studied parameters was uniformly limited. Conclusions: Plethysmography-based SV and PP parameters can be used to detect acute severe volume loss. Sensitive parameters discriminating moderate and severe central hypovolemia are still lacking.

show abstract

Use of Advanced Machine-Learning Techniques for Noninvasive Monitoring of Hemorrhage

Abstract: Machine modeling can accurately identify reduced central blood volume and predict impending hemodynamic decompensation (shock onset) in individuals. Such a capability can provide decision support for earlier intervention.

Cited by 98 publications

References 39 publications

Comparison of compensatory reserve during lower-body negative pressure and hemorrhage in nonhuman primates

Comparison of compensatory reserve during lower-body negative pressure and hemorrhage in nonhuman primates

Robust monitoring of hypovolemia in intensive care patients using photoplethysmogram signals

Noninvasive continuous arterial pressure measurements in the assessment of acute, severe central hypovolemia

Contact Info

Product

Resources

About