Improving Accuracy of Non-invasive Hemoglobin Monitors: A Functional Regression Model for Streaming SpHb Data

Devashish Das, Kalyan S Pasupathy, Nadeem Haddad, Susan Hallbeck, Martin Zielinski, Mustafa Sir

Research output: Contribution to journalArticle

Abstract

Objective: The propose of this article is to develop a method for improving the accuracy of SpHb monitors, which are non-invasive hemoglobin monitoring tools, leading to better critical care protocols in trauma care. Methods: The proposed method is based on fitting smooth spline functions to SpHb measurements collected over a time window and then using a functional regression model to predict the true HgB value for the end of the time window. Results: The accuracy of the proposed method is compared to traditional methods. The mean absolute error between the raw SpHb measurements and the gold standard hemoglobin measurements was 1.26 g/Dl. The proposed method reduced the mean absolute error to 1.08 g/Dl. Conclusion: Fitting a smooth function to SpHb measurements improves the accuracy of Hgb predictions. Significance: Accurate prediction of current and future HgB levels can lead to sophisticated decision models that determine the optimal timing and amount of blood product transfusions.

Original languageEnglish (US)
JournalIEEE Transactions on Biomedical Engineering
DOIs
StateAccepted/In press - Jul 12 2018

Fingerprint

Hemoglobin
Splines
Blood
Monitoring

Keywords

  • Biomedical monitoring
  • Current measurement
  • Functional regression
  • Gold
  • improving accuracy
  • Measurement uncertainty
  • Monitoring
  • noninvasive hemoglobin monitors
  • Standards

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

@article{96c72253103d48b5bb779d290583d405,
title = "Improving Accuracy of Non-invasive Hemoglobin Monitors: A Functional Regression Model for Streaming SpHb Data",
abstract = "Objective: The propose of this article is to develop a method for improving the accuracy of SpHb monitors, which are non-invasive hemoglobin monitoring tools, leading to better critical care protocols in trauma care. Methods: The proposed method is based on fitting smooth spline functions to SpHb measurements collected over a time window and then using a functional regression model to predict the true HgB value for the end of the time window. Results: The accuracy of the proposed method is compared to traditional methods. The mean absolute error between the raw SpHb measurements and the gold standard hemoglobin measurements was 1.26 g/Dl. The proposed method reduced the mean absolute error to 1.08 g/Dl. Conclusion: Fitting a smooth function to SpHb measurements improves the accuracy of Hgb predictions. Significance: Accurate prediction of current and future HgB levels can lead to sophisticated decision models that determine the optimal timing and amount of blood product transfusions.",
keywords = "Biomedical monitoring, Current measurement, Functional regression, Gold, improving accuracy, Measurement uncertainty, Monitoring, noninvasive hemoglobin monitors, Standards",
author = "Devashish Das and Pasupathy, {Kalyan S} and Nadeem Haddad and Susan Hallbeck and Martin Zielinski and Mustafa Sir",
year = "2018",
month = "7",
day = "12",
doi = "10.1109/TBME.2018.2856091",
language = "English (US)",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Improving Accuracy of Non-invasive Hemoglobin Monitors

T2 - A Functional Regression Model for Streaming SpHb Data

AU - Das, Devashish

AU - Pasupathy, Kalyan S

AU - Haddad, Nadeem

AU - Hallbeck, Susan

AU - Zielinski, Martin

AU - Sir, Mustafa

PY - 2018/7/12

Y1 - 2018/7/12

N2 - Objective: The propose of this article is to develop a method for improving the accuracy of SpHb monitors, which are non-invasive hemoglobin monitoring tools, leading to better critical care protocols in trauma care. Methods: The proposed method is based on fitting smooth spline functions to SpHb measurements collected over a time window and then using a functional regression model to predict the true HgB value for the end of the time window. Results: The accuracy of the proposed method is compared to traditional methods. The mean absolute error between the raw SpHb measurements and the gold standard hemoglobin measurements was 1.26 g/Dl. The proposed method reduced the mean absolute error to 1.08 g/Dl. Conclusion: Fitting a smooth function to SpHb measurements improves the accuracy of Hgb predictions. Significance: Accurate prediction of current and future HgB levels can lead to sophisticated decision models that determine the optimal timing and amount of blood product transfusions.

AB - Objective: The propose of this article is to develop a method for improving the accuracy of SpHb monitors, which are non-invasive hemoglobin monitoring tools, leading to better critical care protocols in trauma care. Methods: The proposed method is based on fitting smooth spline functions to SpHb measurements collected over a time window and then using a functional regression model to predict the true HgB value for the end of the time window. Results: The accuracy of the proposed method is compared to traditional methods. The mean absolute error between the raw SpHb measurements and the gold standard hemoglobin measurements was 1.26 g/Dl. The proposed method reduced the mean absolute error to 1.08 g/Dl. Conclusion: Fitting a smooth function to SpHb measurements improves the accuracy of Hgb predictions. Significance: Accurate prediction of current and future HgB levels can lead to sophisticated decision models that determine the optimal timing and amount of blood product transfusions.

KW - Biomedical monitoring

KW - Current measurement

KW - Functional regression

KW - Gold

KW - improving accuracy

KW - Measurement uncertainty

KW - Monitoring

KW - noninvasive hemoglobin monitors

KW - Standards

UR - http://www.scopus.com/inward/record.url?scp=85049977826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049977826&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2856091

DO - 10.1109/TBME.2018.2856091

M3 - Article

C2 - 30010545

AN - SCOPUS:85049977826

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

ER -