Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network

Richard S P Huang, Elena Nedelcu, Yu Bai, Amer Wahed, Kimberly Klein, Hlaing Tint, Igor Gregoric, Manish Patel, Biswajit Kar, Pranav Loyalka, Sriram Nathan, Rajko Radovancevic, Andy N D Nguyen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The prediction of bleeding risk in cardiopulmonary bypass (CPB) patients plays a vital role in their postoperative management. Therefore, an artificial neural network (ANN) to analyze intra-operative laboratory data to predict postoperative bleeding was set up. The JustNN software (Neural Planner Software, Cheshire, England) was used. This ANN was trained using 15 intra-operative laboratory parameters paired with one output category - risk of bleeding, defined as units of blood components transfused in 48 hours. The ANN was trained with the first 39 CPB cases. The set of input parameters for this ANN was also determined, and the ANN was validated with the next 13 cases. The set of input parameters include five components: pro-thrombin time, platelet count, thromboelastograph-reaction time, D-Dimer, and thromboelastograph-coagulation index. The validation results show 9 cases (69.2%) with exact match, 3 cases (23.1%) with one-grading difference, and 1 case (7.7%) with two-grading difference between actual blood usage versus predicted blood usage. To the best of our knowledge, ours is the first ANN developed for post-operative bleeding risk stratification of CPB patients. With promising results, we have started using this ANN to risk-stratify our CPB patients, and it has assisted us in predicting post-operative bleeding risk.

Original languageEnglish (US)
Pages (from-to)181-186
Number of pages6
JournalAnnals of Clinical and Laboratory Science
Volume45
Issue number2
StatePublished - 2015
Externally publishedYes

Fingerprint

Cardiopulmonary Bypass
Hemorrhage
Neural networks
Lung
Blood
Software
Thrombin Time
Platelet Count
England
Platelets
Coagulation
Thrombin

ASJC Scopus subject areas

  • Clinical Biochemistry
  • Molecular Biology
  • Immunology
  • Microbiology
  • Hematology
  • Immunology and Allergy
  • Pathology and Forensic Medicine
  • Medical Laboratory Technology

Cite this

Huang, R. S. P., Nedelcu, E., Bai, Y., Wahed, A., Klein, K., Tint, H., ... Nguyen, A. N. D. (2015). Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network. Annals of Clinical and Laboratory Science, 45(2), 181-186.

Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network. / Huang, Richard S P; Nedelcu, Elena; Bai, Yu; Wahed, Amer; Klein, Kimberly; Tint, Hlaing; Gregoric, Igor; Patel, Manish; Kar, Biswajit; Loyalka, Pranav; Nathan, Sriram; Radovancevic, Rajko; Nguyen, Andy N D.

In: Annals of Clinical and Laboratory Science, Vol. 45, No. 2, 2015, p. 181-186.

Research output: Contribution to journalArticle

Huang, RSP, Nedelcu, E, Bai, Y, Wahed, A, Klein, K, Tint, H, Gregoric, I, Patel, M, Kar, B, Loyalka, P, Nathan, S, Radovancevic, R & Nguyen, AND 2015, 'Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network', Annals of Clinical and Laboratory Science, vol. 45, no. 2, pp. 181-186.
Huang, Richard S P ; Nedelcu, Elena ; Bai, Yu ; Wahed, Amer ; Klein, Kimberly ; Tint, Hlaing ; Gregoric, Igor ; Patel, Manish ; Kar, Biswajit ; Loyalka, Pranav ; Nathan, Sriram ; Radovancevic, Rajko ; Nguyen, Andy N D. / Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network. In: Annals of Clinical and Laboratory Science. 2015 ; Vol. 45, No. 2. pp. 181-186.
@article{9dc4a1ffd6894ae5ac3c75b0c0320a1d,
title = "Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network",
abstract = "The prediction of bleeding risk in cardiopulmonary bypass (CPB) patients plays a vital role in their postoperative management. Therefore, an artificial neural network (ANN) to analyze intra-operative laboratory data to predict postoperative bleeding was set up. The JustNN software (Neural Planner Software, Cheshire, England) was used. This ANN was trained using 15 intra-operative laboratory parameters paired with one output category - risk of bleeding, defined as units of blood components transfused in 48 hours. The ANN was trained with the first 39 CPB cases. The set of input parameters for this ANN was also determined, and the ANN was validated with the next 13 cases. The set of input parameters include five components: pro-thrombin time, platelet count, thromboelastograph-reaction time, D-Dimer, and thromboelastograph-coagulation index. The validation results show 9 cases (69.2{\%}) with exact match, 3 cases (23.1{\%}) with one-grading difference, and 1 case (7.7{\%}) with two-grading difference between actual blood usage versus predicted blood usage. To the best of our knowledge, ours is the first ANN developed for post-operative bleeding risk stratification of CPB patients. With promising results, we have started using this ANN to risk-stratify our CPB patients, and it has assisted us in predicting post-operative bleeding risk.",
author = "Huang, {Richard S P} and Elena Nedelcu and Yu Bai and Amer Wahed and Kimberly Klein and Hlaing Tint and Igor Gregoric and Manish Patel and Biswajit Kar and Pranav Loyalka and Sriram Nathan and Rajko Radovancevic and Nguyen, {Andy N D}",
year = "2015",
language = "English (US)",
volume = "45",
pages = "181--186",
journal = "Annals of Clinical and Laboratory Science",
issn = "0091-7370",
publisher = "Association of Clinical Scientists",
number = "2",

}

TY - JOUR

T1 - Post-operative bleeding risk stratification in cardiac pulmonary bypass patients using artificial neural network

AU - Huang, Richard S P

AU - Nedelcu, Elena

AU - Bai, Yu

AU - Wahed, Amer

AU - Klein, Kimberly

AU - Tint, Hlaing

AU - Gregoric, Igor

AU - Patel, Manish

AU - Kar, Biswajit

AU - Loyalka, Pranav

AU - Nathan, Sriram

AU - Radovancevic, Rajko

AU - Nguyen, Andy N D

PY - 2015

Y1 - 2015

N2 - The prediction of bleeding risk in cardiopulmonary bypass (CPB) patients plays a vital role in their postoperative management. Therefore, an artificial neural network (ANN) to analyze intra-operative laboratory data to predict postoperative bleeding was set up. The JustNN software (Neural Planner Software, Cheshire, England) was used. This ANN was trained using 15 intra-operative laboratory parameters paired with one output category - risk of bleeding, defined as units of blood components transfused in 48 hours. The ANN was trained with the first 39 CPB cases. The set of input parameters for this ANN was also determined, and the ANN was validated with the next 13 cases. The set of input parameters include five components: pro-thrombin time, platelet count, thromboelastograph-reaction time, D-Dimer, and thromboelastograph-coagulation index. The validation results show 9 cases (69.2%) with exact match, 3 cases (23.1%) with one-grading difference, and 1 case (7.7%) with two-grading difference between actual blood usage versus predicted blood usage. To the best of our knowledge, ours is the first ANN developed for post-operative bleeding risk stratification of CPB patients. With promising results, we have started using this ANN to risk-stratify our CPB patients, and it has assisted us in predicting post-operative bleeding risk.

AB - The prediction of bleeding risk in cardiopulmonary bypass (CPB) patients plays a vital role in their postoperative management. Therefore, an artificial neural network (ANN) to analyze intra-operative laboratory data to predict postoperative bleeding was set up. The JustNN software (Neural Planner Software, Cheshire, England) was used. This ANN was trained using 15 intra-operative laboratory parameters paired with one output category - risk of bleeding, defined as units of blood components transfused in 48 hours. The ANN was trained with the first 39 CPB cases. The set of input parameters for this ANN was also determined, and the ANN was validated with the next 13 cases. The set of input parameters include five components: pro-thrombin time, platelet count, thromboelastograph-reaction time, D-Dimer, and thromboelastograph-coagulation index. The validation results show 9 cases (69.2%) with exact match, 3 cases (23.1%) with one-grading difference, and 1 case (7.7%) with two-grading difference between actual blood usage versus predicted blood usage. To the best of our knowledge, ours is the first ANN developed for post-operative bleeding risk stratification of CPB patients. With promising results, we have started using this ANN to risk-stratify our CPB patients, and it has assisted us in predicting post-operative bleeding risk.

UR - http://www.scopus.com/inward/record.url?scp=84929335803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929335803&partnerID=8YFLogxK

M3 - Article

VL - 45

SP - 181

EP - 186

JO - Annals of Clinical and Laboratory Science

JF - Annals of Clinical and Laboratory Science

SN - 0091-7370

IS - 2

ER -