Machine Learning Versus Traditional Scores in Predicting Erythrocyte Need

NCT06594484 | Completed

• 1 other identifier: 2024-6
• Study Type: observational
• Target: 430
• Locations: 1 country
• Sites: 1

Brief Summary

In this study, we compared perioperative bleeding prediction scores with our machine learning-based prediction system in predicting the need for erythrocyte suspension during cardiovascular surgery.

Conditions

Erythrocyte Transfusion; Machine Learning

Keywords

Machine Learning; Cardiovascular Surgery; Perioperative Bleeding; Erythrocyte Transfusion; Predictive Modeling

Outcome Measures

Primary Outcomes (1)

• ML algorithm versus traditional scoring in predicting ES needs

  The success of the ML-based algorithm in correctly predicting the ES need will be calculated.

  During the intraoperative period Cardiac Surgery

Secondary Outcomes (1)

• Deterdetermining the most effective method for predicting ES needs using traditional scores

  During the intraoperative period Cardiac Surgery

Other Outcomes (1)

• ML algorithm of combination of scores

  During the intraoperative period Cardiac Surgery

Study Arms (1)

General Anesthesia Group

The need for ES was recorded in patients undergoing cardiovascular surgery.

Other: Ml Based Algorithm 1; Other: Ml Based Algroithm 2; Other: Bleeding Scores

Interventions

Ml Based Algorithm 1 OTHER

The values in the ML algorithm were selected according to logistic regression analysis and the values used in the other six scores tested. The success rate of the constructed networks correct predictions was considered as the success rate of the algorithm. The usefulness of the test was determined through AUROC analysis. Two algorithms were tested in our study. In the first algorithm (ML1), the dependent variable was erythrocyte suspension (ES) consumption, and the independent variables included patients; demographic data, laboratory data, and operational data

General Anesthesia Group

Ml Based Algroithm 2 OTHER

is an Ml algorithm created by combining commonly used bleeding scores

General Anesthesia Group

Bleeding Scores OTHER

ACTION CRUSCADE TRACK WILL-BLEED PAPWORTH TRUST ACTAPORT skores used to predict ES need

General Anesthesia Group

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Complete files from the data of patients undergoing elective cardiac surgery in Kocaeli City Hospital operating rooms will constitute the study data.

You may qualify if:

• Data from patients who underwent isolated CABG surgeries in the cardiac and vascular surgery operating rooms between 01.01.2023 and 01.01.2024 were evaluated.

You may not qualify if:

• Missing Data
• Emergency surgery
• İntraoperative mortality

Sponsors & Collaborators

• Kocaeli City Hospital: lead

Study Sites (1)

Kocaeli City Hospital

Kocaeli, Izmıt, 41100, Turkey (Türkiye)

Location

Related Publications (5)

• Park J, Bonde PN. Machine Learning in Cardiac Surgery: Predicting Mortality and Readmission. ASAIO J. 2022 Dec 1;68(12):1490-1500. doi: 10.1097/MAT.0000000000001696. Epub 2022 May 9.

  PMID: 35544455 BACKGROUND

• El-Sherbini AH, Shah A, Cheng R, Elsebaie A, Harby AA, Redfearn D, El-Diasty M. Machine Learning for Predicting Postoperative Atrial Fibrillation After Cardiac Surgery: A Scoping Review of Current Literature. Am J Cardiol. 2023 Dec 15;209:66-75. doi: 10.1016/j.amjcard.2023.09.079. Epub 2023 Oct 21.

  PMID: 37871512 BACKGROUND

• Shahian DM, Lippmann RP. Commentary: Machine learning and cardiac surgery risk prediction. J Thorac Cardiovasc Surg. 2022 Jun;163(6):2090-2092. doi: 10.1016/j.jtcvs.2020.08.058. Epub 2020 Aug 24. No abstract available.

  PMID: 32951875 BACKGROUND

• Miles TJ, Ghanta RK. Machine learning in cardiac surgery: a narrative review. J Thorac Dis. 2024 Apr 30;16(4):2644-2653. doi: 10.21037/jtd-23-1659. Epub 2024 Apr 24.

  PMID: 38738250 BACKGROUND

• Tseng PY, Chen YT, Wang CH, Chiu KM, Peng YS, Hsu SP, Chen KL, Yang CY, Lee OK. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care. 2020 Jul 31;24(1):478. doi: 10.1186/s13054-020-03179-9.

  PMID: 32736589 BACKGROUND

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER GOV
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: md

Study Record Dates

• First Submitted: September 6, 2024
• First Posted: September 19, 2024
• Study Start: February 22, 2024
• Primary Completion: May 22, 2024
• Study Completion: May 30, 2024
• Last Updated: September 19, 2024

Record last verified: 2024-09

Data Sharing

• IPD Sharing: Will not share

Locations

TU (1)