Machine Learning Model for Perioperative Transfusion Prediction

Surgery Clinical Trial

Official title:

Development and Interpretation of a Machine Learning Model for Perioperative Transfusion Prediction

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT05228548
• Other study ID #: Machine learning DiskapiTRH
• Status: Completed
• Start date: January 13, 2022
• Est. completion date: February 1, 2022

Study information

• Verified date: January 2022
• Source: Diskapi Teaching and Research Hospital
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

This study aimed to develop and interpret a machine learning model to predict red blood cell (RBC) transfusion.

Description:

A dataset from a multicenter study involving 6121 patients underwent elective major surgery was analysed. Data concerning patients who received inappropriate RBC transfusion were excluded. Twenty one perioperative features were used to predict RBC transfusion. The data set was randomly split into train and validation sets (70-30). Decision tree, random forest, k-nearest neighbors, logistic regression, and eXtreme garadient boosting (XGBoost) methods were used for prediction. The area under the curves (AUC) of the receiver operating characteristics curves for the machine learning models used for RBC transfusion prediction were compared.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 6121
• Est. completion date: February 1, 2022
• Est. primary completion date: February 1, 2022
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years to 100 Years

Eligibility

Inclusion Criteria:

• Adult

• Underwent major elective surgery

Exclusion Criteria:

• Pediatric patients

• Emergency cases

Related Conditions & MeSH terms

• Blood Transfusion
• Surgery

Intervention

Other:
• Perioperative blood transfusion
Perioperative blood transfusion

Locations

Country	Name	City	State
Turkey	Dilek D Unal	Ankara

Sponsors (35)

Lead Sponsor

Collaborator

Diskapi Teaching and Research Hospital

Akdeniz University, Ankara University, Balikesir University, Baskent University, Bulent Ecevit University, Celal Bayar University, Dokuz Eylul University, Erzincan University, Eskisehir Osmangazi University, Firat University, Gazi University, Hacettepe University, Hitit University, Inonu University, Istanbul Medeniyet University, Istanbul University, Kahramanmaras Sutcu Imam University, Karadeniz Technical University, Marmara University, Mersin University, Namik Kemal University, Necmettin Erbakan University, Ondokuz Mayis University, Osmaniye Government Hospital, Saglik Bilimleri Universitesi, Selcuk University, Suleyman Demirel University, T.C. ORDU ÜNIVERSITESI, TC Erciyes University, Tobb University of Economics and Technology, Trakya University, Ufuk University, Uludag University, Yuzuncu Yil University

Country where clinical trial is conducted

Turkey, 

References & Publications (3)

Bernard AC, Davenport DL, Chang PK, Vaughan TB, Zwischenberger JB. Intraoperative transfusion of 1 U to 2 U packed red blood cells is associated with increased 30-day mortality, surgical-site infection, pneumonia, and sepsis in general surgery patients. J — View Citation

Murphy GJ, Reeves BC, Rogers CA, Rizvi SI, Culliford L, Angelini GD. Increased mortality, postoperative morbidity, and cost after red blood cell transfusion in patients having cardiac surgery. Circulation. 2007 Nov 27;116(22):2544-52. Epub 2007 Nov 12. — View Citation

Walczak S, Velanovich V. Prediction of perioperative transfusions using an artificial neural network. PLoS One. 2020 Feb 24;15(2):e0229450. doi: 10.1371/journal.pone.0229450. eCollection 2020. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Number of patients received Red blood cell transfusion	Number of patients received Red blood cell transfusion	Perioperative period
Primary	The area under the curve	The the area under the curve of the receiver operating characteristics curves	Perioperative period