Predicting postoperative transfusion in elective total HIP and knee arthroplasty: Comparison of different machine learning models of a case-control study.

Int J Surg

Department of Orthopedic Surgery, West China Hospital, West China Medical School, SiChuan University, ChengDu, SiChuan Province, People's Republic of China Department of Orthopaedic Surgery, School of Medicine, Duke University, Durham, NC, USA College of Cybersecurity, SiChuan University, ChengDu, SiChuan Province, People's Republic of China.

Published: December 2021

Background: Total joint arthroplasty (TJA) is a very successful orthopedics procedure but associates with a significantly high transfusion rate.

Objective: In this study, we aimed to determine predictors of postoperative blood transfusion in patients undergoing elective hip and knee TJA patients and compare the accuracy of machine learning (ML) algorithms in predicting transfusion risk.

Methods: We utilized data from 12,642 patients undergoing primary unilateral TJA. Risk factors and demographic information were extracted, and predictive models were developed using seven ML algorithms. The area under the receiver operating characteristic curve was used to measure the predictive accuracy of each algorithm.

Results: The overall transfusion rate was 18.7%. Patient-related risk factors for transfusion included age 65-85 (Odds Ratio (OR): 1.175-1.222), female (OR: 1.246), American Society of Anesthesiologists grade Ⅱ or greater (OR: 1.264-2.758). Surgical factors included operation time (OR: 1.736), drain use (OR: 2.202) as well as intraoperative blood loss (OR: 7.895). Elevated preoperative Hb (OR: 0.615), Hct (OR: 0.800), BMI (≥24 kg/m) (OR: 0.613-0.731) and tranexamic acid use (OR: 0.375) were associated with decreased risk of postoperative transfusion. The long short-term memory networks (LSTM) and random forest (RF) models achieved the highest predictive accuracy (p < 0.001).

Conclusion: The risk factors identified in the current study can provide specific, personalized postoperative transfusion risk assessment for a patient considering lower limb TJA. Furthermore, the predictive accuracies of LSTM and RF algorithms were significantly higher than the others, making them potential tools for future personalized preoperative prediction of risk for postoperative transfusion.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijsu.2021.106183DOI Listing

Publication Analysis

Top Keywords

postoperative transfusion
8
hip knee
8
machine learning
8
patients undergoing
8
risk factors
8
predictive accuracy
8
transfusion
7
predicting postoperative
4
transfusion elective
4
elective total
4

Similar Publications

Critical procedural steps in intrauterine transfusion: Delphi survey of international experts.

Ultrasound Obstet Gynecol

January 2025

Division of Fetal Medicine, Department of Obstetrics and Gynecology, Willem-Alexander Children's Hospital, Leiden University Medical Center, Leiden, The Netherlands.

Objective: To determine consensus, using Delphi methodology, on the critical procedural steps for intravascular intrauterine transfusion (IUT) for the treatment of fetal anemia.

Methods: We conducted a two-part Delphi survey of international experts in fetal intervention. The first round of the survey proposed 32 potentially critical steps for the IUT procedure.

View Article and Find Full Text PDF

Objective: This study reports the authors' experience with surgical interventions for nonsyndromic craniosynostosis. They assessed open surgery and minimally invasive endoscopic suturectomy in terms of periprocedural outcomes and related risk factors for postoperative complications and reoperation. This study aimed to provide insights toward surgical approach decisions and lay the groundwork for future prospective studies in this field.

View Article and Find Full Text PDF

Introduction: Hereditary bleeding disorders stem from the absence or insufficient levels of particular clotting proteins, essential for facilitating coagulation in the clotting cascade. Among the most prevalent are hemophilia A (deficiency of Factor VIII), hemophilia B (deficiency of Factor IX), and von Willebrand disease. Management of pharmacoresistant epilepsy is more difficult in a patient with bleeding disorder due to increased risk of bleeding during surgery.

View Article and Find Full Text PDF

Introduction: Although giant cystic pheochromocytoma and paraganglioma (PPGL) are uncommon, they can be life-threatening when it occurs. Unfortunately, prior case reports have shown that giant cystic PPGLs are highly susceptible to diagnostic errors. Therefore, this study aimed to explore giant cystic PPGLs by comparing them with non-cystic PPGLs, defining the clinical features of the affected patients, and analyzing the characteristics of misdiagnosis and mistreatment associated with PPGLs.

View Article and Find Full Text PDF

Background: Jehovah's Witness patients refuse blood transfusion because of their religious beliefs making total hip arthroplasty (THA) challenging. This study aims to determine the safety of THA in Jehovah's Witness patients using standard perioperative protocols as well as evaluate the effectiveness of tranexamic acid (TXA) in controlling blood loss.

Methods: Databases from two tertiary academic centers were queried from 2003 to 2021 to identify THA patients.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!