Development, validation, and usability evaluation of machine learning algorithms for predicting personalized red blood cell demand among thoracic surgery patients

• Published in: International journal of medical informatics (Shannon, Ireland) Vol. 191; p. 105543
• Main Authors: Hur, Sujeong, Yoo, Junsang, Min, Ji Young, Jeon, Yeong Jeong, Cho, Jong Ho, Seo, Ji Young, Cho, Duck, Kim, Kyunga, Lee, Yura, Cha, Won Chul
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.11.2024
• Subjects: Blood management; Clinical Decision Support System; Machine Learning; MSBOS; Transfusion; Transfusion; PT; GPR; INR; Machine Learning; SD; RBC; AMI; CDSS; Blood management; Clinical Decision Support System; ICD-9 CM; aPTT; SHAP; MSBOS; CI; AI; CCI; IQR; RMSE; SUS; HIT; pMSBOS-TS; RF; XG boosting; TS
• ISSN: 1386-5056; 1872-8243; 1872-8243
• DOI: 10.1016/j.ijmedinf.2024.105543

•Personalized RBC predictions enhance TS patient safety and workflow.•Machine learning models outperformed traditional statistical methods.•The pMSBOS-TS reduced RMSE and used fewer RBC packs.•SUS scores suggest good usability of the pMSBOS-TS CDSS.•This study confirms the efficacy of AI in perioperative RBC management. Preparing appropriate red blood cells (RBCs) before surgery is crucial for improving both the efficacy of perioperative workflow and patient safety. In particular, thoracic surgery (TS) is a procedure that requires massive transfusion with high variability for each patient. Hence, the precise prediction of RBC requirements for individual patients is becoming increasingly important. This study aimed to 1) develop and validate a machine learning algorithm for personalized RBC predictions for TS patients and 2) assess the usability of a clinical decision support system (CDSS) integrating this artificial intelligence model. Adult patients who underwent TS between January 2016 and October 2021 were included in this study. Multiple models were developed by employing both traditional statistical- and machine-learning approaches. The primary outcome evaluated the model’s performance in predicting RBC requirements through root mean square error and adjusted R2. Surgeons and informaticians determined the precision MSBOS-Thoracic Surgery (pMSBOS-TS) algorithm through a consensus process. The usability of the pMSBOS-TS was assessed using the System Usability Scale (SUS) survey with 60 clinicians. We identified 7,843 cases (6,200 for training and 1,643 for test sets) of TSs. Among the models with variable performance indices, the extreme gradient boosting model was selected as the pMSBOS-TS algorithm. The pMSBOS-TS model showed statistically significant lower root mean square error (mean: 3.203 and 95% confidence interval [CI]: 3.186–3.220) compared to the calculated Maximum Surgical Blood Ordering Schedule (MSBOS) and a higher adjusted R2 (mean: 0.399 and 95% CI: 0.395–0.403) compared to the calculated MSBOS, while requiring approximately 200 fewer packs for RBC preparation compared to the calculated MSBOS. The SUS score of the pMSBOS-TS CDSS was 72.5 points, indicating good acceptability. We successfully developed the pMSBOS-TS capable of predicting personalized RBC transfusion requirements for perioperative patients undergoing TS.