1
|
Li Q, Lv H, Chen Y, Shen J, Shi J, Zhou C, Yan F. Development and validation of a machine learning prediction model for perioperative red blood cell transfusions in cardiac surgery. Int J Med Inform 2024; 184:105343. [PMID: 38286086 DOI: 10.1016/j.ijmedinf.2024.105343] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 01/10/2024] [Accepted: 01/17/2024] [Indexed: 01/31/2024]
Abstract
OBJECTIVE Several machine learning (ML) models have been used in perioperative red blood cell (RBC) transfusion risk for cardiac surgery with limited generalizability and no external validation. Hence, we sought to develop and comprehensively externally validate a ML model in a large dataset to estimate RBC transfusion in cardiac surgery with cardiopulmonary bypass (CPB). DESIGN A retrospective analysis of a multicenter clinical trial (NCT03782350). PATIENTS The study patients who underwent cardiac surgery with CPB came from four cardiac centers in China and Medical Information Mart for Intensive Cared (MIMIC-IV) dataset. MEASUREMENTS Data from Fuwai Hospital were used to develop an individualized prediction model for RBC transfusion. The model was externally validated in the data from three other centers and MIMIC-IV dataset. Twelve models were constructed. MAIN RESULTS A total of 11,201 eligible patients were included in the model development (2420 in Fuwai Hospital) and external validation (563 in the other three centers and 8218 in the MIMIC-IV dataset). A significant difference was observed between the Logistic Regression and CatboostClassifier (0.72 Vs. 0.74, P = 0.031) or RandomForestClassifier (0.72 Vs. 0.75 p = 0.012) in the external validation and MIMIV-IV datasets (age ≤ 70:0.63 Vs. 0.71, p < 0.001; age > 70:0.63 Vs. 0.70, 0.63 Vs. 0.71, p < 0.001). The CatboostClassifier and RandomForestClassifier model was comparable in development (0.83 Vs. 0.82, p = 0.419), external (0.74 Vs. 0.75, p = 0.268), and MIMIC-IV datasets (age ≤ 70: 0.71 Vs. 0.71, p = 0.574; age > 70: 0.70 Vs. 0.71, p = 0.981). Of note, they outperformed other ML models with excellent discrimination and calibration. The CatboostClassifier and RandomForestClassifier models achieved higher area under precision-recall curve and lower brier loss score in validation and MIMIC-IV datasets. Additionally, we confirmed that low preoperative hemoglobin, low body mass index, old age, and female sex increased the risk of RBC transfusion. CONCLUSIONS In our study, enrolling a broad range of cardiovascular surgeries with CPB and utilizing a restrictive RBC transfusion strategy, robustly validates the generalizability of ML algorithms for predicting RBC transfusion risk. Notably, the CatboostClassifier and RandomForestClassifier exhibit strong external clinical applicability, underscoring their potential for widespread adoption. This study provides compelling evidence supporting the efficacy and practical value of ML-based approaches in enhancing transfusion risk prediction in clinical practice.
Collapse
Affiliation(s)
- Qian Li
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China
| | - Hong Lv
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China
| | - Yuye Chen
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China
| | - Jingjia Shen
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China
| | - Jia Shi
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China
| | - Chenghui Zhou
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China; Center for Anesthesiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, 100029, China.
| | - Fuxia Yan
- Department of Anesthesiology, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing 100037, China.
| |
Collapse
|
2
|
Lenet T, Baker L, Park L, Vered M, Zahrai A, Shorr R, Davis A, McIsaac DI, Tinmouth A, Fergusson DA, Martel G. A Systematic Review and Meta-analysis of Randomized Controlled Trials Comparing Intraoperative Red Blood Cell Transfusion Strategies. Ann Surg 2022; 275:456-466. [PMID: 34319671 PMCID: PMC8820777 DOI: 10.1097/sla.0000000000004931] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
OBJECTIVE The objective of this work was to carry out a meta-analysis of RCTs comparing intraoperative RBC transfusion strategies to determine their impact on postoperative morbidity, mortality, and blood product use. SUMMARY OF BACKGROUND DATA RBC transfusions are common in surgery and associated with widespread variability despite adjustment for casemix. Evidence-based recommendations guiding RBC transfusion in the operative setting are limited. METHODS The search strategy was adapted from a previous Cochrane Review. Electronic databases were searched from January 2016 to February 2021. Included studies from the previous Cochrane Review were considered for eligibility from before 2016. RCTs comparing intraoperative transfusion strategies were considered for inclusion. Co-primary outcomes were 30-day mortality and morbidity. Secondary outcomes included intraoperative and perioperative RBC transfusion. Meta-analysis was carried out using random-effects models. RESULTS Fourteen trials (8641 patients) were included. One cardiac surgery trial accounted for 56% of patients. There was no difference in 30-day mortality [relative risk (RR) 0.96, 95% confidence interval (CI) 0.71-1.29] and pooled postoperative morbidity among the studied outcomes when comparing restrictive and liberal protocols. Two trials reported worse composite outcomes with restrictive triggers. Intraoperative (RR 0.53, 95% CI 0.43-0.64) and perioperative (RR 0.70, 95% CI 0.62-0.79) blood transfusions were significantly lower in the restrictive group compared to the liberal group. CONCLUSIONS Intraoperative restrictive transfusion strategies decreased perioperative transfusions without added postoperative morbidity and mortality in 12/14 trials. Two trials reported worse outcomes. Given trial design and generalizability limitations, uncertainty remains regarding the safety of broad application of restrictive transfusion triggers in the operating room. Trials specifically designed to address intraoperative transfusions are urgently needed.
Collapse
Affiliation(s)
- Tori Lenet
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
| | - Laura Baker
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
| | - Lily Park
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
| | - Michael Vered
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
| | - Amin Zahrai
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
| | - Risa Shorr
- Library Services, The Ottawa Hospital, Ottawa, ON, Canada
| | | | - Daniel I McIsaac
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
- Department of Anesthesiology, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
| | - Alan Tinmouth
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
- Department of Medicine, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Canadian Blood Services, Ottawa, ON, Canada
| | - Dean A Fergusson
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
- Department of Medicine, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Canadian Blood Services, Ottawa, ON, Canada
| | - Guillaume Martel
- Department of Surgery, The Ottawa Hospital, University of Ottawa, Ottawa, ON, Canada
- Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
| |
Collapse
|