Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study
BackgroundRecent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies ha...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-01-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2025/1/e66612 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591245717798912 |
|---|---|
| author | Xiaojuan Xiong Hong Fu Bo Xu Wang Wei Mi Zhou Peng Hu Yunqin Ren Qingxiang Mao |
| author_facet | Xiaojuan Xiong Hong Fu Bo Xu Wang Wei Mi Zhou Peng Hu Yunqin Ren Qingxiang Mao |
| author_sort | Xiaojuan Xiong |
| collection | DOAJ |
| description |
BackgroundRecent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies have explored the risk factors, complications, and risk prediction of preoperative and postoperative traumatic coagulopathy (PPTIC) in patients with trauma.
ObjectiveThis study aims to help clinicians implement timely and appropriate interventions to reduce the incidence of PPTIC and related complications, thereby lowering in-hospital mortality and disability rates for patients with trauma.
MethodsWe analyzed data from 13,235 patients with trauma from 4 medical centers, including medical histories, laboratory results, and hospitalization complications. We developed 10 ML models in Python (Python Software Foundation) to predict PPTIC based on preoperative indicators. Data from 10,023 Medical Information Mart for Intensive Care patients were divided into training (70%) and test (30%) sets, with 3212 patients from 3 other centers used for external validation. Model performance was assessed with 5-fold cross-validation, bootstrapping, Brier score, and Shapley additive explanation values.
ResultsUnivariate logistic regression identified PPTIC risk factors as (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) decreased levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) lower admission diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) emergency surgery and perioperative transfusion. Multivariate logistic regression revealed that patients with PPTIC faced significantly higher risks of sepsis (1.75-fold), heart failure (1.5-fold), delirium (3.08-fold), abnormal coagulation (3.57-fold), tracheostomy (2.76-fold), mortality (2.19-fold), and urinary tract infection (1.95-fold), along with longer hospital and intensive care unit stays. Random forest was the most effective ML model for predicting PPTIC, achieving an area under the receiver operating characteristic of 0.91, an area under the precision-recall curve of 0.89, accuracy of 0.84, sensitivity of 0.80, specificity of 0.88, precision of 0.88, F1-score of 0.84, and Brier score of 0.13 in external validation.
ConclusionsKey PPTIC risk factors include (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) low levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) low diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) the need for emergency surgery and transfusion. PPTIC is associated with severe complications and extended hospital stays. Among the ML models, the random forest model was the most effective predictor.
Trial RegistrationChinese Clinical Trial Registry ChiCTR2300078097; https://www.chictr.org.cn/showproj.html?proj=211051 |
| format | Article |
| id | doaj-art-9416799819554c1498bce7e87b30ccf3 |
| institution | Kabale University |
| issn | 1438-8871 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj-art-9416799819554c1498bce7e87b30ccf32025-01-22T16:00:33ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-01-0127e6661210.2196/66612Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort StudyXiaojuan Xionghttps://orcid.org/0000-0002-5693-0544Hong Fuhttps://orcid.org/0000-0003-2863-3996Bo Xuhttps://orcid.org/0000-0003-2159-0575Wang Weihttps://orcid.org/0000-0001-8608-1822Mi Zhouhttps://orcid.org/0009-0009-6134-6391Peng Huhttps://orcid.org/0009-0009-6468-3115Yunqin Renhttps://orcid.org/0000-0002-8445-8267Qingxiang Maohttps://orcid.org/0000-0002-9268-4846 BackgroundRecent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies have explored the risk factors, complications, and risk prediction of preoperative and postoperative traumatic coagulopathy (PPTIC) in patients with trauma. ObjectiveThis study aims to help clinicians implement timely and appropriate interventions to reduce the incidence of PPTIC and related complications, thereby lowering in-hospital mortality and disability rates for patients with trauma. MethodsWe analyzed data from 13,235 patients with trauma from 4 medical centers, including medical histories, laboratory results, and hospitalization complications. We developed 10 ML models in Python (Python Software Foundation) to predict PPTIC based on preoperative indicators. Data from 10,023 Medical Information Mart for Intensive Care patients were divided into training (70%) and test (30%) sets, with 3212 patients from 3 other centers used for external validation. Model performance was assessed with 5-fold cross-validation, bootstrapping, Brier score, and Shapley additive explanation values. ResultsUnivariate logistic regression identified PPTIC risk factors as (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) decreased levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) lower admission diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) emergency surgery and perioperative transfusion. Multivariate logistic regression revealed that patients with PPTIC faced significantly higher risks of sepsis (1.75-fold), heart failure (1.5-fold), delirium (3.08-fold), abnormal coagulation (3.57-fold), tracheostomy (2.76-fold), mortality (2.19-fold), and urinary tract infection (1.95-fold), along with longer hospital and intensive care unit stays. Random forest was the most effective ML model for predicting PPTIC, achieving an area under the receiver operating characteristic of 0.91, an area under the precision-recall curve of 0.89, accuracy of 0.84, sensitivity of 0.80, specificity of 0.88, precision of 0.88, F1-score of 0.84, and Brier score of 0.13 in external validation. ConclusionsKey PPTIC risk factors include (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) low levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) low diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) the need for emergency surgery and transfusion. PPTIC is associated with severe complications and extended hospital stays. Among the ML models, the random forest model was the most effective predictor. Trial RegistrationChinese Clinical Trial Registry ChiCTR2300078097; https://www.chictr.org.cn/showproj.html?proj=211051https://www.jmir.org/2025/1/e66612 |
| spellingShingle | Xiaojuan Xiong Hong Fu Bo Xu Wang Wei Mi Zhou Peng Hu Yunqin Ren Qingxiang Mao Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study Journal of Medical Internet Research |
| title | Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study |
| title_full | Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study |
| title_fullStr | Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study |
| title_full_unstemmed | Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study |
| title_short | Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study |
| title_sort | ten machine learning models for predicting preoperative and postoperative coagulopathy in patients with trauma multicenter cohort study |
| url | https://www.jmir.org/2025/1/e66612 |
| work_keys_str_mv | AT xiaojuanxiong tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT hongfu tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT boxu tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT wangwei tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT mizhou tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT penghu tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT yunqinren tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy AT qingxiangmao tenmachinelearningmodelsforpredictingpreoperativeandpostoperativecoagulopathyinpatientswithtraumamulticentercohortstudy |