A prediction model for massive hemorrhage in trauma: a retrospective observational study
Abstract Background Massive hemorrhage is the main cause of preventable death after trauma. This study aimed to establish prediction models for early diagnosis of massive hemorrhage in trauma. Methods Using the trauma database of Chinese PLA General Hospital, two logistic regression (LR) models were...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-11-01
|
Series: | BMC Emergency Medicine |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12873-022-00737-y |
_version_ | 1811217693204807680 |
---|---|
author | Chengyu Guo Minghui Gong Lei Ji Fei Pan Hui Han Chunping Li Tanshi Li |
author_facet | Chengyu Guo Minghui Gong Lei Ji Fei Pan Hui Han Chunping Li Tanshi Li |
author_sort | Chengyu Guo |
collection | DOAJ |
description | Abstract Background Massive hemorrhage is the main cause of preventable death after trauma. This study aimed to establish prediction models for early diagnosis of massive hemorrhage in trauma. Methods Using the trauma database of Chinese PLA General Hospital, two logistic regression (LR) models were fit to predict the risk of massive hemorrhage in trauma. Sixty-two potential predictive variables, including clinical symptoms, vital signs, laboratory tests, and imaging results, were included in this study. Variable selection was done using the least absolute shrinkage and selection operator (LASSO) method. The first model was constructed based on LASSO feature selection results. The second model was constructed based on the first vital sign recordings of trauma patients after admission. Finally, a web calculator was developed for clinical use. Results A total of 2353 patients were included in this study. There were 377 (16.02%) patients with massive hemorrhage. The selected predictive variables were heart rate (OR: 1.01; 95% CI: 1.01–1.02; P<0.001), pulse pressure (OR: 0.99; 95% CI: 0.98–0.99; P = 0.004), base excess (OR: 0.90; 95% CI: 0.87–0.93; P<0.001), hemoglobin (OR: 0.95; 95% CI: 0.95–0.96; P<0.001), displaced pelvic fracture (OR: 2.13; 95% CI: 1.48–3.06; P<0.001), and a positive computed tomography scan or positive focused assessment with sonography for trauma (OR: 1.62; 95% CI: 1.21–2.18; P = 0.001). Model 1, which was developed based on LASSO feature selection results and LR, displayed excellent discrimination (AUC: 0.894; 95% CI: 0.875–0.912), good calibration (P = 0.405), and clinical utility. In addition, the predictive power of model 1 was better than that of model 2 (AUC: 0.718; 95% CI: 0.679–0.757). Model 1 was deployed as a public web tool ( http://82.156.217.249:8080/ ). Conclusions Our study developed and validated prediction models to assist medical staff in the early diagnosis of massive hemorrhage in trauma. An open web calculator was developed to facilitate the practical application of the research results. |
first_indexed | 2024-04-12T06:59:01Z |
format | Article |
id | doaj.art-43425fc242dc4aaeba0ab0b14523c705 |
institution | Directory Open Access Journal |
issn | 1471-227X |
language | English |
last_indexed | 2024-04-12T06:59:01Z |
publishDate | 2022-11-01 |
publisher | BMC |
record_format | Article |
series | BMC Emergency Medicine |
spelling | doaj.art-43425fc242dc4aaeba0ab0b14523c7052022-12-22T03:43:03ZengBMCBMC Emergency Medicine1471-227X2022-11-0122111110.1186/s12873-022-00737-yA prediction model for massive hemorrhage in trauma: a retrospective observational studyChengyu Guo0Minghui Gong1Lei Ji2Fei Pan3Hui Han4Chunping Li5Tanshi Li6Present Address: School of Medicine, Nankai UniversitySchool of Software, Tsinghua UniversityDepartment of Information, Medical Supplies Center of PLA General HospitalDepartment of Emergency, First Medical Center, Chinese PLA General HospitalDepartment of Emergency, First Medical Center, Chinese PLA General HospitalSchool of Software, Tsinghua UniversityPresent Address: School of Medicine, Nankai UniversityAbstract Background Massive hemorrhage is the main cause of preventable death after trauma. This study aimed to establish prediction models for early diagnosis of massive hemorrhage in trauma. Methods Using the trauma database of Chinese PLA General Hospital, two logistic regression (LR) models were fit to predict the risk of massive hemorrhage in trauma. Sixty-two potential predictive variables, including clinical symptoms, vital signs, laboratory tests, and imaging results, were included in this study. Variable selection was done using the least absolute shrinkage and selection operator (LASSO) method. The first model was constructed based on LASSO feature selection results. The second model was constructed based on the first vital sign recordings of trauma patients after admission. Finally, a web calculator was developed for clinical use. Results A total of 2353 patients were included in this study. There were 377 (16.02%) patients with massive hemorrhage. The selected predictive variables were heart rate (OR: 1.01; 95% CI: 1.01–1.02; P<0.001), pulse pressure (OR: 0.99; 95% CI: 0.98–0.99; P = 0.004), base excess (OR: 0.90; 95% CI: 0.87–0.93; P<0.001), hemoglobin (OR: 0.95; 95% CI: 0.95–0.96; P<0.001), displaced pelvic fracture (OR: 2.13; 95% CI: 1.48–3.06; P<0.001), and a positive computed tomography scan or positive focused assessment with sonography for trauma (OR: 1.62; 95% CI: 1.21–2.18; P = 0.001). Model 1, which was developed based on LASSO feature selection results and LR, displayed excellent discrimination (AUC: 0.894; 95% CI: 0.875–0.912), good calibration (P = 0.405), and clinical utility. In addition, the predictive power of model 1 was better than that of model 2 (AUC: 0.718; 95% CI: 0.679–0.757). Model 1 was deployed as a public web tool ( http://82.156.217.249:8080/ ). Conclusions Our study developed and validated prediction models to assist medical staff in the early diagnosis of massive hemorrhage in trauma. An open web calculator was developed to facilitate the practical application of the research results.https://doi.org/10.1186/s12873-022-00737-yTraumaMassive hemorrhageLASSOPrediction modelAssisted diagnosis |
spellingShingle | Chengyu Guo Minghui Gong Lei Ji Fei Pan Hui Han Chunping Li Tanshi Li A prediction model for massive hemorrhage in trauma: a retrospective observational study BMC Emergency Medicine Trauma Massive hemorrhage LASSO Prediction model Assisted diagnosis |
title | A prediction model for massive hemorrhage in trauma: a retrospective observational study |
title_full | A prediction model for massive hemorrhage in trauma: a retrospective observational study |
title_fullStr | A prediction model for massive hemorrhage in trauma: a retrospective observational study |
title_full_unstemmed | A prediction model for massive hemorrhage in trauma: a retrospective observational study |
title_short | A prediction model for massive hemorrhage in trauma: a retrospective observational study |
title_sort | prediction model for massive hemorrhage in trauma a retrospective observational study |
topic | Trauma Massive hemorrhage LASSO Prediction model Assisted diagnosis |
url | https://doi.org/10.1186/s12873-022-00737-y |
work_keys_str_mv | AT chengyuguo apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT minghuigong apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT leiji apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT feipan apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT huihan apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT chunpingli apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT tanshili apredictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT chengyuguo predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT minghuigong predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT leiji predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT feipan predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT huihan predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT chunpingli predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy AT tanshili predictionmodelformassivehemorrhageintraumaaretrospectiveobservationalstudy |