PDF
Full
Outline
Objective To explore the risk factors of thrombotic events in trauma patients by using random forest algorithm. Methods The data of 255 trauma patients admitted to the intensive care unit from July 2016 to December 2021 were retrospectively analyzed. These patients were divided into thrombosis group and non-thrombosis group by propensity score matching and according to the occurrence of thrombosis after trauma. The risk factors of 24 clinical variables including age, gender, injury severity score (ISS), acute physiology and chronic health evaluation Ⅱ (APACHE Ⅱ), white blood cell count, red blood cell count, platelet count, hemoglobin, alanine aminotransferase, aspartate aminotransferase, total bilirubin, creatinine, total protein, prothrombin time, activated partial thromboplastin time, thrombin time, fibrinogen, fibrin degradation products, D-dimer, antithrombin 3, coagulation reaction time (CRT), clot formation rate, clot formation kinetics and maximum clot strength (maximal amplitude, MA) within 2 hours after admission were analyzed by random forest algorithm. The predictive values of the variables were evaluated by receiver operating characteristic (ROC) curve and verified by bootstrap method. Results One hundred and ten trauma patients were divided into thrombosis group (n=22) and non-thrombosis group (n=88) by propensity score matching. The results of random forest algorithms showed that high MA level was an important risk factor for thrombotic events after trauma(P<0.05). The area under ROC curve (AUC) of using MA value to predict thrombotic events in trauma patients was 0.70 (95%CI 0.56-0.81, P<0.01), and the bootstrap method confirmed that the AUC of using MA value to predict thrombotic events in trauma patients was 0.70 (95%CI 0.57-0.80, P<0.01). When the cut-off value of MA was 63.3 mm, the sensitivity and specificity of the trauma patients suffering thrombotic events were 63.6% and 78.4%, respectively. Conclusion The high MA level is an important risk factor for thrombotic events in trauma patients.
PDF
199
88
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
