University Hospital of Non-Commercial Joint-Stock Company "Semey Medical University", 1a, Ivan Sechenov str, Semey city, 071400, Republic of Kazakhstan.
Center of habilitation and rehabilitation of persons with disabilities of the Abai region, 109, Karagaily, Semey city, 071400, Republic of Kazakhstan.
BMC Med Inform Decis Mak. 2024 Aug 27;24(1):235. doi: 10.1186/s12911-024-02640-x.
Systemic inflammatory response syndrome (SIRS) is a predictor of serious infectious complications, organ failure, and death in patients with severe polytrauma and is one of the reasons for delaying early total surgical treatment. To determine the risk of SIRS within 24 h after hospitalization, we developed six machine learning models.
Using retrospective data about the patient, the nature of the injury, the results of general and standard biochemical blood tests, and coagulation tests, six models were developed: decision tree, random forest, logistic regression, support vector and gradient boosting classifiers, logistic regressor, and neural network. The effectiveness of the models was assessed through internal and external validation.
Among the 439 selected patients with severe polytrauma in 230 (52.4%), SIRS was diagnosed within the first 24 h of hospitalization. The SIRS group was more strongly associated with class II bleeding (39.5% vs. 60.5%; OR 1.81 [95% CI: 1.23-2.65]; P = 0.0023), long-term vasopressor use (68.4% vs. 31.6%; OR 5.51 [95% CI: 2.37-5.23]; P < 0.0001), risk of acute coagulopathy (67.8% vs. 32.2%; OR 2.4 [95% CI: 1.55-3.77]; P < 0.0001), and greater risk of pneumonia (59.5% vs. 40.5%; OR 1.74 [95% CI: 1.19-2.54]; P = 0.0042), longer ICU length of stay (5 ± 6.3 vs. 2.7 ± 4.3 days; P < 0.0001) and mortality rate (64.5% vs. 35.5%; OR 10.87 [95% CI: 6.3-19.89]; P = 0.0391). Of all the models, the random forest classifier showed the best predictive ability in the internal (AUROC 0.89; 95% CI: 0.83-0.96) and external validation (AUROC 0.83; 95% CI: 0.75-0.91) datasets.
The developed model made it possible to accurately predict the risk of developing SIRS in the early period after injury, allowing clinical specialists to predict patient management tactics and calculate medication and staffing needs for the patient.
Level 3.
The study was retrospectively registered in the ClinicalTrials.gov database of the National Library of Medicine (NCT06323096).
全身炎症反应综合征（SIRS）是严重多发伤患者发生严重感染并发症、器官衰竭和死亡的预测因素，也是延迟早期全面手术治疗的原因之一。为了确定住院后 24 小时内发生 SIRS 的风险，我们开发了六个机器学习模型。
使用患者的回顾性数据、损伤性质、一般和标准生化血液检查以及凝血检查结果，开发了六个模型：决策树、随机森林、逻辑回归、支持向量和梯度提升分类器、逻辑回归器和神经网络。通过内部和外部验证评估模型的有效性。
在 230 名（52.4%）严重多发伤患者中，有 439 名患者在住院后 24 小时内被诊断为 SIRS。SIRS 组与 II 级出血（39.5% vs. 60.5%；OR 1.81 [95% CI: 1.23-2.65]；P=0.0023）、长期使用血管加压药（68.4% vs. 31.6%；OR 5.51 [95% CI: 2.37-5.23]；P<0.0001）、急性凝血病风险（67.8% vs. 32.2%；OR 2.4 [95% CI: 1.55-3.77]；P<0.0001）和肺炎风险（59.5% vs. 40.5%；OR 1.74 [95% CI: 1.19-2.54]；P=0.0042）之间的关联更强，入住 ICU 的时间更长（5±6.3 天 vs. 2.7±4.3 天；P<0.0001），死亡率更高（64.5% vs. 35.5%；OR 10.87 [95% CI: 6.3-19.89]；P=0.0391）。在所有模型中，随机森林分类器在内部（AUROC 0.89；95% CI: 0.83-0.96）和外部验证（AUROC 0.83；95% CI: 0.75-0.91）数据集上均显示出最佳的预测能力。
该模型可以准确预测损伤后早期发生 SIRS 的风险，使临床专家能够预测患者的管理策略，并计算患者的用药和人员配备需求。
3 级。
该研究在国家医学图书馆的 ClinicalTrials.gov 数据库中进行了回顾性注册（NCT06323096）。
