PDF(Pubmed)
Abstract：
OBJECTIVE: We aimed to use machine learning (ML) algorithms with clinical, lab, and imaging data as input to predict various outcomes in traumatic brain injury (TBI) patients.
METHODS: In this retrospective study, blood samples were analyzed for glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1). The non-contrast head CTs were reviewed by two neuroradiologists for TBI common data elements (CDE). Three outcomes were designed to predict: discharged or admitted for further management (prediction 1), deceased or not deceased (prediction 2), and admission only, prolonged stay, or neurosurgery performed (prediction 3). Five ML models were trained. SHapley Additive exPlanations (SHAP) analyses were used to assess the relative significance of variables.
RESULTS: Four hundred forty patients were used to predict predictions 1 and 2, while 271 patients were used in prediction 3. Due to Prediction 3\'s hospitalization requirement, deceased and discharged patients could not be utilized. The Random Forest model achieved an average accuracy of 1.00 for prediction 1 and an accuracy of 0.99 for prediction 2. The Random Forest model achieved a mean accuracy of 0.93 for prediction 3. Key features were extracranial injury, hemorrhage, UCH-L1 for prediction 1; The Glasgow Coma Scale, age, GFAP for prediction 2; and GFAP, subdural hemorrhage volume, and pneumocephalus for prediction 3, per SHAP analysis.
CONCLUSIONS: Combining clinical and laboratory parameters with non-contrast CT CDEs allowed our ML models to accurately predict the designed outcomes of TBI patients. GFAP and UCH-L1 were among the significant predictor variables, demonstrating the importance of these biomarkers.
METHODS: In this retrospective study, blood samples were analyzed for glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1). The non-contrast head CTs were reviewed by two neuroradiologists for TBI common data elements (CDE). Three outcomes were designed to predict: discharged or admitted for further management (prediction 1), deceased or not deceased (prediction 2), and admission only, prolonged stay, or neurosurgery performed (prediction 3). Five ML models were trained. SHapley Additive exPlanations (SHAP) analyses were used to assess the relative significance of variables.
RESULTS: Four hundred forty patients were used to predict predictions 1 and 2, while 271 patients were used in prediction 3. Due to Prediction 3\'s hospitalization requirement, deceased and discharged patients could not be utilized. The Random Forest model achieved an average accuracy of 1.00 for prediction 1 and an accuracy of 0.99 for prediction 2. The Random Forest model achieved a mean accuracy of 0.93 for prediction 3. Key features were extracranial injury, hemorrhage, UCH-L1 for prediction 1; The Glasgow Coma Scale, age, GFAP for prediction 2; and GFAP, subdural hemorrhage volume, and pneumocephalus for prediction 3, per SHAP analysis.
CONCLUSIONS: Combining clinical and laboratory parameters with non-contrast CT CDEs allowed our ML models to accurately predict the designed outcomes of TBI patients. GFAP and UCH-L1 were among the significant predictor variables, demonstrating the importance of these biomarkers.
摘要：
目标：我们的目标是将机器学习(ML)算法与临床、实验室,和影像学数据作为输入，以预测创伤性脑损伤（TBI）患者的各种结果。
方法：在这项回顾性研究中，分析血液样本中的神经胶质纤维酸性蛋白(GFAP)和泛素C末端水解酶L1(UCH-L1).两名神经放射科医生针对TBI常见数据元素（CDE）审查了非对比头部CT。设计了三个结果来预测：出院或入院接受进一步管理(预测1)，死亡或未死亡(预测2)，只有入场，长时间逗留,或进行神经外科手术（预测3）。训练了五个ML模型。Shapley加性扩张（SHAP）分析用于评估变量的相对重要性。
结果：440名患者用于预测预测1和2，而271名患者用于预测3。由于预测3的住院要求，死者和出院病人无法使用。随机森林模型实现了预测1的平均准确度为1.00，预测2的准确度为0.99。随机森林模型实现了预测3的平均准确度为0.93。主要特征是颅外损伤，出血,用于预测1的UCH-L1；格拉斯哥昏迷量表，年龄,预测2的GFAP；和GFAP，硬膜下出血量,根据SHAP分析，预测3为气颅。
结论：将临床和实验室参数与非对比CTCDE相结合，使我们的ML模型能够准确预测TBI患者的设计结果。GFAP和UCH-L1是重要的预测变量，证明了这些生物标志物的重要性。
方法：在这项回顾性研究中，分析血液样本中的神经胶质纤维酸性蛋白(GFAP)和泛素C末端水解酶L1(UCH-L1).两名神经放射科医生针对TBI常见数据元素（CDE）审查了非对比头部CT。设计了三个结果来预测：出院或入院接受进一步管理(预测1)，死亡或未死亡(预测2)，只有入场，长时间逗留,或进行神经外科手术（预测3）。训练了五个ML模型。Shapley加性扩张（SHAP）分析用于评估变量的相对重要性。
结果：440名患者用于预测预测1和2，而271名患者用于预测3。由于预测3的住院要求，死者和出院病人无法使用。随机森林模型实现了预测1的平均准确度为1.00，预测2的准确度为0.99。随机森林模型实现了预测3的平均准确度为0.93。主要特征是颅外损伤，出血,用于预测1的UCH-L1；格拉斯哥昏迷量表，年龄,预测2的GFAP；和GFAP，硬膜下出血量,根据SHAP分析，预测3为气颅。
结论：将临床和实验室参数与非对比CTCDE相结合，使我们的ML模型能够准确预测TBI患者的设计结果。GFAP和UCH-L1是重要的预测变量，证明了这些生物标志物的重要性。
