开发和验证用于预测儿童和青少年创伤后神经外科干预的贝叶斯网络。
Development and validation of a Bayesian network predicting neurosurgical intervention after injury in children and adolescents.
机构信息
From the Division of Trauma and Burn Surgery (T.M.S., G.J.S., E.A.M., W.V.G.-T., R.S.B.), Children's National Hospital, Washington, DC; Division of Electrical Engineering and Computer Science (D.O.), Massachusetts Institute of Technology, Boston, Massachusetts; Department of Neurological Surgery (C.O.), Children's National Hospital, Washington, DC; Department of Biomedical Informatics (P.E.D., T.D.B.), University of Colorado School of Medicine; Department of Pediatrics (P.E.D., T.D.B, M.A.C.) Children's Hospital of Colorado, Aurora, Colorado.
出版信息
J Trauma Acute Care Surg. 2023 Jun 1;94(6):839-846. doi: 10.1097/TA.0000000000003935. Epub 2023 Mar 7.
BACKGROUND
Timely surgical decompression improves functional outcomes and survival among children with traumatic brain injury and increased intracranial pressure. Previous scoring systems for identifying the need for surgical decompression after traumatic brain injury in children and adults have had several barriers to use. These barriers include the inability to generate a score with missing data, a requirement for radiographic imaging that may not be immediately available, and limited accuracy. To address these limitations, we developed a Bayesian network to predict the probability of neurosurgical intervention among injured children and adolescents (aged 1-18 years) using physical examination findings and injury characteristics observable at hospital arrival.
METHODS
We obtained patient, injury, transportation, resuscitation, and procedure characteristics from the 2017 to 2019 Trauma Quality Improvement Project database. We trained and validated a Bayesian network to predict the probability of a neurosurgical intervention, defined as undergoing a craniotomy, craniectomy, or intracranial pressure monitor placement. We evaluated model performance using the area under the receiver operating characteristic and calibration curves. We evaluated the percentage of contribution of each input for predicting neurosurgical intervention using relative mutual information (RMI).
RESULTS
The final model included four predictor variables, including the Glasgow Coma Scale score (RMI, 31.9%), pupillary response (RMI, 11.6%), mechanism of injury (RMI, 5.8%), and presence of prehospital cardiopulmonary resuscitation (RMI, 0.8%). The model achieved an area under the receiver operating characteristic curve of 0.90 (95% confidence interval [CI], 0.89-0.91) and had a calibration slope of 0.77 (95% CI, 0.29-1.26) with a y intercept of 0.05 (95% CI, -0.14 to 0.25).
CONCLUSION
We developed a Bayesian network that predicts neurosurgical intervention for all injured children using four factors immediately available on arrival. Compared with a binary threshold model, this probabilistic model may allow clinicians to stratify management strategies based on risk.
LEVEL OF EVIDENCE
Prognostic and Epidemiological; Level III.
背景
对于颅内压增高的创伤性脑损伤患儿，及时进行手术减压可改善其功能结局和生存情况。既往用于识别儿童和成人创伤性脑损伤后是否需要手术减压的评分系统存在多种使用障碍。这些障碍包括：无法在数据缺失的情况下生成评分，需要可能无法立即获得的影像学检查，以及准确性有限。为了解决这些局限性，我们开发了一个贝叶斯网络，利用入院时可观察到的体格检查结果和损伤特征，来预测受伤儿童和青少年（1-18 岁）接受神经外科干预的概率。
方法
我们从 2017 年至 2019 年创伤质量改进项目数据库中获取了患者、损伤、转运、复苏和手术特征。我们使用贝叶斯网络对预测神经外科干预的概率进行了训练和验证，神经外科干预的定义为进行开颅术、颅骨切除术或颅内压监测。我们使用接收者操作特征曲线和校准曲线下面积来评估模型性能。我们使用相对互信息（RMI）评估每个输入预测神经外科干预的贡献百分比。
结果
最终模型包含四个预测变量，包括格拉斯哥昏迷评分（RMI，31.9%）、瞳孔反应（RMI，11.6%）、损伤机制（RMI，5.8%）和院前心肺复苏的存在（RMI，0.8%）。该模型的受试者工作特征曲线下面积为 0.90（95%置信区间 [CI]，0.89-0.91），校准斜率为 0.77（95%CI，0.29-1.26），y 截距为 0.05（95%CI，-0.14 至 0.25）。
结论
我们开发了一个贝叶斯网络，使用入院时即可获得的四个因素预测所有受伤儿童的神经外科干预。与二元阈值模型相比，这种概率模型可以让临床医生根据风险分层管理策略。
证据等级
预后和流行病学；III 级。
Zotero 插件