深度神经网络预测儿童轻度创伤性脑损伤CT检查需求:对PECARN规则的验证
本研究应用深度人工神经网络和实例硬度阈值算法,在2004至2006年PECARN研究中14,983例18岁以下、Glasgow昏迷量表评分≥14分且有头部CT报告的患儿中复现PECARN临床规则。模型在第一阶段联合两套PECARN规则预测因子训练时敏感度98.6%、特异度99.7%;第二阶段按年龄组分别训练时,A组模型平均敏感度93.7% vs 规则100%、平均特异度97.5% vs 规则53.6%,B组模型平均敏感度99.2% vs 规则98.6%、特异度98.8% vs 规则58.2%。
要点
- DANN模型在联合PECARN-A和PECARN-B预测因子训练时,预测CT需求的敏感度98.6%、特异度99.7%。
- 按年龄组分别训练时,B组(年龄≤2岁)模型平均敏感度99.2% vs PECARN-B规则98.6%,平均特异度98.8% vs 58.2%。
- A组(年龄<2岁)模型平均敏感度93.7% vs PECARN-A规则100%,平均特异度97.5% vs 53.6%。
核心结论
- 深度人工神经网络模型在复现PECARN临床规则、预测儿童轻度创伤性脑损伤后CT检查需求方面,达到了与原始统计学推导临床规则相当的敏感度和突出的特异度。
研究设计与样本
- 研究应用深度人工神经网络模型和实例硬度阈值算法,数据来自2004至2006年PECARN研究收集的儿科人群。
- 纳入14,983例18岁以下、Glasgow昏迷量表评分≥14分且有头部CT报告的患者。
- 使用PECARN-A(A组,年龄<2岁)和PECARN-B(B组,年龄≤2岁)的临床特征直接评估模型。
- 通过比较模型预测结果与PECARN研究者报告结果,计算平均准确率、敏感度、精确率和特异度。
- 采用5折交叉验证预测儿科患者CT检查需求。
诊断标准与关键数值
- 第一阶段:DANN模型联合两套PECARN临床规则预测因子训练,预测CT需求的敏感度98.6%、特异度99.7%。
- 第二阶段A组:DANN模型平均敏感度93.7% vs PECARN-A规则100%,平均特异度97.5% vs PECARN-A规则53.6%。
- 第二阶段B组:DANN模型平均敏感度99.2% vs PECARN-B规则98.6%,平均特异度98.8% vs PECARN-B规则58.2%。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: Only 10% of CT scans unveil positive findings in mild traumatic brain injury, raising concerns of its overuse in this population. A number of clinical rules have been developed to address this issue, but they still suffer limitations in their specificity. Machine learning models have been applied in limited studies to mimic clinical rules; however, further improvement in terms of balanced sensitivity and specificity is still needed. In this work, the authors applied a deep artificial neural networks (DANN) model and an instance hardness threshold algorithm to reproduce the Pediatric Emergency Care Applied Research Network (PECARN) clinical rule in a pediatric population collected as a part of the PECARN study between 2004 and 2006.
METHODS: The DANN model was applied using 14,983 patients younger than 18 years with Glasgow Coma Scale scores ≥ 14 who had head CT reports. The clinical features of the PECARN rules, PECARN-A (group A, age < 2 years) and PECARN-B (group B, age ≤ 2 years), were used to directly evaluate the model. The average accuracy, sensitivity, precision, and specificity were calculated by comparing the model's prediction outcome to that reported by the PECARN investigators. The instance hardness threshold and DANN model were applied to predict the need for CT in pediatric patients using 5-fold cross-validation.
RESULTS: In the first phase, the DANN model resulted in 98.6% sensitivity and 99.7% specificity for predicting the need for CT using the predictors of the two PECARN clinical rules combined to train the model. In the second phase, the DANN model was superior to both the PECARN-A and PECARN-B rules using the predictors for each age group separately to train the model. Compared with the clinical rule, for group A, the model achieved an average sensitivity (93.7% versus 100%) and specificity (97.5% versus 53.6%); for group B, the average sensitivity of the model was 99.2% versus 98.6%, and the specificity was 98.8% versus 58.2%.
CONCLUSIONS: In this study, a DANN model achieved comparable sensitivity and outstanding specificity for replicating the PECARN clinical rule and predicting the need for CT in pediatric patients after mild traumatic brain injury compared with the original statistically derived clinical rule.
引用
- Ellethy, Chandra, Nasrallah, et al. Deep Neural Networks Predict the Need for CT in Pediatric Mild Traumatic Brain Injury: A Corroboration of the PECARN Rule. J Am Coll Radiol. 2022. PMID: 35381190. doi:10.1016/j.jacr.2022.02.024
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。