Awan Nabil, Kumar Raj G, Juengst Shannon B, DiSanto Dominic, Harrison-Felix Cynthia, Dams-O'Connor Kristen, Pugh Mary Jo, Zafonte Ross D, Walker William C, Szaflarski Jerzy P, Krafty Robert T, Wagner Amy K
Department of Physical Medicine and Rehabilitation, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
Department of Biostatistics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
Epilepsia. 2025 Feb;66(2):482-498. doi: 10.1111/epi.18210. Epub 2024 Dec 10.
Although traumatic brain injury (TBI) and post-traumatic epilepsy (PTE) are common, there are no prospective models quantifying individual epilepsy risk after moderate-to-severe TBI (msTBI). We generated parsimonious prediction models to quantify individual epilepsy risk between acute inpatient rehabilitation for individuals 2 years after msTBI.
We used data from 6089 prospectively enrolled participants (≥16 years) in the TBI Model Systems National Database. Of these, 4126 individuals had complete seizure data collected over a 2-year period post-injury. We performed a case-complete analysis to generate multiple prediction models using least absolute shrinkage and selection operator logistic regression. Baseline predictors were used to assess 2-year seizure risk (Model 1). Then a 2-year seizure risk was assessed excluding the acute care variables (Model 2). In addition, we generated prognostic models predicting new/recurrent seizures during Year 2 post-msTBI (Model 3) and predicting new seizures only during Year 2 (Model 4). We assessed model sensitivity when keeping specificity ≥.60, area under the receiver-operating characteristic curve (AUROC), and AUROC model performance through 5-fold cross-validation (CV).
Model 1 (73.8% men, 44.1 ± 19.7 years, 76.1% moderate TBI) had a model sensitivity = 76.00% and average AUROC = .73 ± .02 in 5-fold CV. Model 2 had a model sensitivity = 72.16% and average AUROC = .70 ± .02 in 5-fold CV. Model 3 had a sensitivity = 86.63% and average AUROC = .84 ± .03 in 5-fold CV. Model 4 had a sensitivity = 73.68% and average AUROC = .67 ± .03 in 5-fold CV. Cranial surgeries, acute care seizures, intracranial fragments, and traumatic hemorrhages were consistent predictors across all models. Demographic and mental health variables contributed to some models. Simulated, clinical examples model individual PTE predictions.
Using information available, acute-care, and year-1 post-injury data, parsimonious quantitative epilepsy prediction models following msTBI may facilitate timely evidence-based PTE prognostication within a 2-year period. We developed interactive web-based tools for testing prediction model external validity among independent cohorts. Individualized PTE risk may inform clinical trial development/design and clinical decision support tools for this population.
虽然创伤性脑损伤（TBI）和创伤后癫痫（PTE）很常见，但尚无前瞻性模型可量化中重度创伤性脑损伤（msTBI）后个体的癫痫风险。我们生成了简约预测模型，以量化msTBI患者急性住院康复期至伤后2年之间的个体癫痫风险。
我们使用了创伤性脑损伤模型系统国家数据库中6089名前瞻性入组参与者（≥16岁）的数据。其中，4126名个体在伤后2年期间收集了完整的癫痫发作数据。我们进行了病例完整分析，使用最小绝对收缩和选择算子逻辑回归生成多个预测模型。基线预测指标用于评估2年癫痫发作风险（模型1）。然后在排除急性护理变量的情况下评估2年癫痫发作风险（模型2）。此外，我们生成了预测msTBI后第2年新的/复发癫痫发作的预后模型（模型3）以及仅预测第2年新癫痫发作的模型（模型4）。我们在保持特异性≥0.60时评估模型敏感性、受试者操作特征曲线下面积（AUROC）以及通过5折交叉验证（CV）的AUROC模型性能。
模型1（73.8%为男性，44.1±19.7岁，76.1%为中度TBI）在5折交叉验证中的模型敏感性 = 76.00%，平均AUROC = 0.73±0.02。模型2在5折交叉验证中的模型敏感性 = 72.16%，平均AUROC = 0.70±0.02。模型3在5折交叉验证中的敏感性 = 86.63%，平均AUROC = 0.84±0.03。模型4在5折交叉验证中的敏感性 = 73.68%，平均AUROC = 0.67±0.03。颅脑手术、急性护理期癫痫发作、颅内碎片和创伤性出血在所有模型中都是一致的预测指标。人口统计学和心理健康变量对一些模型有贡献。模拟的临床实例可对个体PTE预测进行建模。
利用现有的信息、急性护理和伤后第1年的数据，msTBI后的简约定量癫痫预测模型可能有助于在2年内及时进行基于证据的PTE预后评估。我们开发了基于网络的交互式工具，用于测试独立队列中预测模型的外部有效性。个体化的PTE风险可为该人群的临床试验开发/设计和临床决策支持工具提供参考。
