An Sungtae, Malhotra Kunal, Dilley Cynthia, Han-Burgess Edward, Valdez Jeffrey N, Robertson Joseph, Clark Chris, Westover M Brandon, Sun Jimeng
Georgia Institute of Technology, College of Computing, Atlanta, GA, USA.
UCB Pharma, Smyrna, GA, USA.
Epilepsy Behav. 2018 Dec;89:118-125. doi: 10.1016/j.yebeh.2018.10.013. Epub 2018 Nov 7.
Patients with drug-resistant epilepsy (DRE) are at high risk of morbidity and mortality, yet their referral to specialist care is frequently delayed. The ability to identify patients at high risk of DRE at the time of treatment initiation, and to subsequently steer their treatment pathway toward more personalized interventions, has high clinical utility. Here, we aim to demonstrate the feasibility of developing algorithms for predicting DRE using machine learning methods. Longitudinal, intersected data sourced from US pharmacy, medical, and adjudicated hospital claims from 1,376,756 patients from 2006 to 2015 were analyzed; 292,892 met inclusion criteria for epilepsy, and 38,382 were classified as having DRE using a proxy measure for drug resistance. Patients were characterized using 1270 features reflecting demographics, comorbidities, medications, procedures, epilepsy status, and payer status. Data from 175,735 randomly selected patients were used to train three algorithms and from the remainder to assess the trained models' predictive power. A model with only age and sex was used as a benchmark. The best model, random forest, achieved an area under the receiver operating characteristic curve (95% confidence interval [CI]) of 0.764 (0.759, 0.770), compared with 0.657 (0.651, 0.663) for the benchmark model. Moreover, predicted probabilities for DRE were well-calibrated with the observed frequencies in the data. The model predicted drug resistance approximately 2 years before patients in the test dataset had failed two antiepileptic drugs (AEDs). Machine learning models constructed using claims data predicted which patients are likely to fail ≥3 AEDs and are at risk of developing DRE at the time of the first AED prescription. The use of such models can ensure that patients with predicted DRE receive specialist care with potentially more aggressive therapeutic interventions from diagnosis, to help reduce the serious sequelae of DRE.
耐药性癫痫（DRE）患者的发病和死亡风险很高，然而他们转诊至专科护理往往会延迟。在开始治疗时识别出有DRE高风险的患者，并随后引导他们的治疗路径走向更个性化的干预措施，具有很高的临床实用性。在此，我们旨在证明使用机器学习方法开发预测DRE算法的可行性。分析了2006年至2015年来自美国药房、医疗和已判定的医院理赔数据的纵向交叉数据，这些数据来自1376756名患者；292892名符合癫痫纳入标准，38382名使用耐药性替代指标被归类为患有DRE。使用1270个反映人口统计学、合并症、药物治疗、手术、癫痫状态和付款人状态的特征对患者进行表征。来自175735名随机选择患者的数据用于训练三种算法，其余数据用于评估训练模型的预测能力。仅包含年龄和性别的模型用作基准。最佳模型随机森林的受试者工作特征曲线下面积（95%置信区间[CI]）为0.764（0.759，0.770），而基准模型为0.657（0.651，0.663）。此外，DRE的预测概率与数据中的观察频率校准良好。该模型在测试数据集中的患者两种抗癫痫药物（AED）治疗失败前约2年预测出耐药性。使用理赔数据构建的机器学习模型预测哪些患者可能≥3种AED治疗失败，并在首次开具AED处方时就有发生DRE的风险。使用此类模型可确保预测为DRE的患者从诊断时起就接受专科护理，并可能采取更积极的治疗干预措施，以帮助减少DRE的严重后遗症。
