Machine Learning Algorithms for Objective Remission and Clinical Outcomes with Thiopurines
Machine Learning Algorithms for Objective Remission and Clinical Outcomes with Thiopurines
复制标题
DOI：
10.1093/ecco-jcc/jjx014
复制
发表时间：
2017-07-01
影响因子：
8
通讯作者：
Higgins, Peter D. R.
中科院分区：
文献类型：
--
作者：
Waljee, Akbar K.;Sauder, Kay;Higgins, Peter D. R.
背景和目标：大数据分析利用数据中的模式来收集有价值的信息，但很少在临床护理中实施。优化炎症性肠病[IBD]的巯基嘌呤治疗已被证明是困难的。目前使用6-硫代鸟嘌呤核苷酸[6 TGN]代谢物的方法在随机对照试验[RCT]中失败，并且尚未用于预测客观缓解[ OR]。我们的目标是：1）使用实验室值和年龄开发机器学习算法[MLA]，以识别使用硫嘌呤的客观缓解患者; 2）确定实现算法预测的客观缓解是否会导致每年更少的临床事件。方法：客观缓解定义为缺乏肠道炎症的客观证据。开发MLAs以预测三种结局：客观缓解、不依从和优先分流至6-甲巯基嘌呤[6-MMP]。使用受试者工作特征曲线下面积[AuROC]评价算法的性能。新的类固醇处方，住院，腹部手术的临床事件率measured.Results：回顾性分析1080 IBD患者的巯基嘌呤的医疗记录进行。验证集中算法预测缓解的AuROC为0.79，6-TGN为0.49。持续算法预测缓解（APR）患者每年的平均临床事件数为1.08，而非持续APR患者为3.95 [p < 1 x 10（-5）]。算法预测缓解的个体终点类固醇处方/年[-1.63，p < 1 x 10（-5）]、住院/年[-1.05，p < 1 x 10（-5）]和手术/年[-0.19，p = 0.065]减少。机器学习算法能够识别使用硫嘌呤的IBD患者，其具有算法预测的客观缓解，这种状态与显着的临床益处相关，包括减少类固醇处方，住院，还有手术
Background and Aims: Big data analytics leverage patterns in data to harvest valuable information, but are rarely implemented in clinical care. Optimising thiopurine therapy for inflammatory bowel disease [IBD] has proved difficult. Current methods using 6-thioguanine nucleotide [6TGN] metabolites have failed in randomized controlled trials [RCTs], and have not been used to predict objective remission [ OR]. Our aims were to: 1) develop machine learning algorithms [MLA] using laboratory values and age to identify patients in objective remission on thiopurines; and 2) determine whether achieving algorithm-predicted objective remission resulted in fewer clinical events per year.Methods: Objective remission was defined as the absence of objective evidence of intestinal inflammation. MLAs were developed to predict three outcomes: objective remission, nonadherence, and preferential shunting to 6-methylmercaptopurine [6-MMP]. The performance of the algorithms was evaluated using the area under the receiver operating characteristic curve [AuROC]. Clinical event rates of new steroid prescriptions, hospitalisations, and abdominal surgeries were measured.Results: Retrospective review was performed on medical records of 1080 IBD patients on thiopurines. The AuROC for algorithm-predicted remission in the validation set was 0.79 vs 0.49 for 6-TGN. The mean number of clinical events per year in patients with sustained algorithm-predicted remission [APR] was 1.08 vs 3.95 in those that did not have sustained APR [p < 1 x 10(-5)]. Reductions in the individual endpoints of steroid prescriptions/year [-1.63, p < 1 x 10(-5)], hospitalisations/year [-1.05, p < 1 x 10(-5)], and surgeries/year [-0.19, p = 0.065] were seen with algorithm-predicted remission.Conclusions: A machine learning algorithm was able to identify IBD patients on thiopurines with algorithm-predicted objective remission, a state associated with significant clinical benefits, including decreased steroid prescriptions, hospitalisations, and surgeries.