Classification and Prediction of Post-Trauma Outcomes Related to PTSD Using Circadian Rhythm Changes Measured via Wrist-Worn Research Watch in a Large Longitudinal Cohort.
Classification and Prediction of Post-Trauma Outcomes Related to PTSD Using Circadian Rhythm Changes Measured via Wrist-Worn Research Watch in a Large Longitudinal Cohort.
复制标题
DOI：
10.1109/jbhi.2021.3053909
复制
发表时间：
2021-08
影响因子：
7.7
通讯作者：
Clifford GD
中科院分区：
文献类型：
--
作者：
Cakmak AS;Alday EAP;Da Poian G;Rad AB;Metzler TJ;Neylan TC;House SL;Beaudoin FL;An X;Stevens JS;Zeng D;Linnstaedt SD;Jovanovic T;Germine LT;Bollen KA;Rauch SL;Lewandowski CA;Hendry PL;Sheikh S;Storrow AB;Musey PI;Haran JP;Jones CW;Punches BE;Swor RA;Gentile NT;McGrath ME;Seamon MJ;Mohiuddin K;Chang AM;Pearson C;Domeier RM;Bruce SE;O'Neil BJ;Rathlev NK;Sanchez LD;Pietrzak RH;Joormann J;Barch DM;Pizzagalli DA;Harte SE;Elliott JM;Kessler RC;Koenen KC;Ressler KJ;Mclean SA;Li Q;Clifford GD
创伤后应激障碍（PTSD）是一种由威胁或恐怖事件引起的精神疾病。我们假设，通过佩戴在手腕上的研究手表测量的昼夜节律变化可以预测创伤后的结果。方法：1618例外伤后急诊科（ED）入院患者。在第8周进行了三份标准化问卷调查，以测量与创伤后应激障碍、睡眠障碍和疼痛对日常生活的干扰有关的创伤后结果。研究人员从研究手表上采集了8周的脉搏活动和运动数据。反映昼夜节律的标准和新颖的运动和心血管指标是利用这些数据得出的。这些特征被用来训练不同的分类器来预测从第8周的调查中得出的三个结果。在ED进行的临床调查也被用作基线模型的特征。结果：通过logistic回归模型对疼痛干扰受试者进行分类时，基于研究手表的特征获得了最高的交叉验证性能，受试者工作特征曲线下面积（AUC）为0.70。基于ED调查的模型的AUC为0.77，研究观察和ED调查指标的融合将AUC提高到0.79。意义：这项工作首次尝试利用机器学习方法，利用潜在创伤后应激障碍人群的昼夜节律不同步，从被动可穿戴数据中预测和分类创伤后症状。
Post-Traumatic Stress Disorder (PTSD) is a psychiatric condition resulting from threatening or horrifying events. We hypothesized that circadian rhythm changes, measured by a wrist-worn research watch are predictive of post-trauma outcomes. Approach: 1618 post-trauma patients were enrolled after admission to emergency departments (ED). Three standardized questionnaires were administered at week eight to measure post-trauma outcomes related to PTSD, sleep disturbance, and pain interference with daily life. Pulse activity and movement data were captured from a research watch for eight weeks. Standard and novel movement and cardiovascular metrics that reflect circadian rhythms were derived using this data. These features were used to train different classifiers to predict the three outcomes derived from week-eight surveys. Clinical surveys administered at ED were also used as features in the baseline models. Results: The highest cross-validated performance of research watch-based features was achieved for classifying participants with pain interference by a logistic regression model, with an area under the receiver operating characteristic curve (AUC) of 0.70. The ED survey-based model achieved an AUC of 0.77, and the fusion of research watch and ED survey metrics improved the AUC to 0.79. Significance: This work represents the first attempt to predict and classify post-trauma symptoms from passive wearable data using machine learning approaches that leverage the circadian desynchrony in a potential PTSD population.