Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study.
Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study.
复制标题
整合无监督和监督学习技术来预测创伤性脑损伤：一项基于人群的研究。
DOI：
10.1016/j.ibmed.2023.100118
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Escobar,Michael
中科院分区：
文献类型：
--
作者：
Zulbayar,Suvd;Mollayeva,Tatyana;Colantonio,Angela;Chan,Vincy;Escobar,Michael
这项工作旨在识别创伤性脑损伤(TBI)患者先前存在的健康状况，并采用无监督学习算法和监督学习算法相结合的方法，建立第一次TBI事件及其外部原因的预测模型。我们获得了2002年4月1日至2020年3月31日期间在急诊科或急性护理医院就诊的488,107名脑损伤患者和488,107名匹配的对照组患者长达5年的伤前诊断。诊断是从安大略省健康保险计划(OHIP)数据库中获得的，该数据库包含加拿大安大略省医生关于住院和门诊服务的全省索赔数据。对OHIP诊断代码进行了筛选过程，以将后续分析限制在预测TBI的代码上，得出结论：314个代码与TBI显著相关。潜在狄利克雷分配(LDA)模型被应用于诊断代码，并产生了19个主题的最佳数量，这些主题与已发表的文献一致，但也建议其他未探索的领域。LDA模型中估计的词-主题概率通过揭示潜在的诊断模式帮助我们检测脑外伤患者的发病前状况，同时估计的文档-主题概率被用于变量创建作为降维的形式。我们为队列中的每个患者创建了19个主题分数，并将其与社会人口因素一起用于随机森林二进制分类器模型。使用接收器操作特征曲线下面积(AUC)评估的测试集性能为：TBI事件(AUC=60.85)，外部伤害原因：跌倒(AUC=60.85)，被/反对击中(AUC=60.83)，骑自行车碰撞(AUC=60.76)，机动车碰撞(AUC=60.83)。我们的分析成功地证明了使用机器学习来预测各种外部原因造成的脑损伤的可行性，并确定了影响这一预测的最重要的因素。
This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.