arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.09706cs.AIstat.AP
收藏

从区域EHR数据库开发知识增强的慢性病风险预测模型

Developing Knowledge-enhanced Chronic Disease Risk Prediction Models from Regional EHR Repositories

IBM Research(IBM研究院)

Jing Mei, Eryu Xia, Xiang Li, Guotong Xie

摘要:

精准医疗需要精确的疾病风险预测模型。在文献中,已经有很多成熟的(国际)国家风险模型,但当将它们应用于当地人群时,预测性能变得不令人满意。为了解决本地化的问题,本文探讨的方式来开发知识增强本地化的风险模型。一方面,我们通过从区域电子健康记录(EHR)存储库中学习来调整模型,另一方面,我们提出将知识注入到EHR数据学习过程中。对于实验,我们利用合并队列方程(PCE,如ACC/AHA指南中推荐的估计ASCVD风险)来开发糖尿病中的局部ASCVD风险预测模型。实验结果表明,如果直接对我们的队列使用PCE算法,AUC仅为0.653,而我们的知识增强局部风险模型可以获得更高的预测性能,AUC为0.723(提高了10.7%)。

英文摘要:

Precision medicine requires the precision disease risk prediction models. In literature, there have been a lot well-established (inter-)national risk models, but when applying them into the local population, the prediction performance becomes unsatisfactory. To address the localization issue, this paper exploits the way to develop knowledge-enhanced localized risk models. On the one hand, we tune models by learning from regional Electronic Health Record (EHR) repositories, and on the other hand, we propose knowledge injection into the EHR data learning process. For experiments, we leverage the Pooled Cohort Equations (PCE, as recommended in ACC/AHA guidelines to estimate the risk of ASCVD) to develop a localized ASCVD risk prediction model in diabetes. The experimental results show that, if directly using the PCE algorithm on our cohort, the AUC is only 0.653, while our knowledge-enhanced localized risk model can achieve higher prediction performance with AUC of 0.723 (improved by 10.7%).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑