An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction.
An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction.
复制标题
DOI：
10.1016/j.artmed.2022.102439
复制
发表时间：
2023-01
影响因子：
7.5
通讯作者：
Wang, Fusheng
中科院分区：
文献类型：
--
作者：
Dong, Xinyu;Wong, Rachel;Lyu, Weimin;Abell-Hart, Kayley;Deng, Jianyuan;Liu, Yinan;Hajagos, Janos G.;Rosenthal, Richard N.;Chen, Chao;Wang, Fusheng
关键词：
阿片类药物过量（OD）已成为美国意外死亡的主要原因，在COVID-19大流行期间，过量死亡人数创下历史新高。打击阿片类药物危机需要通过识别有过量风险的个体来瞄准高需求人群。深度学习作为一种利用大规模电子健康记录（EHR）建立预测模型的强大方法而出现，但它受到电子健康记录数据之间复杂内在关系的挑战。此外，由于缺乏临床上有意义的可解释性，它的效用受到限制，这对于使用此类模型做出知情的临床或政策决策是必要的。在本文中，我们提出了一种结合长短期记忆（LSTM）和图神经网络（GNN）的集成深度学习模型light来预测患者的OD风险。light模型可以结合疾病进展的时间效应和从临床特征之间的相互作用中学到的知识。我们使用超过500万患者的Cerner Health Facts数据库对该模型进行了评估。我们的实验表明，该模型优于传统的机器学习方法和其他深度学习模型。我们还提出了一种新的可解释性方法，利用gnn提供的嵌入分别对患者和EHR特征进行聚类，并对临床解释进行定性特征聚类分析。我们的研究表明，light可以利用纵向电子病历数据和患者电子病历的内在图表结构来提供有效和可解释的OD风险预测，这可能会潜在地改善临床决策支持。
Opioid overdose (OD) has become a leading cause of accidental death in the United States, and overdose deaths reached a record high during the COVID-19 pandemic. Combating the opioid crisis requires targeting high-need populations by identifying individuals at risk of OD. While deep learning emerges as a powerful method for building predictive models using large scale electronic health records (EHR), it is challenged by the complex intrinsic relationships among EHR data. Further, its utility is limited by the lack of clinically meaningful explainability, which is necessary for making informed clinical or policy decisions using such models. In this paper, we present LIGHTED, an integrated deep learning model combining long short term memory (LSTM) and graph neural networks (GNN) to predict patients' OD risk. The LIGHTED model can incorporate the temporal effects of disease progression and the knowledge learned from interactions among clinical features. We evaluated the model using Cerner's Health Facts database with over 5 million patients. Our experiments demonstrated that the model outperforms traditional machine learning methods and other deep learning models. We also proposed a novel interpretability method by exploiting embeddings provided by GNNs to cluster patients and EHR features respectively, and conducted qualitative feature cluster analysis for clinical interpretations. Our study shows that LIGHTED can take advantage of longitudinal EHR data and the intrinsic graph structure of EHRs among patients to provide effective and interpretable OD risk predictions that may potentially improve clinical decision support.
登录
查看更多内容
DOI：
10.1145/2939672.2939754
发表时间：
2016-08
期刊：
KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
影响因子：
--
作者：
Grover A;Leskovec J
通讯作者：
Leskovec J
CDC规定慢性疼痛的阿片类药物的指南 - 美国，2016年。
DOI：
10.1001/jama.2016.1464
发表时间：
2016-04-19
期刊：
JAMA
影响因子：
--
作者：
Dowell D;Haegerich TM;Chou R
通讯作者：
Chou R
影响因子：
5.7
作者：
Breiman, L
通讯作者：
Breiman, L
影响因子：
4.9
作者：
Asfaw A;Boden LI
通讯作者：
Boden LI
影响因子：
1.7
作者：
Fluss, R;Faraggi, D;Reiser, B
通讯作者：
Reiser, B