An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction.

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.

Optical Tracking of the Interfacial Dynamics of Single SARS-CoV-2 Pseudoviruses.

The frequent detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) RNA in healthcare environments, accommodations, and wastewater has attracted great attention to the risk of viral transmission by environmental fomites. However, the process of SARS-CoV-2 adsorption to exposed surfaces in high-risk environments remains unclear. In this study, we investigated the interfacial dynamics of single SARS-CoV-2 pseudoviruses with plasmonic imaging technology. Through the use of this technique, which has high spatial and temporal resolution, we tracked the collision of viruses at a surface and differentiated their stable adsorption and transient adsorption. We determined the effect of the electrostatic force on virus adhesion by correlating the solution and surface chemistry with the interfacial diffusion velocity and equilibrium position. Viral adsorption was found to be enhanced in real scenarios, such as in simulated saliva. This work not only describes a plasmonic imaging method to examine the interfacial dynamics of a single virus but also provides direct measurements of the factors that regulate the interfacial adsorption of SARS-CoV-2 pseudovirus. Such information is valuable for understanding virus transport and environmental transmission and even for designing anticontamination surfaces.