Joint Spatiotemporal Attention for Mortality Prediction of Patients with Long COVID

Degan Hao, Mohammadreza Negahdar

Keywords: longitudinal data, mortality prediction, COVID-19, attention

TL;DR: We proposed a joint spatiotemporal attention mechanism for deep learning-based mortality prediction of long covid.

Abstract: Long COVID is a general term of Post-Acute Sequelae of COVID-19. Patients with Long COVID can endure long-lasting symptoms including fatigue, headache, dyspnea and anosmia, facing increased risk of death. Identifying the cohorts with severe long-term complications in COVID-19 could benefit the treatment planning and resource arrangement. However, due to the heterogeneous phenotypes and various duration of symptoms presented in patients with Long COVID, it is difficult to predict their outcomes from their longitudinal data. In this study, we proposed a spatiotemporal attention mechanism to weigh feature importance jointly from the temporal dimension and feature space of longitudinal medical data. Considering that medical examinations can have interchangeable orders in adjacent time points, we restricted the learning of short-term dependency with a Local-LSTM and the learning of long-term dependency with the joint spatiotemporal attention. We also compared the proposed method with several state-of-the-art methods and a method in clinical practice. The methods are evaluated on a hard-to-acquire clinical dataset of patients with Long COVID. Experimental results show the Local-LSTM with joint spatiotemporal attention achieved superior performance in mortality prediction comparing to related methods. By analyzing the critical time points identified by the joint spatiotemporal attention, we identified time-specific prognostic biomarkers for life-threatening Long COVID. The proposed method provides a clinical tool for the severity assessment of Long COVID.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )