Publication:
Medical data wrangling with sequential variational autoencoders

Loading...
Thumbnail Image
Identifiers
Publication date
2022-06
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
Medical data sets are usually corrupted by noise and missing data. These missing patterns are commonly assumed to be completely random, but in medical scenarios, the reality is that these patterns occur in bursts due to sensors that are off for some time or data collected in a misaligned uneven fashion, among other causes. This paper proposes to model medical data records with heterogeneous data types and bursty missing data using sequential variational autoencoders (VAEs). In particular, we propose a new methodology, the Shi-VAE, which extends the capabilities of VAEs to sequential streams of data with missing observations. We compare our model against state-of-theart solutions in an intensive care unit database (ICU) and a dataset of passive human monitoring. Furthermore, we find that standard error metrics such as RMSE are not conclusive enough to assess temporal models and include in our analysis the cross-correlation between the ground truth nd the imputed signal. We show that Shi-VAE achieves the best performance in terms of using both metrics, with lower computational complexity than the GP-VAE model, which is the state-of-the-art method for medical records.
Description
Keywords
Deep learning, Variational autoencoders, Missing data, Heterogeneous, Sequential data
Bibliographic citation
IEEE Journal of biomedical and health informatics, 26(6), Jun. 2022, Pp. 2737-2745