Medical Data Wrangling With Sequential Variational Autoencoders

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 fash...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE journal of biomedical and health informatics Ročník 26; číslo 6; s. 2737 - 2745
Hlavní autori: Barrejon, Daniel, Olmos, Pablo M., Artes-Rodriguez, Antonio
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.06.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Computer applications
Correlation
Cross correlation
Data models
Databases, Factual
Deep learning
heterogeneous
Hospitals
Humans
Measurement
Medical records
Missing data
Monitoring
Root-mean-square errors
sequential data
Standard error
Time series analysis
VAE
ISSN:2168-2194, 2168-2208, 2168-2208
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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-the-art 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 and 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.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2168-2194
2168-2208
2168-2208
DOI:10.1109/JBHI.2021.3123839