Partial Multiple Imputation With Variational Autoencoders: Tackling Not at Randomness in Healthcare Data

• Tipo: Artigo em Revista Científica Internacional
• Data: 2022

Autores

Pereira, RC (Autor) Outra; Pedro Henriques Abreu (Autor) Outra; Pedro Pereira Rodrigues (Autor) FMUP

Revista

Título: IEEE Journal of Biomedical and Health Informatics

Vol. 26

Páginas: 4218-4227

ISSN: 2168-2194

Editora: IEEE

Indexação

ISI Web of Knowledge - 2 Citações

Scopus - 4 Citações

Outras Informações

ID Authenticus: P-00W-WMS

DOI: 10.1109/jbhi.2022.3172656

Abstract (EN): Missing data can pose severe consequences in critical contexts, such as clinical research based on routinely collected healthcare data. This issue is usually handled with imputation strategies, but these tend to produce poor and biased results under the Missing Not At Random (MNAR) mechanism. A recent trend that has been showing promising results for MNAR is the use of generative models, particularly Variational Autoencoders. However, they have a limitation: the imputed values are the result of a single sample, which can be biased. To tackle it, an extension to the Variational Autoencoder that uses a partial multiple imputation procedure is introduced in this work. The proposed method was compared to 8 state-of-the-art imputation strategies, in an experimental setup with 34 datasets from the medical context, injected with the MNAR mechanism (10% to 80% rates). The results were evaluated through the Mean Absolute Error, with the new method being the overall best in 71% of the datasets, significantly outperforming the remaining ones, particularly for high missing rates. Finally, a case study of a classification task with heart failure data was also conducted, where this method induced improvements in 50% of the classifiers.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 10