Data Imputation and Compression For Parkinson's Disease Clinical Questionnaires

Peralta, Maxime; Jannin, Pierre; Haegelen, Claire; Baxter, John, S H

Data Imputation and Compression For Parkinson's Disease Clinical Questionnaires

Document detail

ID

oai:HAL:hal-02570967v3

Topic

Autoencoders Medical questionnaires Data imputation Parkinson’s Disease PPMI Parkinson's disease [INFO.INFO-NE]Computer Science [cs... [STAT.ML]Statistics [stat]/Machine... [INFO.INFO-AI]Computer Science [cs... [SDV.IB]Life Sciences [q-bio]/Bioe...

Author

Peralta, Maxime Jannin, Pierre Haegelen, Claire Baxter, John, S H

Langue

Editor

HAL CCSD;Elsevier

Year

2021

listing date

12/15/2023

Keywords

parkinson disease science

Metrics

Abstract

International audience; Medical questionnaires are a valuable source of information but are often difficult to analyse due to both their size and the high possibility of having missing values.

This is a problematic issue in biomedical data science as it may complicate how individual questionnaire data is represented for statistical or machine learning analysis.

In this paper, we propose a deeply-learnt residual autoencoder to simultaneously perform non-linear data imputation and dimensionality reduction.

We present an extensive analysis of the dynamics of the performances of this autoencoder regarding the compression rate and the proportion of missing values.

This method is evaluated on motor and non-motor clinical questionnaires of the Parkinson's Progression Markers Initiative (PPMI) database and consistently outperforms linear coupled imputation and reduction approaches.

Peralta, Maxime,Jannin, Pierre,Haegelen, Claire,Baxter, John, S H, 2021, Data Imputation and Compression For Parkinson's Disease Clinical Questionnaires, HAL CCSD;Elsevier