A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: A case study in two clinical domains

Vasileios C Pezoulas; Grigoris I Grigoriadis; George Gkois; Nikolaos S Tachos; Tim Smole; Zoran Bosnić; Matej Pičulin; Iacopo Olivotto; Fausto Barlocco; Marko Robnik-Šikonja; Djordje G Jakovljevic; Andreas Goules; Athanasios G Tzioufas; Dimitrios I Fotiadis

doi:10.1016/j.compbiomed.2021.104520

A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: A case study in two clinical domains

Comput Biol Med. 2021 Jul:134:104520. doi: 10.1016/j.compbiomed.2021.104520. Epub 2021 Jun 6.

Authors

Affiliations

¹ Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, GR45110, Greece.
² Faculty of Computer and Information Science, University of Ljubljana, Večna Pot 113, 1000, Ljubljana, Slovenia.
³ Department of Experimental and Clinical Medicine, University of Florence and Cardiomyopathies Unit, Azienda Ospedaliera Careggi, Florence, Italy.
⁴ Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne, UK and with the Faculty of Health and Life Sciences, Coventry University, Coventry, UK.
⁵ Department of Pathophysiology, Faculty of Medicine, National and Kapodistrian University of Athens (NKUA), GR 15772, Athens, Greece.
⁶ Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, GR45110, Greece; Department of Biomedical Research, FORTH-IMBB, Ioannina, GR45110, Greece. Electronic address: fotiadis@uoi.gr.

PMID: 34118751
DOI: 10.1016/j.compbiomed.2021.104520

Abstract

Virtual population generation is an emerging field in data science with numerous applications in healthcare towards the augmentation of clinical research databases with significant lack of population size. However, the impact of data augmentation on the development of AI (artificial intelligence) models to address clinical unmet needs has not yet been investigated. In this work, we assess whether the aggregation of real with virtual patient data can improve the performance of the existing risk stratification and disease classification models in two rare clinical domains, namely the primary Sjögren's Syndrome (pSS) and the hypertrophic cardiomyopathy (HCM), for the first time in the literature. To do so, multivariate approaches, such as, the multivariate normal distribution (MVND), and straightforward ones, such as, the Bayesian networks, the artificial neural networks (ANNs), and the tree ensembles are compared against their performance towards the generation of high-quality virtual data. Both boosting and bagging algorithms, such as, the Gradient boosting trees (XGBoost), the AdaBoost and the Random Forests (RFs) were trained on the augmented data to evaluate the performance improvement for lymphoma classification and HCM risk stratification. Our results revealed the favorable performance of the tree ensemble generators, in both domains, yielding virtual data with goodness-of-fit 0.021 and KL-divergence 0.029 in pSS and 0.029, 0.027 in HCM, respectively. The application of the XGBoost on the augmented data revealed an increase by 10.9% in accuracy, 10.7% in sensitivity, 11.5% in specificity for lymphoma classification and 16.1% in accuracy, 16.9% in sensitivity, 13.7% in specificity in HCM risk stratification.

Keywords: Artificial intelligence; Data augmentation; HCM risk stratification; Lymphoma classification; Virtual population generation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Artificial Intelligence*
Bayes Theorem
Humans
Neural Networks, Computer
Risk Assessment