A sample blood test has recently become an important tool to help identify false-positive/negative rRT-PCR tests. Importantly, this is mainly because it is an inexpensive and handy option to detect potential COVID-19 patients. However, this test should be conducted by certified laboratories, expensive equipment, and trained personnel, and 3-4 hours are needed to deliver results. Furthermore, it has relatively large false-negative rates around 15-20%. Consequently, an alternative and more accessible solution, quicker and less costly, is needed. This paper introduces flexible and unsupervised data-driven approaches to detect COVID-19 infection based on blood test samples. In other words, we address the problem of COVID-19 infection detection using a Blood test as an anomaly detection problem through an unsupervised deep hybrid model. Essentially, we amalgamate the features extraction capability of the Variational Autoencoder (VAE) and the detection sensitivity of the one-class Support Vector Machine algorithm (1SVM). Two sets of routine blood tests samples from the Hospital Albert Einstein, Sco Paulo, Brazil, and the San Raffaele Hospital in Milan, Italy, are used to assess the performance of the investigated deep learning models. Here, missing values have been imputed based on Random Forest regressor. Compared to Generative adversarial networks (GAN), Deep Belief Network (DBN), and restricted Boltzmann machine (RBM)-based 1SVM, the traditional VAE, GAN, DBN, and RBM with softmax layer as discriminator layer, and the standalone 1SVM, the proposed VAE-based 1SVM detector offers superior discrimination performance of potential COVID-19 infections. Results also revealed that the deep learning-driven 1SVM detection approaches provide promising detection performance compared to the conventional deep learning models.
|Original language||English (US)|
|Number of pages||1|
|Journal||IEEE Transactions on Instrumentation and Measurement|
|State||Published - 2021|
ASJC Scopus subject areas
- Electrical and Electronic Engineering