Targeted deep learning classification and feature extraction for clinical diagnosis

Yiting Tsai; Vikash Nanthakumar; Saeed Mohammadi; Susan A Baldwin; Bhushan Gopaluni; Fei Geng

doi:10.1016/j.isci.2023.108006

Targeted deep learning classification and feature extraction for clinical diagnosis

iScience. 2023 Sep 28;26(11):108006. doi: 10.1016/j.isci.2023.108006. eCollection 2023 Nov 17.

Authors

Yiting Tsai¹, Vikash Nanthakumar², Saeed Mohammadi², Susan A Baldwin¹, Bhushan Gopaluni¹, Fei Geng¹

Affiliations

¹ University of British Columbia, 2360 East Mall, Vancouver, BC V6T 1Z3, Canada.
² McMaster University, 1280 Main St W, Hamilton, ON L8S 4L8, Canada.

Abstract

Protein biomarkers can be used to characterize symptom classes, which describe the metabolic or immunodeficient state of patients during the progression of a specific disease. Recent literature has shown that machine learning methods can complement traditional clinical methods in identifying biomarkers. However, many machine learning frameworks only apply narrowly to a specific archetype or subset of diseases. In this paper, we propose a feature extractor which can discover protein biomarkers for a wide variety of classification problems. The feature extractor uses a special type of deep learning model, which discovers a latent space that allows for optimal class separation and enhanced class cluster identity. The extracted biomarkers can then be used to train highly accurate supervised learning models. We apply our methods to a dataset involving COVID-19 patients and another involving scleroderma patients, to demonstrate improved class separation and reduced false discovery rates compared to results obtained using traditional models.

Keywords: Artificial intelligence applications; Computer-aided diagnosis method; Health sciences.