COVID-19 Clinical Status Associated With Outcome Severity: An Unsupervised Machine Learning Approach

Overview

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side-effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial Intelligence (AI) and Machine Learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classification which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying Principal Component Analysis (PCA) on the numerical part of the dataset and Multiple Correspondence Analysis (MCA) on the categorical part of the dataset. Then, the Bayesian Information Criterion(BIC) was applied to Gaussian Mixture Models (GMM) in order to identify the optimal number of clusters, under which, the best grouping of patients occurs. The proposed methodology identified 4 clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and patient's mortality.

An algorithmic pipeline based on unsupervised machine learning algorithms, which aims to operate in tandem with physicians and provide additional knowledge for the proper categorization of COVID-19 infected patients based on their severity, is proposed in this study. Data from patients hospitalized in our clinic are collected and stored in separate Microsoft Excel files (.xlsx), which are loaded into memory. A script is concatenating them all into a single dataframe where they are checked for NaN (Not a Number) values. Because of the nature of the data, patients with missing information are discarded entirely from the dataset, since information inference would be a biased practice for the particular application. Next, we apply data normalization by scaling all numerical variables between the (0,1) range, so that the range of all numerical variables is the same, and any bias towards certain variables is avoided .A thorough and detailed data collection process was designed in order to collect information for the patients, without disturbing the clinical treatment, or upsetting them in the process.