Automated Detection of Persistent Inflammatory Biomarkers in Post-COVID-19 Patients Using Machine Learning Techniques

TL;DR

This study demonstrates how machine learning models can effectively automate the detection of persistent inflammatory biomarkers in post-COVID-19 patients, aiding early diagnosis and personalized treatment.

Contribution

It introduces a machine learning framework for identifying persistent inflammation biomarkers in post-COVID-19 patients using clinical data from Iraq.

Findings

High accuracy and precision of models in detecting inflammation

Effective feature selection improved model performance

Potential for clinical application in post-COVID care

Abstract

The COVID-19 pandemic has left a lasting impact on individuals, with many experiencing persistent symptoms, including inflammation, in the post-acute phase of the disease. Detecting and monitoring these inflammatory biomarkers is critical for timely intervention and improved patient outcomes. This study employs machine learning techniques to automate the identification of persistent inflammatory biomarkers in 290 post-COVID-19 patients, based on medical data collected from hospitals in Iraq. The data encompassed a wide array of clinical parameters, such as C-reactive protein and interleukin-6 levels, patient demographics, comorbidities, and treatment histories. Rigorous data preprocessing and feature selection processes were implemented to optimize the dataset for machine learning analysis. Various machine learning algorithms, including logistic regression, random forests, support vector machines, and gradient boosting, were deployed to construct predictive models. These models exhibited promising results, showcasing high accuracy and precision in the identification of patients with persistent inflammation. The findings of this study underscore the potential of machine learning in automating the detection of persistent inflammatory biomarkers in post-COVID-19 patients. These models can serve as valuable tools for healthcare providers, facilitating early diagnosis and personalized treatment strategies for individuals at risk of persistent inflammation, ultimately contributing to improved post-acute COVID-19 care and patient well-being. Keywords: COVID-19, post-COVID-19, inflammation, biomarkers, machine learning, early detection.