Home // PANDEMICS ANALYTICS 2025, International Conference on Pandemics Analytics // View article

Statistical and Predictive Analysis to Identify Risk Factors and Effects of Post COVID-19 Syndrome

Authors:
Milad Leyli-abadi
Sonja van Ockenburg
Axel Tahmasebimoradi
Jean-Patrick Brunet

Keywords: Post COVID-19 syndrome; PCC; predictive analysis; Machine learning; Explainability

Abstract:
Some corona virus disease 2019 (COVID-19) symptoms can persist for months after infection, leading to what is termed Post COVID-19 condition. Factors such as vaccination timing, patient characteristics, and pre-existing conditions may contribute to the prolonged effects and intensity of Post COVID-19 condition. Each patient, based on their unique combination of factors, develops a specific risk or intensity of Post COVID-19 condition. In this work, we aim to achieve two objectives: (1) conduct a statistical analysis to identify relationships between various factors and Post COVID-19 condition, and (2) perform predictive analysis of Post COVID-19 condition intensity using these factors. We benchmark and interpret various data-driven approaches using data from the Lifelines COVID-19 cohort. Our results show that Neural Networks (NN) achieve the best performance in terms of Mean Absolute Percentage Error (MAPE), with predictions averaging 19% error. Additionally, interpretability analysis reveals key factors such as loss of smell, headache, muscle pain, and vaccination timing as significant predictors, while chronic disease and sex are critical risk factors. These insights provide valuable guidance for understanding Post COVID-19 condition (PCC) and developing targeted interventions.

Pages: 14 to 20

Copyright: Copyright (c) IARIA, 2025

Publication date: October 26, 2025

Published in: conference

ISBN: 978-1-68558-313-2

Location: Barcelona, Spain

Dates: from October 26, 2025 to October 30, 2025