This paper is in the following e-collection/theme issue:

Artificial Intelligence (2185) JMIR Theme Issue: COVID-19 Special Issue (2558) Machine Learning (2121) Clinical Information and Decision Making (1953)

Published on in Vol 27 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/66919, first published .
A Comprehensive Drift-Adaptive Framework for Sustaining Model Performance in COVID-19 Detection From Dynamic Cough Audio Data: Model Development and Validation

A Comprehensive Drift-Adaptive Framework for Sustaining Model Performance in COVID-19 Detection From Dynamic Cough Audio Data: Model Development and Validation

A Comprehensive Drift-Adaptive Framework for Sustaining Model Performance in COVID-19 Detection From Dynamic Cough Audio Data: Model Development and Validation

Authors of this article:

Theofanis Ganitidis1 Author Orcid Image ;   Maria Athanasiou1 Author Orcid Image ;   Konstantinos Mitsis1 Author Orcid Image ;   Konstantia Zarkogianni2 Author Orcid Image ;   Konstantina S Nikita1, 3 Author Orcid Image
Article Authors Cited by (2) Tweetations (1) Metrics

Conference Proceedings

  1. Ganitidis T, Vlontzou M, Athanasiou M, Nikita K, Davatzikos C. 2025 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI). Source-Free Active Learning for Adapting Alzheimer’s Diagnostic Deep Learning Models Across Neuroimaging Cohorts View
  2. Kostavasili D, Ganitidis T, Athanasiou M, Nikita K. 2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE). Fairness-Aware Deep Learning Model for Covid19 Detection from Cough Audio Recordings View