What is it about?
This exploratory study examined whether miR-21 expression, together with demographic, lifestyle, clinical, and exercise-related information, could distinguish between exercise and non-exercise status. Three supervised machine learning models were tested using an integrated participant profile rather than relying on miR-21 alone.
Featured Image
Why is it important?
miR-21 alone did not clearly distinguish exercise from non-exercise status. However, when miR-21 was combined with participant and exercise-related variables, the machine learning models showed very high internal classification performance. This highlights the value of combining molecular biomarkers with broader individual characteristics when studying exercise responses.
Perspectives
The findings suggest that exercise-related biological responses are unlikely to be explained by a single biomarker. Integrating molecular markers such as miR-21 with lifestyle, demographic, clinical, and exercise information may offer a more useful approach for future personalized exercise assessment. Because this was a small exploratory proof-of-concept study, larger independent studies are needed to validate these findings.
Associate Professor Fatma Hassan Abd Elbasset Mourgan
Sohar University
Read the Original
This page is a summary of: Machine Learning-based Classification of Exercise Status Using miR-21 Expression and Multivariable Participant Profiles, Biomedical and Biotechnology Research Journal (BBRJ), April 2026, Wolters Kluwer Health,
DOI: 10.4103/bbrj.bbrj_72_26.
You can read the full text:
Contributors
The following have contributed to this page
