Author
Listed:
- Muhammad Asad Abbas
- Kashif Munir
- Ali Raza
- Madiha Amjad
- Nagwan Abdel Samee
- Mona M Jamjoom
- Zahid Ullah
Abstract
Thyroid syndrome, a complex endocrine disorder, involves the dysregulation of the thyroid gland, impacting vital physiological functions. Common causes include autoimmune disorders, iodine deficiency, and genetic predispositions. The effects of thyroid syndrome extend beyond the thyroid itself, affecting metabolism, energy levels, and overall well-being. Thyroid syndrome is associated with severe cases of thyroid dysfunction, highlighting the potentially life-threatening consequences of untreated or inadequately managed thyroid disorders. This research aims to propose an advanced meta-learning approach for the timely detection of Thyroid syndrome. We used a standard thyroid-balanced dataset containing 7,000 patient records to apply advanced machine-learning methods. We proposed a novel meta-learning model based on a unique stack of K-Neighbors (KN) and Random Forest (RF) models. Then, a meta-learning Logistic Regression (LR) model is built based on the collective experience of stacked models. For the first time, the novel proposed KRL (KN-RF-LR) method is employed for the effective diagnosis of Thyroid syndrome. Extensive research experiments illustrated that the novel proposed KRL outperformed state-of-the-art approaches, achieving an impressive performance accuracy of 98%. We vindicated the performance scores through k-fold cross-validation and enhanced performance using hyperparameter tuning. Our research revolutionized the timely detection of thyroid syndrome, contributing to the enhancement of human life by reducing thyroid mortality rates.
Suggested Citation
Muhammad Asad Abbas & Kashif Munir & Ali Raza & Madiha Amjad & Nagwan Abdel Samee & Mona M Jamjoom & Zahid Ullah, 2024.
"A novel meta learning based stacked approach for diagnosis of thyroid syndrome,"
PLOS ONE, Public Library of Science, vol. 19(11), pages 1-20, November.
Handle:
RePEc:plo:pone00:0312313
DOI: 10.1371/journal.pone.0312313
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0312313. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.