Trends in Clinical and Medical Sciences
Vol. 3 (2023), Issue 3, pp. 06 – 20
ISSN: 2791-0814 (online) 2791-0806 (Print)
DOI: 10.30538/psrp-tmcs2023.0054
Derangement of gonadal hormone and its relation with oxidative stress for \(\beta\)-thalassemia patients
Debleena Basu\(^{1,*}\), Rupal Sinha\(^{2}\), Saswata Sahub\(^{2}\), Jyotsna Malla\(^{3}\) and Partha Sarathi Ghosal\(^{2}\)
\(^{1}\) Department of Biochemistry, R.G. Kar Medical College \& Hospital Kolkata, Kolkata, 700004, West Bengal, India.
\(^{2}\) School of Water Resources, Indian Institute of Technology Kharagpur, Kharagpur, 721302, India.
\(^{3}\) Computer Science and Engineering, Vellore Institute of Technology, Vellore, 632014, India.
Copyright © 2023 Debleena Basu, Rupal Sinha,Saswata Sahub,Jyotsna Malla and Partha Sarathi Ghosal. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received: May 21, 2023 – Accepted: October 21, 2023 – Published: November 13, 2023
Abstract
Background: Background: Enhanced iron levels in patients afflicted with \(\beta\)-thalassemia induces oxidative stress, which restrains the secretion of gonadal and pituitary hormones. The associated severity level based on several hormones and oxidative stress biomarkers is not been demonstrated so far.
Method: The present study encompasses the employment of hierarchical clustering and different classifiers for determining the severity of the disease based on the analyzed clinical parameters in the study population. Furthermore, the hormonal parameters along with ferritin levels were used as input parameters for the prediction of the oxidative stress biomarkers ([Malondialdehyde (MDA) and protein carbonyl] through neural networks.
Result: A Significant negative correlation was observed between the oxidative stress biomarkers and the hormonal levels in both the female and male datasets of the case group. The clustering results depicted that the datasets corresponding to high oxidative stress biomarkers with very low gonadal hormones represented severe levels of the disease. Support vector machine outperformed the other classifiers in the case of the male dataset. The neural network efficiently predicted female and male models’ MDA and protein carbonyl values. High Fisher’s F-value (2042.035 to 6353.659) and low p-value (<0.001) established the significance of each model.
Conclusion: The proposed framework can be used as a real-life decision tool for medical professionals to diagnose and treat \(\beta\)-thalassemia from a proper classification of the severity of the disease. Furthermore, the passive determination of some critical blood parameters may avoid the complex analytical procedure and its high cost.
Method: The present study encompasses the employment of hierarchical clustering and different classifiers for determining the severity of the disease based on the analyzed clinical parameters in the study population. Furthermore, the hormonal parameters along with ferritin levels were used as input parameters for the prediction of the oxidative stress biomarkers ([Malondialdehyde (MDA) and protein carbonyl] through neural networks.
Result: A Significant negative correlation was observed between the oxidative stress biomarkers and the hormonal levels in both the female and male datasets of the case group. The clustering results depicted that the datasets corresponding to high oxidative stress biomarkers with very low gonadal hormones represented severe levels of the disease. Support vector machine outperformed the other classifiers in the case of the male dataset. The neural network efficiently predicted female and male models’ MDA and protein carbonyl values. High Fisher’s F-value (2042.035 to 6353.659) and low p-value (<0.001) established the significance of each model.
Conclusion: The proposed framework can be used as a real-life decision tool for medical professionals to diagnose and treat \(\beta\)-thalassemia from a proper classification of the severity of the disease. Furthermore, the passive determination of some critical blood parameters may avoid the complex analytical procedure and its high cost.
Keywords:
Pituitary hormones; Machine learning; Ferritin; MDA; Protein Carbonyl