A computational approach for correlational analysis of symptoms of major depressive disorder
NUST Journal of Natural Sciences · 2025
DOI: 10.53992/njns.v10i3.272 ↗Kurz gefasst
Fachartikel in der Zeitschrift NUST Journal of Natural Sciences, 2025. Verfasst von Sahar Safdar und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Major Depressive Disorder (MDD) is a complicated mental illness that consists of wide range of correlated symptoms. According to DSM-V, it is characterized by pervasive low mood, loss of interest or pleasure in nearly all activities, and additional symptoms that can cause significant distress in social, occupational, and important areas of life. In this study, association rules, decision tree classification and agglomerative clustering are employed to classify MDD symptoms interconnection and their co-occurrence pattern. A combination of key symptoms occurrence, such as aggression with euphoric responses and overthinking with euphoria are identified through association rules that show highest lift values. Decision tree is employed to predict primary node which is mood swing as key predictor of MDD. Then, agglomerative clustering is used to split the dataset into three clusters based on expert diagnosis to identify the range of symptoms that overlap. In this study, computational approach is utilized to unravel the hidden pattern and overlapping of correlated symptoms that will help in improved diagnosis and better personalized treatment plans. This study highlighted the interrelationships of symptoms associated with MDD and their thorough examination for therapeutic approach. Future perspectives should focus on diverse datasets with extension and validation of findings that produce sustainable findings for clinical decision making. By the complex interplay of symptoms of MDD shows the contribution of this research towards advancement of evidence-based diagnostics, ultimately aim to improve clinical outcomes by intergradational symptomatic study.
Zitieren
APA
Safdar, S., Rauf, A., Zaheer, A., Fatima, Z., Shah, S. H. A., & Bakhtiar, S. M. (2025). A computational approach for correlational analysis of symptoms of major depressive disorder. NUST Journal of Natural Sciences. https://doi.org/10.53992/njns.v10i3.272
Vancouver
Safdar S, Rauf A, Zaheer A, Fatima Z, Shah SHA, Bakhtiar SM. A computational approach for correlational analysis of symptoms of major depressive disorder. NUST Journal of Natural Sciences. 2025. doi:10.53992/njns.v10i3.272
BibTeX
@article{Safdar2025,
author = {Safdar, Sahar and Rauf, Abdur and Zaheer, Aneeza and Fatima, Zeenat and Shah, Syed Haseeb Ahmad and Bakhtiar, Syeda Marriam},
title = {A computational approach for correlational analysis of symptoms of major depressive disorder},
journal = {NUST Journal of Natural Sciences},
year = {2025},
doi = {10.53992/njns.v10i3.272}
}
EUVIMED