NORMA eResearch @NCI Library

Diagnosis and Classification of Mental Disorders using Machine Learning Techniques

SundaraPandiyan, Abinaya (2023) Diagnosis and Classification of Mental Disorders using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Today’s lifestyle and work cultures have increased people’s levels of pressure and stress, which has led to different mental disorders like stress, schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), and many more. The majority of symptoms are quite common, which leads people to ignore them, as it is challenging to diagnose mental disorders. The objective of this research is to identify and classify the level of anxiety, stress, and depression among individuals. It will be classified based on the input provided to several questions related to their current emotion and the number of events they are experiencing. The DAAS 42 dataset from Kaggle is considered for this research. Deep learning models like the feed-forward neural network (FNN) and ensemble models of voting classifiers are used in this study, along with traditional models like Extreme Gradient Boosting (XG boots), Adaptive Boosting (Ada boost), Decision Tree, K-Nearest Neighbors (KNN), and Gaussian Naive Bayes. Overall, the deep learning model and voting classifier performed well, followed by XGBoost. The voting classifier trained with 20 features had the highest accuracy for anxiety at 91.6% and FNN with an accuracy of 93.8% had the highest accuracy for stress data. For depression, both the FNN and the voting classifier had the highest accuracy of 93%.

Item Type: Thesis (Masters)
Muntean, Cristina Hava
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
R Medicine > RA Public aspects of medicine > RA790 Mental Health
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 26 May 2023 16:56
Last Modified: 26 May 2023 16:56

Actions (login required)

View Item View Item