Hybrid predictive model for Asthma Diagnosis Using Environmental and lifestyle factors

Joy, Anna (2024) Hybrid predictive model for Asthma Diagnosis Using Environmental and lifestyle factors. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (781kB) | Preview
Preview	PDF (Configuration Manual) Download (968kB) | Preview

Abstract

Asthma diagnosis contains various challenging problems and issues which emerge due to its complexity of the disease by the influence of various environmental, lifestyle and historical factors that included in imbalanced datasets. To ensure timely interventions, improving patient outcomes and reducing the economic burden, which is related with untreated or misdiagnosed asthma, early detection is very crucial. Traditional diagnostic methods such as Logistic Regression, SVM, decision tree and Random Forest often struggle to accurately predicting asthma cases that particularly in imbalanced datasets where non-asthma cases dominate which result high accuracy. This research study mainly focus the limitations of traditional diagnostic models in handling such complexities by proposing a hybrid machine learning model that combines Gradient Boosting and Neural Networks. In order to handle the issue of class imbalance, we have used two different oversampling technique such as synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN). While these methods improved data balance which shows a high overall accuracy of 95% for predicting non-asthma cases using the hybrid model, even though fails to detect asthma cases, with a recall of 0.00 ,that were marginal which results in the need for more advanced methods to optimize hybrid architectures. We are analysing the stacked model that integrating neural networks and gradient boosting which has a poor performance with an AUC of 0.4864 when using oversampling technique ADASYN.

The research also explores the potential for various diagnostic tools and proposes meaningful future work that including advanced ensemble learning methods.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basilio, Jorge UNSPECIFIED
Uncontrolled Keywords:	Hybrid model; SMOTE; ADASYN; Asthma Diagnosis; class imbalance
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 15:02
Last Modified:	02 Sep 2025 15:02
URI:	https://norma.ncirl.ie/id/eprint/8718

Actions (login required)

View Item