NORMA eResearch @NCI Library

Diagnosis of Cervical Cancer using Hybrid Machine Learning Models

Singh, Harsh Dev (2018) Diagnosis of Cervical Cancer using Hybrid Machine Learning Models. Masters thesis, Dublin, National College of Ireland.

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


With the advancement of technology & its collaboration with health care, the world has gained a lot of benefits. Advanced data mining and machine learning techniques are continuously improving existing statistical methods in medical field. These improved techniques will help to deliver an intelligent medical health care in the 21st century. This research focuses on the diagnosis of cervical cancer by using the data mining techniques. Cervical cancer is one of the most fatal cancer, the reason being the delay in diagnosis of the disease. This gives rise to a strong need to expedite the process, which is the motivation for this research. To efficiently predict true cervical cancer patients, a better subset of attributes is required. This research uses the Genetic Algorithm (GA) as feature selection algorithm to generate better subset for predictors. The classification algorithms used in this research are "svmLinear", "RandomForest" and "gbm" with the oversampling technique, "SMOTE". Bayesian optimisation is used for hyper parameter tuning, to boost the true positive accuracy for above models. Comparative analysis of all the models has been done on the basis of sensitivity and specificity, where, GBM has delivered more promising results with sensitivity of 0.778 (77.8%) followed by "svmLinear" with sensitivity of 0.5558 (55.58%), and "RandomForest" with sensitivity = 0.44 (44.4%). These sensitivity results will be helpful for the real-time application to make sure that no cancer patient remains untreated.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Q Science > Life sciences > Medical sciences > Pathology > Tumors > Cancer
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Caoimhe Ní Mhaicín
Date Deposited: 05 Nov 2018 10:49
Last Modified: 05 Nov 2018 10:54

Actions (login required)

View Item View Item