A Machine Learning based Decision Support System to Predict the Presence of Cervical Cancer
- Resource Type
- Conference
- Authors
- Gopinath, B.; Santhi, R.; Dhivya Praba, R.
- Source
- 2023 2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), 2023 2nd International Conference on. :1-4 Jun, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
General Topics for Engineers
Power, Energy and Industry Applications
Signal Processing and Analysis
Decision support systems
Training
Machine learning algorithms
Biological system modeling
Training data
Predictive models
Prediction algorithms
cervix
diagnosis
learning
Naïve Bayes
pap-smear
- Language
Cancer occurring in cervix, a part connecting the uterus and vagina, is one of the frequently happening cancer types among gynecological cancers following uterine cancer. The symptoms generally are experienced once the patient progresses to stage 1b cervical carcinoma on the canal (cervix uteri) joining the uterus and vagina which is clinically observable lesion. The Pap-Smear test is used for early-stage detection technique. Identification of the precancerous or cancerous cells on the individual’s cervix is done by the Papanicolaou test. Pap-Smear produces false-positive/false-negative results. Machine learning algorithms could provide us with an accurate diagnosis by conducting classification, prediction, and estimation. The ensemble technique incorporates four algorithms using the concept of machine learning. The latter provides the highest accuracy of 99% so that it enables the healthcare practitioners to make informed decisions. The proposed work aims to develop an intelligent decision support system which can aid medical practitioners in carrying out informed medical procedures. The system when containerized could make way for portability and easy deployment.