Comparative Analysis of ML Algorithms for Breast Cancer Detection

Slavkovska, Daniela and Ristevski, Blagoj and Petreska, Anita (2023) Comparative Analysis of ML Algorithms for Breast Cancer Detection. In: 13th International Conference on Applied Internet and Information Technologies AIIT2023, October 13th, Bitola, Rebublic North Macedonia.

Text Comparative Analysis of ML Algorithms for Breast Cancer.pdf - Published Version Download (1MB)

Abstract

Artificial intelligence and machine learning algorithms with their advanced predictive and diagnostic techniques help healthcare providers make the right decisions in the process of disease prevention and early diagnosis. Breast cancer as a disease of modern dynamic living is gaining momentum. Its early detection is crucial to increase the chances of survival through better treatment options. Exploratory data analysis (EDA) as a key step in data analysis involves systematic examination and visualization of data to discover patterns, outliers and dependencies, enabling hypothesis generation and making correct decisions. As powerful algorithms applied for classification, Logistic regression is used, K-nearest neighbors (KNN), Naïve Bayes, Decision Tree, Random Forest, XGBoost Support, Deep Learning and NeNetwork. In our study, a comparative analysis of the most commonly used Machine Learning (ML) algorithms has been done by evaluating various metrics such as accuracy, F-measure, confusion matrix and specificity. Limitations of machine learning algorithms often include issues such as overhead, high computational requirements, and data quality. Challenges may arise from the need for large labeled datasets, algorithmic bias, and concerns about interpretability. Future work in machine learning should focus on developing more robust models that can generalize well to diverse data, improving the interpretability of complex models.

Item Type:	Conference or Workshop Item (Poster)
Subjects:	Scientific Fields (Frascati) > Natural sciences > Computer and information sciences Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions:	Faculty of Information and Communication Technologies
Depositing User:	Prof. d-r. Blagoj Ristevski
Date Deposited:	17 Dec 2023 20:58
Last Modified:	17 Dec 2023 20:58
URI:	https://eprints.uklo.edu.mk/id/eprint/9530

Actions (login required)

View Item