MEDICAL DATA CLASSIFICATION ALGORITHM FOR ONCOLOGY PREDICTION
Abstract
The article presents the results of research on the application of Logistic Regression and Decision Tree with the use of PCA algorithm in the task of cancer detection and prediction. The problem and relevance of this research are analyzed. Various literature sources and machine learning methods are reviewed. A detailed analysis of the chosen methods is conducted, along with their mathematical models. Training of respective models and a series of experiments are carried out to select the best parameters on two selected datasets, which are thoroughly analyzed in the study. The accuracy of the models is evaluated, and corresponding metrics such as Classification report, Confusion Matrix, and Roc-curve are constructed. Additionally, experiments are conducted to enhance the accuracy of the models using the PCA algorithm. As a result, significantly improved outcomes are achieved with the second dataset, while the accuracy improvement is not achieved with the first dataset. After the experimental phase, the obtained results are analyzed in detail, and corresponding histograms with the results are provided. This research demonstrates that the PCA algorithm is better utilized when dealing with datasets with a large number of features. Overall, the study yields promising results in cancer detection and prediction, and the value of this research is highlighted with the described conclusions. The paper evaluates the results using various metrics, such as accuracy and sensitivity, and compares the results with other analysis and classification methods. It has been proven that these methods can improve the process of oncology diagnosis, contribute to the reduction of false classifications and contribute to the early detection of the disease.
References
2. Jenni A.M., Sidey-Gibbons C.J. Machine learning in medicine: a practical introduction. BMC Medical Research Methodology. 2019. Vol. 19. No. 64. https://doi.org/10.1186/s12874-019-0681-4
3. Kourou K., Exarchos T.P., Exarchos K.P. Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal. 2015. Vol. 13. 8-17. https://doi.org/10.1016/j.csbj.2014.11.005
4. Li Y., Hu G., Liu L., Xie Y., Xu Z. A performance analysis of dimensionality reduction algorithms in machine learning models for cancer prediction. Data in Brief. 2021. Vol. 37. 100125. https://doi.org/10.1016/j.health.2022.100125
5. Sayed S. Machine Learning Is The Future Of Cancer Prediction. Towards Data Science. 2018. URL: https://towardsdatascience.com/machine-learning-is-the-future-of-cancer-prediction-e4d28e7e6dfa.
6. Azar A.S., Rikan S.B., Naemi A. Application of machine learning techniques for predicting survival in ovarian cancer. BMC Medical Informatics and Decision Making. 2022. Vol. 22. No. 68. https://doi.org/10.1186/s12911-022-02087-y
7. Jaber N. Can Artificial Intelligence Help See Cancer in New, and Better, Ways? National Cancer Institute. 2022. URL: https://www.cancer.gov/news-events/cancer-currents-blog/2022/artificial-intelligence-cancer-imaging.
8. Mudawi N.A., Alazeb A. A Model for Predicting Cervical Cancer Using Machine Learning Algorithms. Sensors (Basel). 2022. Vol. 22(11). 4132. https://doi.org/10.3390/s22114132
9. Kourou K., Exarchos T.P., Exarchos K.P. Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal. 2015. Vol. 13. 8-17. https://doi.org/10.1016/j.csbj.2014.11.005
10. Yan-yan Y., Lu Y. Decision tree methods: applications for classification and prediction. Shanghai Archives of Psychiatry. 2015. Vol. 27. No. 2. 130-135. https://doi.org/10.11919/j.issn.1002-0829.215027.
ISSN 
