MACHINE LEARNING APPLICATION FOR IDENTIFYING LYMPH NODES IN THE THYROID GLAND
DOI:
https://doi.org/10.24867/17BE03AvramovicKeywords:
machine learning, classificationAbstract
The paper describes the creation and analysis of a model for the identification of papillary thyroid cancer. The subject of the research are patients in whom no pathological phenomena or lymph node metastases, have been detected clinically and ultrasound. The surgical outcome findings of these patients point out that preop ultrasound diagonosis could not be considered reliable and that they were wrong in about 40% of patients. The aim of this paper is to achieve the sensitivity and specificity of the model that will provide a good enough result.
References
[1] Andread C. Muller, Sarah Guido, Introduction to Machine Learning with Python, O'Reilly Media, Inc. 2016.
[2] Kevin P. Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012.
[3] Trevor Hastie, Robert Tibishirani, Jeronime Friedman, The Elements of Statistical Learning, Springer, 2009.
[4] Martin Krzwinski, Naomi Altman, Classification and regression trees, Nature America, Nature Methods, Vol. 14 No. 8, August 2017.
[5] Jake Lever, Matrin Krzywinski, Naomi Altman, Model selection and overfitting. Nature America, Nature Methods, Vol. 13 No. 9, September 2016.
[6] Candice Bentejac, Anna Csorgo, Gonzalo Matrinez-Munoz, A Comparative Analysis of XGBoost., ResearchGate, November 2019.
[2] Kevin P. Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012.
[3] Trevor Hastie, Robert Tibishirani, Jeronime Friedman, The Elements of Statistical Learning, Springer, 2009.
[4] Martin Krzwinski, Naomi Altman, Classification and regression trees, Nature America, Nature Methods, Vol. 14 No. 8, August 2017.
[5] Jake Lever, Matrin Krzywinski, Naomi Altman, Model selection and overfitting. Nature America, Nature Methods, Vol. 13 No. 9, September 2016.
[6] Candice Bentejac, Anna Csorgo, Gonzalo Matrinez-Munoz, A Comparative Analysis of XGBoost., ResearchGate, November 2019.
Downloads
Published
2022-04-03
Issue
Section
Electrotechnical and Computer Engineering
