Application of machine learning methods for the prediction of distress in patients with oncological diseases

  • Ginka Kaleva Marinova Technical University of Varna
  • Todor Ganchev Tеchnical University of Varna, Varna , Bulgaria http://orcid.org/0000-0003-0384-4033
  • Nedyalko Nikolov Tеchnical University of Varna, Varna , Bulgaria
Keywords: distress management, oncological dataset, classification, boosting, bagging, Multilayer Perceptron Neural Network

Abstract

Distress management is of particular importance in all disease treatment strategies that aim to cope with medical conditions, which require prolonged therapy. Here, we present results obtained in a comparative study of various classification methods for automated distress detection. For the purposes of the present study, use was made of a common experimental protocol that relies on a dataset of approximately 6 000 oncological patients at different stages of therapy. The dataset consists of the binary responses to specific questions in a purposefully-designed self-evaluation questionnaire on the degree of distress. Conducted, within such a framework, was a performance assessment of three distress detectors based on Multilayer Perceptron Neural Network (MLP NN), boosting and bagging meta-classification methods and evaluated, further, was the performance of nine characteristic descriptors (KR1-KR9) representing the informative content of the dataset in different ways. The results obtained in the experiments prove conclusively that one of the characteristic descriptors, KR8 and KR9, significantly outperform the other descriptors in terms of classification accuracy, precision, recall, and F-measure.

Author Biography

Ginka Kaleva Marinova, Technical University of Varna

Technical University of Varna

Faculty of Automation and Computing

Department of Computer Science and Engineering

References

VanHoose L. еt al. (2015) An analysis of the distress thermometer problem list and distress in patients with cancer, Support Care Cancer, 23, 1225-1232.
Crossref
 
Riba, Michelle B. et al. (2019). Distress Management, Version 3, NCCN Clinical Practice Guidelines in Oncology, JNCCN.org, 17(10), 1229-1249. 
Crossref
 
Власаков, В., и колектив (2015) Психосоциална подкрепа и рехабилитация в онкологията, национален експертен борд клинично ръководство, основано на доказателства, Атр Трейсър.
 
Breiman, L. (1996) Bagging Predictors, Machine Learning , 24, 123-140.
Crossref
 
Кашницкий, Ю.С., & Игнатов, Д.И. (2015) Ансамблевый метод машинного обучения, основанный на рекомендации классификаторов Интеллектуальные системы, Теория и приложения, Интеллектуальные системы. Теория и приложения, 19(4), 37-55.
Google Scholar

Mitchell, T. (1997). Machine Learning. McGraw-Hill, vol 1.
 
Kantardzic, M., (2002) Data Mining Concepts, Models, Methods, and Algorithms,(1st ed.) Wiley-IEEE Press.
Google Scholar

Hossin, M., Sulaiman, M.N. (2015) A Review on Evaluation Metrics for Data Classification Evaluations, International Journal of Data Mining & Knowledge Management Process (IJDKP), 5(2), 1-11.
Crossref
 
Калчева-Арабаджиева, Н., & Николов, Н. (2017) Сравнителен анализ между наивния бейсов класификатор и метода на опорните вектори използващ оптимизация при класификация на български текст в машинното обучение, Списание Компютърни науки и технологии, ТУ - Варна, 97-105.
 
Zhu W., Zeng, N, & Wang, N. (2010) Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS implementations, NESUG: Health Care and Life Sciences, 19, 1-9.
Google Scholar

Powers, D.M.W., (2011) Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation, Journal of Machine Learning Technologies, 2(1), 37-63.
Google Scholar

Muhamedyev, R. (2015) Machine learning methods: An overview, Computer Modeling &New Technologies, 19(6), 14-29.
Google Scholar

Marinova, G., Ganchev, T., and Nikolov, N., (2020) Synthesis of characteristic descriptors for the detection of distress, 2020 International Conference on Biomedical Innovations and Applications (BIA), Varna, Bulgaria, 73-76, 
Crossref


Total number of hits on abstract = 18 times

Downloads for 2021

Download data is not yet available.
Published
2021-01-31
How to Cite
Marinova, G., Ganchev, T., & Nikolov, N. (2021, January 31). Application of machine learning methods for the prediction of distress in patients with oncological diseases. ANNUAL JOURNAL OF TECHNICAL UNIVERSITY OF VARNA, BULGARIA, 4(2), 130-137. https://doi.org/10.29114/ajtuv.vol4.iss2.204
Section
INFORMATION TECHNOLOGIES, COMMUNICATION AND COMPUTER EQUIPMENT
Bookmark and Share