Machine learning models selection under uncertainty: application in cancer prediction

2024;
: pp. 230–238
https://doi.org/10.23939/mmc2024.01.230
Received: July 07, 2023
Revised: March 03, 2024
Accepted: March 04, 2024

Lamrani Alaoui Y., Benmir M., Aboulaich R.  Machine learning models selection under uncertainty: application in cancer prediction.  Mathematical Modeling and Computing. Vol. 11, No. 1, pp. 230–238 (2024)

1
Mohammadia School of Engineering (EMI), Mohammed V University in Rabat
2
Mohammadia School of Engineering, Mohammed V University in Rabat
3
Mohammadia School of Engineering, Mohammed V University in Rabat

Cancer stands as the foremost global cause of mortality, with millions of new cases diagnosed each year.  Many research papers have discussed the potential benefits of Machine Learning (ML) in cancer prediction, including improved early detection and personalized treatment options.  The literature also highlights the challenges facing the field, such as the need for large and diverse datasets as well as interpretable models with high performance.  The aim of this paper is to suggest a new approach in order to select and assess the generalization performance of ML models in cancer prediction, particularly for datasets with limited size.  The estimates of the generalization performance are generally influenced by numerous factors throughout the process of training and testing.  These factors include the impact of the training–testing ratio as well as the random selection of datasets for training and testing purposes.

  1. Zhang C., Hu J., Li H., Ma H., Othmane B., Ren W., Yi Z., Qiu D., Ou Z., Chen J., Zu X.  Emerging biomarkers for predicting bladder cancer lymph node metastasis.  Frontiers in Oncology.  11, 648968 (2021).
  2. Wang P., Li Y., Reddy C. K.  Machine learning for survival analysis: A survey.  ACM Computing Surveys.  51 (6), 1–36 (2019).
  3. Levine A. B., Schlosser C., Grewal J., Coope R., Jones S. J. M., Yip S.  Rise of the machines: advances in deep learning for cancer diagnosis.  Trends in Cancer.  5 (3), 157–169 (2019).
  4. Huang S., Yang J., Fong S., Zhao Q.  Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges.  Cancer letters.  471, 61–71 (2020).
  5. Abreu P. H., Santos M. S., Abreu M. H., Andrade B., Silva D. C.  Predicting breast cancer recurrence using machine learning techniques: a systematic review.  ACM Computing Surveys.  49 (3), 1–40 (2016).
  6. Nguyen Q. H., Ly H.-B., Ho L. S., Al-Ansari N., Le H. V., Tran V. Q., Prakash I., Pham B. T.  Influence of data splitting on performance of machine learning models in prediction of shear strength of soil.  Mathematical Problems in Engineering.  2021, 4832864 (2021).
  7. Witten I. H., Frank E., Hall M. A.  Credibility: evaluating what's been learned.  Data Mining: Practical Machine Learning Tools and Techniques.  147–187 (2011).
  8. Japkowicz N., Shah M.  Performance evaluation in machine learning.  Machine Learning in Radiation Oncology.  41–56 (2015).
  9. Kou G., Lu Y., Peng Y., Shi Y.  Evaluation of classification algorithms using MCDM and rank correlation.  International Journal of Information Technology & Decision Making.  11 (01), 197–225 (2012).
  10. Qu Z., Wan C., Yang Z., Lee P. T.-W.  A discourse of multi-criteria decision making (MCDM) approaches.  Multi-Criteria Decision Making in Maritime Studies and Logistics.  7–29 (2018).
  11. Uçar M. K., Nour M., Sindi H., Polat K.  The effect of training and testing process on machine learning in biomedical datasets.  Mathematical Problems in Engineering.  2020, 2836236 (2020).
  12. Raschka S.  Model evaluation, model selection, and algorithm selection in machine learning.  Preprint arXiv:1811.12808 (2018).
  13. Zheng A.  Evaluating machine learning models: a beginner's guide to key concepts and pitfalls.  O'Reilly Media (2015).
  14. Torra V.  Hesitant fuzzy sets.  International Journal of Intelligent Systems.  25 (6), 529–539 (2010).
  15. Zhang N., Wei G.  Extension of VIKOR method for decision making problem based on hesitant fuzzy set.  Applied Mathematical Modelling.  37 (7), 4938–4947 (2013).
  16. Zadeh L. A.  Fuzzy sets.  Information and Control.  8 (3), 338–353 (1965).
  17. Hu J., Zhang X., Chen X., Liu Y.  Hesitant fuzzy information measures and their applications in multi-criteria decision making.  International Journal of Systems Science.  47 (1), 62–76 (2016).
  18. Gal T., Stewart T., Hanne T. (Eds.).  Multicriteria decision making: advances in MCDM models, algorithms, theory, and applications.  Springer Science + Business Media, New York (2013).
  19. Hwang C. L., Yoon K.  Methods for multiple attribute decision making.  Multiple Attribute Decision Making. 58–191 (1981).
  20. Shih H.-S., Shyur H.-J., Lee E. S.  An extension of TOPSIS for group decision making.  Mathematical and Computer Modelling.  45 (7–8), 801–813 (2007).
  21. Xu Z., Zhang X.  Hesitant fuzzy multi-attribute decision making based on TOPSIS with incomplete weight information.  Knowledge-Based Systems.  52, 53–64 (2013).
  22. Sayadi M. K., Heydari M., Shahanaghi K.  Extension of VIKOR method for decision making problem with interval numbers.  Applied Mathematical Modelling.  33 (5), 2257–2262 (2009).