Computational Techniques for Diagnosing Polycystic Ovary Syndrome: A Comparative Analysis

• Roney Nogueira de Sousa IFCE
• Ana Júlia Lopes de Brito UFC

DOI: https://doi.org/10.5753/ercas.2024.238700

Abstract

This article compares different machine learning classifiers for identifying patients with polycystic ovary syndrome using a public dataset. Techniques such as z-score normalization, outlier removal, and normalization through SMOTE were applied, along with k-fold cross-validation. The Random Forest algorithm stood out, achieving an accuracy of 93.20%.

References

Dabravolski, S. A., Nikiforov, N. G., Eid, A. H., Nedosugova, L. V., Starodubova, A. V., Popkova, T. V., Bezsonov, E. E., and Orekhov, A. N. (2021). Mitochondrial dysfunction and chronic inflammation in polycystic ovary syndrome. International journal of molecular sciences, 22(8):3923.

de Souza Pena, V., Gonçalves, A. C. R., Vieira, I. R., de Sousa, M. R., de Souza, A. C. D., La Croix, L. M. d. O., Fernandes, B. B., and da Cunha Gonçalves, S. J. (2022). Uma análise sobre as características da síndrome dos ovários policísticos: uma revisão de literatura. Revista Eletrônica Acervo Médico, 4:e9996–e9996.

Piccini, C. D., dos Santos Michelon, E., Medeiros, A. G., Heinen, C. A., Maranghelli, G. S., and von Eye Corleta, H. (2020). Síndrome dos ovários policísticos, complicações metabólicas, cardiovasculares, psíquicas e neoplásicas de longo prazo: uma revisão sistematizada. Clinical and Biomedical Research, 40(3).

Raperport, C. and Homburg, R. (2019). The source of polycystic ovarian syndrome. Clinical Medicine Insights: Reproductive Health, 13:1179558119871467.