o:35321 Selecting critical features for biomedical data classification en Abstract: In this paper, the application of machine learning methods on large data sets with numerous features was investigated, with a focus on the identification of critical features in order to reduce the data and produce more accurate results. The research discusses feature extraction techniques for classifying two biomedical data sets with 62 and 71 features, respectively. The results were compared and presented using four classification techniques. The acquired results demonstrate that the selected important features typically produce more accurate results, or at least the same results while reducing the size of the data set and making data collecting easier. Keywords: feature selection, machine learning, biomedical data classification, pregnant women 1552099 10.46793/ICCBI23.136M 1552100 978-86-6125-262-4 2024-12-10T09:20:35.748Z 44 no 46 Ulfeta Marovac Državni univerzitet u Novom Pazaru 86849033 0000-0001-7232-3755 Lejlija Memić Državni univerzitet u Novom Pazaru person 53072393 0000-0002-2692-6229 Aldina Pljasković Državni univerzitet u Novom Pazaru person 29219175 0000-0003-4312-3839 Nataša Đorđević Državni univerzitet u Novom Pazaru person 0000-0002-1100-5689 Zana Dolićanin Državni univerzitet u Novom Pazaru person 2237799 0000-0003-0457-3087 Goran Babić University of Kragujevac, Faculty of Medical Sciences person 0000-0002-0837-7350 application/pdf 1701171 https://phaidrabg.bg.ac.rs/o:35321 no yes 1 70 92000001 20A01 In 2nd International Conference on Chemo and BioInformatics. University of Kragujevac, Institute for Information Technologies. 136 139 2023