Naslov
On Cervical Cancer Diagnostics Using Machine Learning

Autori
Glučina, Matko ; Lorencin, Ariana ; Lorencin, Ivan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
RI-STEM proceedings / - , 2022, 19-22

Skup
International Student Scientific Conference (Ri-STEM 2022)

Mjesto i datum
Rijeka, Hrvatska, 08.06.2022. - 09.06.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Artificial intelligence ; Cervical cancer ; Machine learning ; Multilayer perceptron ; Neurons

Sažetak
This paper presents the classification of cervical cancer using the Multilayer Perceptron into a publicly available dataset Cervical cancer (Risk Factors) taken from the UCI Machine learning repository consisting of 36 attributes with 859 instances. The target values were Hinselmann, Schiller, Cytology, and biopsy by processing the dataset and using the GridSearch method, the MLP algorithm gives a high percentage of accuracy for all four outputs, but an insight into other metrics shows that additional research elaboration is needed. based on the f1 score the best result for Hinselmann is 0.17, Schiller in the amount of 0.4, Cytology 0.29, and Biopsy 0.19 which indicates more than enough of a poor-quality model for implementation in real conditions.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Interdisciplinarne tehničke znanosti, Temeljne medicinske znanosti

POVEZANOST RADA