NUMERO: #20240632

Título: EXPLORING THE POTENTIAL OF MULTILAYER PERCEPTRON IN CLASSIFYING SALIVARY GLAND TUMORS

Nome do Apresentador: Anna Luiza Damaceno ARAUJO

Categoria do Trabalho: Painel de pesquisa científica (PPC)

Área Temática: Estomatologia

Resumo: Objective: This study investigated the use of a multilayer perceptron (MLP) to classify salivary gland tumors (SGT) into benign and malignant based on clinical predictors.
Methods: We performed a retrospective cross-sectional study with a cohort of 100 patients diagnosed with SGT, including fifty benign and fifty malignant tumors, confirmed by biopsy, between 2005 and 2022. We used 5-fold cross-validation to train a MLP with 9 data input, two hidden layers with 100 and 50 neurons and 5 output neurons. Performance metrics, such as accuracy, sensitivity, specificity and F1-score, were calculated for each fold.
Results: MLP achieved an average accuracy of 0.78, sensitivity of 0.63, specificity of 0.90 and F1-score of 0.59, demonstrating promising performance.
Conclusion: The results indicate that MLP is an effective tool to assist in the in differentiation of benign and malignant SGT based on clinical predictors, offering valuable insights for clinical practice. This methodology provides a comprehensive and accurate approach to evaluating predictive models, enabling detailed analysis of their performance and generalization to unseen data.

Autor 1:  Anna Luiza Damaceno ARAUJO

E-mail 1:  [email protected]

Autor 2:   Luís Arthur de Melo TASSINARI

E-mail 2:  [email protected]

Autor 3 :  Matheus Cardoso MORAES

E-mail 3:  [email protected]

Autor 4:  Márcio Ajudarte LOPES

E-mail 4:  [email protected]

Autor 5:  Pablo Agustin VARGAS

E-mail 5:  [email protected]

Autor 6:  Luiz Paulo KOWALSKI

E-mail 6:  [email protected]

Autor 7:  Alan Roger SANTOS-SILVA

E-mail 7:  [email protected]