Revisiting N-CNN for Clinical Practice

Autor(es)

Ferreira, Leonardo Antunes ; Carlini, Lucas Pereira ; Sa Coutrin, Gabriel de Almeida ; Heideirich, Tatiany Marcondes ; de Moraes Barros, Marina Carvalho ; Guinsburg, Ruth ; Thomaz, Carlos Eduardo

• Tipo de documento: Artigo Científico
• Fonte: PREDICTIVE INTELLIGENCE IN MEDICINE, PRIME 2023; v. 14277, p. 10-pg., 2023-01-01.

Resumo

This paper revisits the Neonatal Convolutional Neural Network (N-CNN) by optimizing its hyperparameters and evaluating how they affect its classification metrics, explainability and reliability, discussing their potential impact in clinical practice. We have chosen hyper-parameters that do not modify the original N-CNN architecture, but mainly modify its learning rate and training regularization. The optimization was done by evaluating the improvement in F1 Score for each hyperparameter individually, and the best hyperparameters were chosen to create a Tuned N-CNN. We also applied soft labels derived from the Neonatal Facial Coding System, proposing a novel approach for training facial expression classification models for neonatal pain assessment. Interestingly, while the Tuned N-CNN results point towards improvements in classification metrics and explainability, these improvements did not directly translate to calibration performance. We believe that such insights might have the potential to contribute to the development of more reliable pain evaluation tools for newborns, aiding healthcare professionals in delivering appropriate interventions and improving patient outcomes. (AU)

• Processo FAPESP: 18/13076-9 - Imagens de Faces, Extração de Características e Reconhecimento de Padrões: Métodos Computacionais para Avaliação de Dor em Recém-Nascidos
• Beneficiário: Carlos Eduardo Thomaz
• Modalidade de apoio: Auxílio à Pesquisa - Regular