Interpretable Machine Learning in Healthcare through Generalized Additive Model with Pairwise Interactions (GA2M): Predicting Severe Retinopathy of Prematurity

Karatekin T., Sancak S., Çelik G., Topçuoǧlu S., Karatekin G., Kirci P., ...Daha Fazla

2019 International Conference on Deep Learning and Machine Learning in Emerging Applications, Deep-ML 2019, İstanbul, Türkiye, 26 - 28 Ağustos 2019, ss.61-66 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/deep-ml.2019.00020
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.61-66
  • Anahtar Kelimeler: GA2M, GAM, generalized additive model, interpretability of machine learning in healthcare, logistic regression, neonatology, Retinopathy of Prematurity (RoP)
  • İstanbul Gelişim Üniversitesi Adresli: Evet

Özet

© 2019 IEEE.We have investigated the risk factors that lead to severe retinopathy of prematurity using statistical analysis and logistic regression as a form of generalized additive model (GAM) with pairwise interaction terms (GA2M). In this process, we discuss the trade-off between accuracy and interpretability of these machine learning techniques on clinical data. We also confirm the intuition of expert neonatologists on a few risk factors, such as gender, that were previously deemed as clinically not significant in RoP prediction.