Determining the temporal factors of survival associated with brain and nervous system cancer patients: A hybrid machine learning methodology
Küçük Resim Yok
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Routledge Journals, Taylor & Francis Ltd
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Purpose Although different cancer types have been investigated from the perspective of biomedical sciences, machine learning-based studies have been scant. The present study aims to uncover the temporal effects of factors that are important for brain and central nervous system (BCNS) cancer survival, by proposing a machine learning methodology. Methods Several feature selection, data balancing, and machine learning algorithms (in addition to the sensitivity analysis) were employed to analyze the dynamic (i.e. varying) effects of several feature sets on the survival outputs. Results The results show that Gradient Boosting (GB) along with Logistic Regression (LR) and Artificial Neural Networks (ANN) outperform the other classification algorithms in this study. Furthermore, it has been observed that the importance of several features/variables varies from 1- to 5- and 10-year survival predictions. Conclusion Although the proposed hybrid methodology is validated on a large and feature-rich BCNS cancer data set, it can also be utilized to study survival prognostics of other cancer or chronic disease types.
Açıklama
Anahtar Kelimeler
Temporal Effect, Machine Learning, Healthcare Analytics, Parsimonious Model, Brain And Other Nervous System Cancer, Predictive Modeling
Kaynak
International Journal of Healthcare Management
WoS Q Değeri
N/A
Scopus Q Değeri
Q2
