AUTHOR=Dehdar Samira , Salimifard Khodakaram , Mohammadi Reza , Marzban Maryam , Saadatmand Sara , Fararouei Mohammad , Dianati-Nasab Mostafa 

TITLE=Applications of different machine learning approaches in prediction of breast cancer diagnosis delay

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1103369

DOI=10.3389/fonc.2023.1103369

ISSN=2234-943X

ABSTRACT=Background: The increasing rate of BC incidence and mortality in Iran has turned this disease into a challenge. Delay in diagnosis leads to more advanced stages of BC and a lower chance of survival, which makes this cancer even more fatal. 
Objectives: The present study was aimed at identifying the predicting factors for delayed BC diagnosis in females in Iran.
Methods: In this study, four machine learning methods were conducted to analyze the data of 630 women with confirmed BC. To analyze the data, Extreme gradient boosting (XGBoost), Random Forest (RF), Neural Networks (NN), Logistic Regression (LR) methods were applied. 
Results: Thirty percent of patients had a delayed BC diagnosis. Of all, 88.5% of patients with delayed diagnosis were ever married, 72.1% had urban residency, and 84.8% had health insurance. The top three important factors in the RF model were urban residency (12.04), breast disease history (11.58) and having other comorbidities (10.72). In the EGB, urban residency (17.54), having other comorbidities (17.14) and age at first childbirth (> 30) (13.13) and in the LR model, having other comorbidities (49.41), older age at first childbirth (82.57) and having no childbirth (44.19) were the top factors. Finally, in the NN, we found that being married (50.05), marriage age above 30 (18.03), and other breast disease history (15.83) were the main factors predicting delay in BC diagnosis.
Conclusion:  Machine learning techniques suggest that women with an urban residency who got married or had their first child at an age older than 30 and those with no childbirth are at a higher risk of diagnosis delay, and it is necessary to be educated about BC risk factors, symptoms, and self-breast-examination to shorten the delay in diagnosis.