Premium
A model to predict the survivability of cancer comorbidity through ensemble learning approach
Author(s) -
Naghizadeh Majid,
Habibi Narges
Publication year - 2019
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/exsy.12392
Subject(s) - comorbidity , prostate cancer , cancer , boosting (machine learning) , survivability , medicine , computer science , ensemble learning , breast cancer , feature selection , oncology , machine learning , computer network
Cancer is one of the most common death causes worldwide. Breast and genital cancers in women and prostate cancer in men constitute three of the most common cancers. Detection and prevention of these types of cancers are critical objectives. Recent findings indicate that some patients suffer from cancer comorbidity. The probability of survival among patients with comorbid condition is lower than those with only one type of cancer. The importance of concomitant chronic illnesses during cancer treatment through the SEER data is assessed through many machine‐learning approaches. In order to improve the accuracy of prediction of survival rates in patients with cancer and comorbidity of cancers, the gradient boosting ensemble method is adopted for feature selection and modelling. This proposed method increases the accuracy rate and reduces the error rate, and exhibits a significant predictive improvement of survival rates in comorbid cancer compared with the previous proposed models.