Abstract
Patients at different ages have different rates of cell development and metabolisms. As a result, age should be an essential part of how a disease diagnosis model is trained and optimized. Unfortunately, most of the existing studies have not taken age into account. This study demonstrated that disease diagnosis models could be improved by merely applying individual models for patients of different age groups. Both transcriptomes and methylomes of the TCGA breast cancer dataset (TCGA-BRCA) were utilized for the analysis procedure of feature selection and classification. Our experimental data strongly suggested that disease diagnosis modeling should integrate patient age into the whole experimental design.
Highlights
Some types of cancers grow faster in younger hosts
This study modeled the early detection of breast cancer as a binary classification problem, due to the fact that there were much fewer samples in stage IV than the other three stages
The maximal information coefficient (MIC) value was in the range [0, 1] and a larger MIC value means a higher correlation between the two variables
Summary
Some types of cancers grow faster in younger hosts. Renal cancer has an average growth rate of 0.3 cm per year and many clinical studies focused on the surveillance of small tumors only in elderly patients (Mues et al, 2010; Mehrazin et al, 2014). Seven feature selection algorithms were evaluated for their classification performances on the datasets with different age groups. The balanced accuracy [bAcc = (Sn + Sp)/2] was usually utilized to evaluate the classification model without generating bias for a dataset with significantly different numbers of positive and negative samples (Feng et al, 2018).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
