Logistic Broken Adaptive Ridge Procedure for Colon Cancer Data Analysis

Logistic Broken Adaptive Ridge Procedure for Colon Cancer Data Analysis

Author Info

Corresponding Author
Hong Yin
School of Mathematics, Renmin University of China, Beijing

A B S T R A C T

Background: Colon cancer is the leading cause of cancer-related deaths in the world in both man and women. Knowing the causes and risk factors for colon cancer can help you understanding the importance of routine screening for colon cancer, as well as learn if you are one of the people who should begin screening at the earlier age. Due to the limitation of clinical diagnose, management and treatment outcomes, it is of great necessity to develop effective methods for colon cancer detection and prediction especially cDNA Microarrays and high- density oligonucleotide chips are increasingly used in cancer research. Methods: Here we propose a novel logistic broken adaptive ridge procedure to address the problem of colon cancer results prediction through selecting effective few variables or genes from 2000 candidate genes. Results: In total 62 cases with 40 colon cancer patients and 22 healthy patients were included in our analysis. Each case consists of 2000 genes which challenged all the competitive method. From the results, we are so surprised that our proposed method outperforms the classical variable selection approaches in error rate of training data and extra testing data. Conclusions: Logistic adaptive ridge procedure is very effective for colon cancer predictions, either in terms of prognosis or diagnose. It may benefit patients by guiding therapeutic options. We hope it will contribute to the wider biology and related communities.

Article Info

Article Type
Research Article
Publication history
Received: Wed 16, Oct 2019
Accepted: Mon 11, Nov 2019
Published: Tue 10, Dec 2019
Copyright
© 2023 Hong Yin. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Hosting by Science Repository.
DOI: 10.31487/j.COR.2019.5.14