Toward Integrated Clinical and Gene Expression Profiles for Breast Cancer Prognosis: A Review Paper

International Journal of Biometric and Bioinformatics

Safaai Deris¹  Farzana Kabir Ahmad¹  Nor Hayati Othman¹ 

关键词: Gene expression;    Classification;    Prognosis;    Feature selection;    Breast cancer;   

DOI  :  

学科分类：计算机科学（综合）

来源: Computer Science Journals

【 摘 要 】

Breast cancer patients with the same diagnostic and clinical prognostic profile can have markedly different clinical outcome. This difference is possibly caused by the limitation of current breast cancer prognostic indices, which group molecularly distinct patients into similar clinical classes based mainly on morphological of disease. Traditional clinical based prognosis models were discovered contain some restriction to address the heterogeneity of breast cancer.The invention of microarray technology and its ability to simultaneously interrogate thousands genes has changed the paradigm of molecular classification of human cancers as well as it shifted clinical prognosis model to broader prospect. Numerous studies have revealed the potential value of gene expression signatures in examining the risk of disease recurrence. However, currently most of these studies attempted to implement genetic marker based prognostic models to replace the traditional clinical markers, yet neglecting the rich information contain in clinical information. Therefore, this research took an effort to integrate both clinical and microarray data in order to obtain accurate breast cancer prognosis, by taking into account that these data complements each other. This article presents a review of the development of breast cancer prognosis models, concentrating precisely on clinical and gene expression profiles. The literature is reviewed in an explicit machine learning framework, which include the elements of feature selection and classification techniques.

【 授权许可】

Unknown