Identifying Key Genetic Variant for Interstitial Lung Disease in Lung Cancer Patients by Machine Learning

• Main Authors: Hsieh, Min-Wei, 謝閔薇
• Other Authors: Chen, Sheng-I
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/nx75y2

碩士 === 國立交通大學 === 工業工程與管理系所 === 107 === Lung cancer has long been the top-ranking cause of deaths in Taiwan. The World Health Organization has also ranked lung cancer as the most common cause of death. Although interstitial lung disease is not a malignancy, it is difficult to treat the disease to prolong patient’s survival and various subtypes are unable to be diagnosed in the early stage. Interstitial lung disease is often accompanied by lung cancer, the causation of both diseases is not yet clear, and the cause leading to both diseases is still unknown. In order to identify key factors, we explore the relationship between both diseases from a genetic perspective. Through the surgical specimens of lung cancer patients and interstitial lung disease concurred with lung cancer patients obtained by the Next Generation Sequencing, the challenge we encountered with is that the data only contains a very small number of samples. We apply machine learning to identify key factors associated with the diseases among a large number of gene bases, where six different methods related to sampling and feature selection are used. The goal of our study is to identify key factors to trigger both interstitial lung disease and lung cancer simultaneously. With the application of machine learning, this study will provide a direction for further genomic study on other diseases.