Background: Lung cancer is one of the most common types of cancer, among which lung adenocarcinoma accounts\nfor the largest proportion. Currently, accurate staging is a prerequisite for effective diagnosis and treatment of lung\nadenocarcinoma. Previous research has used mainly single-modal data, such as gene expression data, for classification\nand prediction. Integrating multi-modal genetic data (gene expression RNA-seq, methylation data and copy number\nvariation) from the same patient provides the possibility of using multi-modal genetic data for cancer prediction. A\nnew machine learning method called gcForest has recently been proposed. This method has been proven to be\nsuitable for classification in some fields. However, the model may face challenges when applied to small samples and\nhigh-dimensional genetic data.\nResults: In this paper, we propose a multi-weighted gcForest algorithm (MLW-gcForest) to construct a lung\nadenocarcinoma staging model using multi-modal genetic data. The new algorithm is based on the standard\ngcForest algorithm. First, different weights are assigned to different random forests according to the classification\nperformance of these forests in the standard gcForest model. Second, because the feature vectors generated\nunder different scanning granularities have a diverse influence on the final classification result, the feature vectors\nare given weights according to the proposed sorting optimization algorithm. Then, we train three MLW-gcForest\nmodels based on three single-modal datasets (gene expression RNA-seq, methylation data, and copy number\nvariation) and then perform decision fusion to stage lung adenocarcinoma. Experimental results suggest that the\nMLW-gcForest model is superior to the standard gcForest model in constructing a staging model of lung\nadenocarcinoma and is better than the traditional classification methods. The accuracy, precision, recall, and AUC\nreached 0.908, 0.896, 0.882, and 0.96, respectively.\nConclusions: The MLW-gcForest model has great potential in lung adenocarcinoma staging, which is helpful for\nthe diagnosis and personalized treatment of lung adenocarcinoma. The results suggest that the MLW-gcForest\nalgorithm is effective on multi-modal genetic data, which consist of small samples and are high dimensional.
Loading....