Multimodal feature-optimized approaches for cancer classification using microarray gene expression analysis

Uncontrolled abnormal cell growth, referred to as cancer, can result in tumors, other fatal disabilities, and immune system deterioration. Typically, the treatment procedure is longer and extremely expensive owing to its higher recurrence and death rates. Early and precise detection and assessment of cancer are significant for improving patient survival rates. Moreover, initial cancer detection makes the treatment simpler and improves the rate of recovery, leading to a lower mortality rate. Gene expression data plays an important part in cancer classification at the initial phase. Precise cancer classification is a challenging and complex task because of the high-dimensional nature of gene expression data, coupled with the small sample size. With the help of artificial intelligence (AI), researchers have recently developed fundamental models utilizing AI methods to diagnose and predict cancer. These techniques now play a leading role in increasing the precision of survival predictions, cancer susceptibility, and recurrence. This paper presents an Artificial Intelligence-Based Multimodal Approach for Cancer Genomics Diagnosis Using Optimized Significant Feature Selection Technique (AIMACGD-SFST) model. The aim is to develop precise and effective techniques for cancer genomics analysis using advanced computational and analytical techniques. The preprocessing stage comprises min-max normalization, handling missing values, encoding target labels, and splitting the dataset into training and testing sets. Furthermore, the AIMACGD-SFST model employs the coati optimization algorithm (COA) method for feature selection process to choose the related features from the dataset. Finally, the ensemble models, namely deep belief network (DBN), temporal convolutional network (TCN), and variational stacked autoencoder (VSAE) are employed for the classification process. The experimental validation of the AIMACGD-SFST approach is performed under three diverse datasets. The comparison study of the AIMACGD-SFST approach illustrated superior accuracy value of 97.06%, 99.07%, and 98.55% over existing models under diverse datasets.