Detection of DICER1 Mutation at an Early Stage Using UniCNN Model

New methods of decoding biological sources and understanding artificial intelligence have created a shift in cancer care. AI, alongside sophisticated procedures, is better suited to connect tumors with individual patients. The extensions are applied using a deep learning (DL) network to forecast the probability of gene mutations from a set of well-known clinical variables. The road to applications of DL to medicine is thus evidently long and not simple, yet it appears to be possible to assist in oncologists’ decision-making with this method. We introduce the UniCNN structure based on data fusion and enhancement, which builds bioinformatics for sequence data. Our model has been tailored extensively to predict DICER1 mutations. Our model can improve early lung neoplasms regarding screening by exploring the DNA data of DICER1 gene changes. In particular, we have exceeded the existing state-of-the-art DICER1 mutation prediction models on multiple main criteria. Experimental results demonstrate that our model surpasses existing ones in critical metrics like sensitivity, accuracy, precision, F1 ratio, and AUC. Our result suggests its potential as a valuable and intriguing tool for early gene mutation detection, reducing misdiagnosis risks and enabling earlier treatment initiation.