Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202381,
        author = {Kavitha K and Aksharha S and Saraswathi K and Srinithi A and Naveena K},
        title = {Classification of Autoimmune Disease using Hybrid CNN-BiLstm Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {12176-12184},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202381},
        abstract = {Autoimmune diseases such as Type 1 Diabetes (T1D) and Multiple Sclerosis (MS) occur when the immune system mistakenly attacks the body’s own tissues. Early detection of these diseases is important for effective treatment and disease management. T cell receptor (TCR) sequences provide valuable information about immune responses and can be used to identify disease specific immune patterns.
This study proposes a computational framework for predicting autoimmune diseases using TCR sequence analysis and deep learning techniques. The dataset contains Complementarity Determining Region 3 (CDR3) sequences along with V gene and J gene information. Data preprocessing techniques are applied to clean and standardize the dataset. The biological sequences are then encoded using tokenization and padding techniques to convert them into numerical representations suitable for machine learning models.
A hybrid deep learning architecture combining Convolutional Neural Networks (CNN) and Bidirectional Long Short Term Memory (BiLSTM) is used to extract sequence level features and capture long range dependencies in TCR sequences.
The system performs classification at the TCR sequence (cell) level, predicting whether each sequence belongs to Healthy, T1D, or MS classes. Final patient diagnosis is obtained by aggregating predictions from multiple sequences using majority voting. Experimental results demonstrate high classification accuracy, indicating the effectiveness of machine learning techniques for autoimmune disease prediction.},
        keywords = {Autoimmune Disease Prediction, TCR Sequence Analysis, CNN BiLSTM, Deep Learning, Bioinformatics.},
        month = {May},
        }