Comparative Analysis of LSTM and Ensemble LSTM Approaches for Gene Mutation Classification in Cancer

Dorgham, Osama, Aburass, Sanad and Rumman, Maha Abu (2023) Comparative Analysis of LSTM and Ensemble LSTM Approaches for Gene Mutation Classification in Cancer. In: 2023 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT).

Full text not available from this repository. (Request a copy)

Abstract

In this study, we present an in-depth comparison of five different deep learning approaches for the classification of gene mutations based on a dataset provided by the Kaggle competition "Personalized Medicine: Redefining Cancer Treatment." The models compared include a Long Short-Term Memory (LSTM) model, an ensemble of LSTM and Bidirectional LSTM (BiLSTM), an ensemble of LSTM and 1-Dimensional Convolutional Neural Network (1D-CNN), an ensemble of LSTM and Gated Recurrent Unit (GRU), and a multi-ensemble model combining LSTM, BiLSTM, 1D-CNN, and GRU. These models were evaluated on several metrics including accuracy, precision, recall, F1 score, and mean squared error (MSE) for both the training and validation sets. Among all the models, the LSTM + 1D-CNN ensemble model demonstrated superior performance on the validation set while also being the most time-efficient model to train. These results contribute to the growing body of research in the field of personalized medicine and highlight the efficacy of deep learning ensemble models in the classification of gene mutations, which could play a vital role in future cancer treatment strategies.

Affiliation: Skyline University College
SUC Author(s): Dorgham, Osama
All Author(s): Dorgham, Osama, Aburass, Sanad and Rumman, Maha Abu
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Gene Mutation Classification, Text Classification, Long Short-Term Memory
Subjects: A Business and Management > AK Health care and delivery
B Information Technology > BR Deep Learning
Divisions: Skyline University College > School of IT
Depositing User: Mr Mosys Team
Date Deposited: 26 Apr 2024 14:58
Last Modified: 26 Apr 2024 14:58
URI: https://research.skylineuniversity.ac.ae/id/eprint/877
Publisher URL: https://doi.org/10.1109/ICMLANT59547.2023.10372993
Publisher OA policy:
Related URLs:

    Actions (login required)

    View Item
    View Item
    Statistics for SkyRep ePrint 877 Statistics for this ePrint Item