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)
Statistics for this ePrint Item |