Prediction of Breast Cancer Diseases From Genes Using Pso and Cso Tuned Long Short-term Memory
Preprint
- 2 April 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
Gene data set collected from a diverse population gene expression profiles, genetic variations, and clinical attributes for earlier detection cancer. Time Series Forecasting (TSF) techniques are applied and exploits temporal dependencies within the gene data, enables the prediction of breast cancer and progression. The proposed methodology such as Particle Swarm Optimization-Long Short Term Memory (PSO & LSTM) and Cat Swarm Optimization -Long Short Term Memory (CSO & LSTM) combines with gene data augmentation and analyse the temporal patterns breast cancer genes. Receiver Operating Characteristic (ROC) curve is used for evaluation the proposed models predictive performance. The proposed methods are validated in traditional dataset and collected gene data sets, from National Center for Biotechnology Information (NCBI). The results are compared with existing classification model and evaluated the effectiveness of the TSF methods such as of CSO-LSTM and PSO-LSTM in prediction of breast cancer diseases. The proposed methods contribute to early detection by leveraging time series forecasting techniques. The proposed model improves the accuracy of and reliability of breast cancer prediction, which enables health professional with more information and potentially enhances the patient outcomesKeywords
All Related Versions
This publication has 34 references indexed in Scilit:
- A self-adaptive binary cat swarm optimization using new time-varying transfer function for gene selection in DNA microarray expression cancer dataSoft Computing, 2023
- Automatic breast cancer diagnosis based on hybrid dimensionality reduction technique and ensemble classificationJournal of Cancer Research and Clinical Oncology, 2023
- Time series radiomics for the prediction of prostate cancer progression in patients on active surveillanceEuropean Radiology, 2023
- A novel deep learning motivated data augmentation system based on defect segmentation requirementsJournal of Intelligent Manufacturing, 2023
- Prediction of Rotor Slot Size Variations in Induction Motor Using Polynomial Chirplet Transform and Regression AlgorithmsArabian Journal for Science and Engineering, 2022
- A deep learning-based approach for detection of lung cancer using self adaptive sea lion optimization algorithm (SA-SLnO)Journal of Ambient Intelligence and Humanized Computing, 2022
- Optimized feature selection method using particle swarm intelligence with ensemble learning for cancer classification based on microarray datasetsNeural Computing and Applications, 2022
- Review paper on research direction towards cancer prediction and prognosis using machine learning and deep learning modelsJournal of Ambient Intelligence and Humanized Computing, 2021
- Sentiment analysis and text categorization of cancer medical records with LSTMJournal of Ambient Intelligence and Humanized Computing, 2019
- Genetic algorithm based cancerous gene identification from microarray data using ensemble of filter methodsMedical & Biological Engineering & Computing, 2018