What question did this study set out to answer?

Develop and evaluate canonical machine learning and deep learning models to predict the presence and clinical stages of colon cancer using extracellular vesicle RNA-seq data.

March 13, 2023SensorsOpen Access

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

View Full Paper

Ask AI

Bookmark

Develop and evaluate canonical machine learning and deep learning models to predict the presence and clinical stages of colon cancer using extracellular vesicle RNA-seq data.
Analyzed extracellular vesicle RNA-seq profiles from healthy individuals and colon cancer patients across both disease presence and staging classes.
Trained and compared five canonical machine learning algorithms (kNN, LMT, RT, RC, RF) alongside three deep learning architectures (1-D CNN, LSTM, BiLSTM).
Optimized deep learning hyperparameters using a genetic meta-heuristic optimization algorithm.
For cancer presence prediction, 1-D CNN achieved the highest accuracy among deep learning models at 97.67%, while Random Committee, Logistic Model Tree, and Random Forest achieved 97.33% among canonical classifiers.
For cancer staging classification, BiLSTM yielded the highest performance at 98.00% accuracy, followed by 1-D CNN at 97.00% and Random Forest at 97.33%.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Bioinformatics study demonstrates high diagnostic and staging accuracy using RNA-seq models in colon cancer patients, highlighting the utility of extracellular vesicle transcriptomics.

Cite This Study

Bostancı et al. (2023) studied this question.

synapsesocial.com/papers/6a87bef80316bff1e9fe73b2 https://doi.org/10.3390/s23063080

View Full Paper

Ask AI

Bookmark

Implication

Bioinformatics study demonstrates high diagnostic and staging accuracy using RNA-seq models in colon cancer patients, highlighting the utility of extracellular vesicle transcriptomics.

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

Key Points

Discussion

Implication

Cite This Study

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider