AUTOSURV: INTERPRETABLE DEEP LEARNING FRAMEWORK FOR CANCER SURVIVAL ANALYSIS INCORPORATING CLINICAL AND MULTI-OMICS...

Area of Science:

• Oncology
• Bioinformatics
• Machine Learning

Background:

• Accurate cancer prognosis is crucial for treatment optimization and patient quality of life.
• Integrating omics data (gene expression, miRNA expression) with clinical information offers a more comprehensive prognostic view.
• Understanding molecular mechanisms underlying cancer progression is essential.

Conclusions:

• The developed deep learning framework offers a powerful tool for accurate cancer prognosis.
• Integrating multi-modal data improves the precision of cancer outcome prediction.
• Feature identification provides insights into molecular mechanisms and potential therapeutic targets.