Towards computational solutions for precision medicine based big data healthcare system using deep learning models: A...

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Precision medicine leverages genomic data and electronic medical records (EMR) for personalized healthcare.
• Advances in DNA sequencing and EMR have enabled large-scale human genome projects.
• Deep learning models offer advanced analytical capabilities for complex health data.

Purpose of the Study:

• To review the importance of deep learning models in precision medicine research.
• To highlight state-of-the-art research using deep learning for diverse healthcare data.
• To identify future research directions in deep learning for precision medicine.

Main Methods:

• Review of deep learning applications in precision medicine.
• Analysis of deep learning model taxonomies used in healthcare research.
• Examination of data inputs, applications, repositories, and evaluation metrics.

Main Results:

• Deep learning models effectively process massive, multi-modal data at multiple abstraction levels.
• These models can autonomously identify inherent features from input data.
• The review categorizes research based on deep learning model types and their outcomes.

Conclusions:

• Deep learning is crucial for handling the diverse and disparate big data in precision medicine.
• The review provides a taxonomy of current deep learning approaches in the field.
• Promising analytical avenues for future precision medicine research are identified.