Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review

Area of Science:

• Medical Informatics
• Natural Language Processing
• Artificial Intelligence

Background:

• The rapid growth of clinical text data presents challenges for healthcare professionals.
• Existing tools and methods struggle to keep pace with daily data generation.

Purpose of the Study:

• To review text processing pipelines using deep learning in healthcare.
• To discuss applications of deep learning in clinical text analysis.
• To identify challenges and future research scopes.

Main Methods:

• Survey of deep learning models including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU).
• Analysis of text processing pipelines in the healthcare domain.

Main Results:

• Deep learning methods offer solutions for analyzing vast clinical text data.
• Applications include clinical concept extraction, dialogue systems, sentiment analysis, clinical trial matching, and pharmacovigilance.

Conclusions:

• Deep learning and text processing integration is crucial for optimizing healthcare.
• Further research is needed to address challenges in deploying these technologies in clinical settings.