About this Research Topic
Deep transfer learning (DTL), a technique derived from deep learning, is increasingly recognized for its ability to overcome data scarcity challenges in various fields, particularly in public health. By leveraging models that have been pre-trained on large datasets, DTL is adept at extracting intricate features from limited health data, which is often the case in these settings. Despite its considerable advantages, the real-world application of DTL in public health faces critical issues such as domain adaptation, ensuring model interpretability, mitigating biases, and addressing ethical concerns.
Goal:
This Research Topic aims to advance our understanding of how deep transfer learning can effectively tackle issues related to data diversity and deficiency in public health environments. It strives to elucidate how DTL can improve predictive accuracy in disease surveillance, enhance diagnostic procedures through medical imaging, boost efficiency in drug discovery, and refine health behavior analyses.
Scope:
This scope initially emphasizes the focus on providing solutions tailored specifically for public health tasks through the development of bespoke DTL frameworks that are robust, fair, and transparent. In pursuing these solutions, the discussion extends to various related themes, aiming to cover a broad spectrum of applications and challenges in the field:
• DTL for disease prediction and diagnosis
• Use of DTL for monitoring infectious diseases and identifying outbreaks
• The integration of DTL in medical imaging to enable early disease detection
• Enhancing drug discovery and repurposing with deep learning models
• Personalized medicine advancements leveraging DTL
• Analysis of health informatics and electronic health records through DTL
• Exploring health data from social media with deep learning techniques
• Applying DTL to design public health interventions and inform policy-making
• Addressing ethical issues and developing methodologies for DTL use in public health
Keywords: Deep transfer learning (DTL), Public Health, Health Informatics, Disease Surveillance, Medical Image Analysis, Drug Discover, Health Behaviour Analysis
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.