Recent Advances of Knowledge Discovery Assisted Clinical Diagnosis
1Southwest University, Chongqing, China
2Hong Kong Metropolitan University, Hong Kong
3The University of Hong Kong, Hong Kong
4Department of Computer Science, Shantou University, Shantou, China
5University of Technology Sydney, Sydney, Australia
Recent Advances of Knowledge Discovery Assisted Clinical Diagnosis
Description
The emergence of the artificial intelligence (AI) era has supported the development of disease diagnosis. Diagnostic data becomes multisource and diverse, helping to explain diseases from different perspectives. Thus, discovering valuable information from abundant data and further realizing precision medicine is an urgent task for AI assisted clinical diagnosis and treatment. Recently, AI-based techniques have achieved great success in many healthcare areas such as medical imaging processing, high-throughput sequencing, biomarker detection, etc., but it still faces challenges.
As biomedical data is featured by a small number of samples with high-dimension features, designing efficient feature selection (FS) models for reducing phenotype-independent biomedical features plays an important role in biomedical detection tasks. Bio-omics, omics imaging and electronic medical records are collected in different time and spatial scales of biological systems, discovering valuable information. However, fusing multisource data for diagnosis and treatment is currently challenging.
This Special Issue encourages original research and review articles of novel contributions, recent techniques, and data analytic approaches for AI-based clinical diagnosis and treatment. We also welcome the analysis and design of feature selection and extraction for biomedical data as well as the interpretability of deep learning in clinical diagnosis.
Potential topics include but are not limited to the following:
- • Feature selection and extraction in biomedical data analysis
- • Knowledge discovery in clinical diagnosis
- • Knowledge discovery and fusion for multisource biomedical data
- • Deep learning in medical diagnosis
- • Fuzzy clustering-based medical image segmentation
- • AI-based high-throughput sequencing
- • AI-based analysis for gene expression profiling
- • AI-based cancer classification and therapy
- • Parallelization of feature learning
- • Interpretability of AI-based diagnosis