Knowledge Discovery-Based Computational Technologies for Medical Big Data
1City University of Hong Kong, Hong Kong
2Shantou University, Shantou, China
3University of Alberta, Edmonton, Canada
Knowledge Discovery-Based Computational Technologies for Medical Big Data
Description
The advent of the 5G era has greatly promoted the development of telemedicine. However, as medical equipment is upgraded, this causes the amount of obtained medical data to increase exponentially and the data to become high-dimensional, diversified, and multi-structured. Medical big data includes physical parameters, biochemical indicators, electromyogram (EMG) signals, electroencephalogram (EEG) signals, X-ray images, ultrasound, and text files, among others.
Discovering the hidden valuable knowledge in massive and irregular data is challenging work. A new effective approach to deal with medical big data is the use of artificial intelligence (AI) technology, which mainly includes three tasks: supervised learning, semi-supervised learning, and unsupervised learning. Supervised learning is mainly used for disease diagnosis and prediction of medical events, whereas unsupervised learning and semi-supervised learning are mainly used to mine the potential correlation information in medical features. The aim of learning is to find useful information in the original data. Generally speaking, the collected medical original data will be preprocessed, which includes data denoising, filling, dimensionality reduction, and transformation. The mathematical model is then constructed and solved using statistical methods, nonlinear optimization, and intelligent algorithms, among other technologies.
The purpose of this Special Issue is to collect recent research into the construction of innovative mathematical models for medical big data processing and to discuss the latest machine learning methods for processing medical data. We also aim to collect the latest association rule mining methods, classification mining and analysis methods, cluster analysis methods, anomaly mining and analysis methods, and epidemic monitoring and prediction models. We welcome both original research and review articles.
Potential topics include but are not limited to the following:
- Feature selection technology in medical data
- Feature extraction technology in medical data
- Data dimensionality reduction methods in medical data
- Disease diagnosis and treatment based on medical data
- Epidemic monitoring and forecasting models based on medical data
- Mining and analysis models of abnormal medical data
- Chronic disease prevention models based on medical big data
- Medical data association rule discovery based on deep learning
- Health management models based on deep learning
- Multi-source medical data fusion