Machine Learning Techniques Driven Medicine Analysis

Dear Colleagues,

With billions of mobile devices in use worldwide, the cost of medical device connectors and sensors has fallen dramatically, and recording and transmitting medical data has never been easier. However, the transformation of physiological data into clinical information of real value requires artificial intelligence algorithms. Processing the big data implicit in biomedical time series and images, accounting for individual differences, identifying and extracting characteristic patterns of health function, and translating these patterns into guiding clinical information requires an adequate knowledge base of physiology, advanced digital signal processing capabilities, and machine learning (e.g., deep learning) skills to support this. The creation of intelligent algorithms combined with new wearable portable biosensors offers unprecedented possibilities and opportunities for remote patient monitoring (i.e., non-traditional clinical settings) and condition management. This Topic will focus on various aspects of information processing, including data pre-processing, visualization, regression, dimensionality reduction, function selection, classification (LR, SVM, NN) and its role in healthcare decision support. The focus will be on computer tools and machine learning techniques, including machine learning fundamentals, classifiers, and deep learning, in conjunction with relevant theory and using the processing of medical datasets (e.g., medical time series) as an example, covering modern artificial intelligence and its biomedical applications.

Prof. Dr. Chunhua Su
Dr. Celestine Iwendi
Topic Editors