Health care data analysis and visualization using interactive data exploration for sportsperson

• Published in: Science China. Information sciences Vol. 65; no. 6; p. 162101
• Main Authors: Liu, Hao, Zhang, Yang, Lian, Ke, Zhang, Yifei, Martínez, Oscar Sanjuán, Crespo, Rubén González
• Format: Journal Article
• Language: English
• Published: Beijing Science China Press 01.06.2022; Springer Nature B.V
• Subjects: Artificial intelligence; Big Data; Computer Science; Correlation coefficients; Data acquisition; Data analysis; Data mining; Error reduction; Health care; Information Systems and Communication Service; Remote monitoring; Research Paper; Scientific visualization; Sports; Sports training; Telemedicine; Training; Visualization; Workflow; data visualization; health monitoring; artificial intelligence; data analysis, athletics
• ISSN: 1674-733X; 1869-1919
• DOI: 10.1007/s11432-021-3412-9

Sports have scored significant attention among the public in this multifaceted world. Diverse training strategies are followed by many athletics and even flexible to adapt comfortable and optimal techniques. This fact has led physicians and educators to encourage remote health surveillance as one of the core strategies in athletic training. The need for innovative data exploration methodologies capable of facing Big Data’s influence to make remote monitoring services viable has been raised by the growing ties of networks that deliver high quantities of real-time data. This paper presents an interactive healthcare data exploration and visualization (IHDEV) model to enhance multi-scaling data analysis and visualization in the athletic health vision platform. This paper aims to simplify optimization methods to measure sportsperson muscle tension. This model illustrates a three-layer architecture with a raw data acquisition layer, data analysis layer, and visualization layer. The first layer considers the acquisition of health-related data from the athletes for remote monitoring using IoT and stores it into the cloud. The data analysis layer adapts artificial intelligence (AI) in data mining. The final layer introduces an intelligent interactive data visualization model assisted by a reactive workflow mechanism, enabling analysis and visualization solutions to be composed in a personalized data flow appropriate to the athletic training. This experimental study extended with two healthcare datasets to show the feasibility of IHDEV in promoting healthcare based athletic monitoring and improves the accuracy ratio of 96.7%, prediction ratio of 96.2%, an efficiency ratio of 96.8%, Pearson correlation coefficient of 98.2%, and reduces the error rate of 18.7% compared to other conventional models.