Artificial Intelligence in Elite Sports—A Narrative Review of Success Stories and Challenges

Abstract

This paper explores the role of artificial intelligence (AI) in elite sports. We approach the topic from two perspectives. Firstly, we provide a literature based overview of AI success stories in areas other than sports. We identified multiple approaches in the area of Machine Perception, Machine Learning and Modeling, Planning and Optimization as well as Interaction and Intervention, holding a potential for improving training and competition. Secondly, we discover the present status of AI use in elite sports. Therefore, in addition to another literature review, we interviewed leading sports scientist, which are closely connected to the main national service institute for elite sports in their countries. The analysis of this literature review and the interviews show that the most activity is carried out in the methodical categories of signal and image processing. However, projects in the field of modeling & planning have become increasingly popular within the last years. Based on these two perspectives, we extract deficits, issues and opportunities and summarize them in six key challenges faced by the sports analytics community. These challenges include data collection, controllability of an AI by the practitioners and explainability of AI results.

Strengths, weaknesses, opportunities, and threats associated with the application of artificial intelligence in connection with sport research, coaching, and optimization of athletic performance: a brief SWOT analysis

“…When the data employed by AI fails to encompass all relevant aspects of the question being posed ( 6 ) and/or is characterized by low quality, flaws, bias, incompleteness, or unreliability, the analyses conducted and the prospective insights derived or conclusions drawn could be fallacious. Particularly worrisome in this context is the fact that the data employed to train AI models are often historical and may not always capture emerging trends, changes in techniques, strategies or rules, or individual differences that can exert a significant impact on the current situation.…”

“…This community is still in the early stages of utilizing the potential of AI ( 6 ) to maintain and improve athletic performance, prevent injuries, optimize training and assist in overall decision-making ( 7 – 9 ). However, as has already been carried out with other novel technologies being applied to the practice of and research on sports ( 10 , 11 ), an ongoing and comprehensive understanding of the potential strengths, weaknesses, opportunities, and threats (SWOT) of AI in this context is required.…”

Performance and healthcare analysis in elite sports teams using artificial intelligence: a scoping review

“…During these last years, there has been a great evolution and applications of AI and ML in sports, and some authors have defined the key challenges for AI usage in elite sports, including correct data collection, the process of connecting AI and elite sports communities, the need to keep control in the hands of practitioners, maintaining the explainability of AI results, developing robust predictive models, and closing the loop defined as the need to provide feedback to the AI system to develop quality and self-adaptation ( 5 ).…”

VO2maxprediction based on submaximal cardiorespiratory relationships and body composition in male runners and cyclists: a population study

“…Recently, we have been observing the development of prediction methods with the usage of machine learning (ML) and artificial intelligence (AI). Both ML and AI are used in sport science as forecasting and decision-making support tools (Abut and Akay, 2015;Bobowik and Wiszomirska, 2022;Chmait and Westerbeek, 2021;Hammes et al, 2022;Rossi et al, 2021).…”

“…Recently, we have been observing the development of prediction methods with the usage of machine learning (ML) and artificial intelligence (AI). Both ML and AI are used in sport science as forecasting and decision-making support tools (Abut and Akay, 2015; Bobowik and Wiszomirska, 2022; Chmait and Westerbeek, 2021; Hammes et al, 2022; Rossi et al, 2021). There is growing evidence that VO 2max prediction based on ML models, especially support vector ML and artificial neural network models, exhibits more robust and accurate results compared to multiple linear regression only (Abut and Akay, 2015; Ashfaq et al, 2022).…”