Last week at Teradata Universe 2019, we sponsored a roundtable on Next-gen Concepts for Player Performance and Wellness. Participants included experts in professional sports, brain health, cardiovascular health and Artificial Intelligence (AI). With increasing cultural awareness around the role of brain health in maintaining player performance and reducing player risk in professional sports, leaders from industry, academia, professional sports and start-ups discussed the latest methods in measuring indicators of physical health and mental wellness using Teradata Vantage, as well as new sensors, including EEG headsets provided by Wavi Performance.
Leading up to the workshop, we analyzed several EEG scans and conducted preliminary results comparing anonymized brain measurements of various populations, including:
Professional & high school athletes in different sports (football, basketball, rugby and soccer);
Military personnel (pilots, special forces and non-combatants) and;
Teradata executive leaders.
The results were presented at this roundtable, highlighting distinct differences in subsets of the brain measures in particular sports, as seen in Figure 1, or across these professions, as seen in Figure 2.
Figure 1 - P300 Delay vs Theta/Beta ration for Athletes in Various Sports
Figure 2 - Reaction Time vs P300 Delay for high performers in sports, industry and military domains
We spent some time looking at EEG results from various high performers in different domains. In particular, Figure 2 shows NFL athletes demonstrated a lower physical reaction time to novel stimuli, while other high performers in post-combat military or athletes in high-flow sports (e.g. soccer, basketball) showed higher P300 delays than athletes in the NFL. P300 is a measure of brain response speed and attentional resources; an increase in P300 delay may signal changes in cognitive function.
The discussion highlighted that, by using more objective data, sports enterprises can enable more thorough statistical analysis of these observations. These observations would then allow athletes and sports teams to utilize brain measurements to unlock each player’s unique potential and reduce the risks of brain injury across their career.
These observations would then allow athletes and sports teams to utilize brain measurements to unlock each player’s unique potential and reduce the risks of brain injury across their career.
Another example discussed in our roundtable was tangential to sports but still highly relevant. We conducted EEGs scan on several executive leaders in Teradata and demonstrated a well-understood phenomenon between the relation of cognitive speed and theta/beta. Theta and Beta frequency bands are affected by cortical arousal and can give insight into how your brain functions. Figure 3 shows that in our Teradata executives, higher theta/beta ratios may present as inattention, while others may benefit from cortical arousal. This is illustrated by a linear relationship where higher theta/beta was proportionate with lower cognitive speed, with most subjects demonstrating higher F3/F4 alpha power. Large differences in alpha power between the left-front and right-front of the brain have been associated with anxiety. It’s not easy being an executive so maybe EEG can be used in a corporate wellness program for high performers!
Figure 3 - P300 Delay vs Theta/Beta for Teradata Executives
During the second half of the roundtable, we focused on the “Digital Twin” concept. The “Digital Twin," illustrated in Figure 4, is a digital replica of a living or non-living physical entity where, by bridging the physical and the virtual world, data is transmitted seamlessly. This “Digital Twin” concept allows the virtual entity to exist simultaneously with the physical entity. Using the wide array of multi-modal sensors available today, we can create a digital twin of an athlete by combining physical performance data (e.g., video and wearable sensors), brain & mental health data (e.g., EEG, social media) and general wellness (e.g., injury logs, electronic medical records EMRs).
Figure 4 - The Digital Twin is an essential concept for harnessing EEG sensors
Computational AI models could then be trained to predict the interactions of different factors and the effects of various interventions (e.g., time off, brain training, dietary supplements). These predictions would then inform the selection of the best set of actions to improve the athlete’s performance and reduce risk. In a sports or even a corporate wellness program, this could be used to prevent burn-out and monitor the time course of recovery after mild traumatic brain injuries (mTBIs) caused by concussions or other adverse events. Creating such a digital twin would require measuring an athlete’s brain baselines and repeating these measurements across his or her career.
Figure 5 - By applying Pervasive Data Intelligence to the Player Digital Twin, we can improve Player Performance & Player Wellness
The discussion also highlighted an interesting analog to these professional sports concepts, namely e-gaming. Since e-gaming relies heavily on players' mental skills and is often performed in a controlled stationary environment, participants identified e-gaming as one of the areas where players could most benefit from longitudinal brain measurements and discussed practical ways to incorporate these into a player’s regiment.
These are exciting times for the application of AI in fields such as sports, e-sports, sports medicine and mental health. The future of sports, and other high-performance, competitive activities, is unlimited given the precise application of AI for Player Performance & Wellness. By leveraging Pervasive Data Intelligence in Teradata Vantage, seen in Figure 5, new insights using AI are readily available for the next-generation of high performers.
Atif is the Global VP, Emerging Practices, Artificial Intelligence & Deep Learning at Teradata.
Based in San Diego, Atif specializes in enabling clients across all major industry verticals, through strategic partnerships, to deliver complex analytical solutions built on machine and deep learning. His teams are trusted advisors to the world’s most innovative companies to develop next-generation capabilities for strategic data-driven outcomes in the areas of artificial intelligence, deep learning & data science.
Atif has more than 18 years in strategic and technology consulting, working with senior executive clients. During this time, he has both written extensively and advised organizations on numerous topics, ranging from improving the digital customer experience to multi-national data analytics programs for smarter cities, cyber network defense for critical infrastructure protection, financial crime analytics for tracking illicit funds flow, and the use of smart data to enable analytic-driven value generation for energy & natural resource operational efficiencies.