Normalized claim
NFL clubs using Digital Athlete: 32 clubs increase
being used across all 32 NFL clubs for the first time this past season
Building a digital athlete: Using AI to rewrite the playbook on NFL player safety
Use case typePredictive decision supportUpdated Jun 13, 2026
The NFL and AWS built the Digital Athlete to improve player health and safety by combining game, practice, tracking, video, and sensor data. The system uses AI and machine learning to create a complete view of player experience, run millions of simulations, identify injury risk, and support personalized injury prevention, training, and recovery. The platform uses synchronized 38-camera 5K 60fps capture and computer vision to generate 3D pose estimation and virtual skeletons for movement analysis. It processes millions of video frames and hundreds of millions of player position data points weekly, and is used across all 32 NFL clubs.
- Organization
- National Football League
- Industry
- Other
- Location
- United States
- Published
- February 2024
Reported outcomes
500,000,000 data points/week
Practice tracking data processed per weekOther quantified impact
32 clubsNFL clubs using Digital Athlete6,800,000 frames/weekVideo frames processed per week100,000,000 points/weekPlayer locations and positions processed per week2 daysManual injury tracking time removed
Strategic outcomes
New product / capabilityCreated a league-wide injury analytics platformRisk & complianceImproved injury risk prediction and preventionNew product / capabilityEnabled 3D movement analysis for injury reviewScale & capacityDeployed across all NFL clubs
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Video frames processed per week: 6,800,000 frames/week increase
processes about 6.8 million video frames
Normalized claim
Player locations and positions processed per week: 100,000,000 points/week increase
documents around 100 million locations and positions of players on the field
Normalized claim
Practice tracking data processed per week: 500,000,000 data points/week increase
more than 500 million data points (10 Hz location data) per week
Normalized claim
Manual injury tracking time removed: 2 days decrease
removes the need for a manual injury tracking process that used to require days of work
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- National Football League
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- NFL
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Predictive Analytics
- 2Computer Vision
- 3Simulation
- NFL teams previously gathered and analyzed injury information through siloed, time-consuming manual processes.
- The league needed better ways to predict and prevent injuries and support safer training and rule decisions.
- AWS captures and combines large-scale tracking, video, equipment, weather, and play-type data for the Digital Athlete.
- AI/ML models identify helmets and helmet impacts from footage and cross-reference with Next Generation Stats data.
- The system runs millions of simulations of games and scenarios, supports risk mitigation modeling, and is developing 3D pose estimation for injury analysis.
- Used across all 32 NFL clubs.
- Processes about 6.8 million video frames and around 100 million player locations and positions per week.
- During team practices, processes about 15,000 miles of player tracking data per week, equating to more than 500 million data points.
- Removes days of manual injury tracking by club training and medical staff.
Architecture
AWS captures and combines large-scale player tracking, video, equipment, weather, and play-type data. The Digital Athlete uses AI/ML to detect helmets and impacts, runs millions of simulations, and uses synchronized 38-camera 5K60fps capture to build 3D pose estimates and virtual player skeletons for movement analysis.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
ExpandedExpanded
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2026.
Measures whether this deployment's public evidence persists — not whether the system is still in production.
Type: Customer StoryPublished: Feb 1, 2024Publisher: NFLEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Market context
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...