Video Analysis of Head Impact Sensor Data From Adolescent Soccer Players

Background: Recent advances in technology have enabled the development of head impact sensors, which provide a unique opportunity for sports medicine researchers to study head kinematics in contact sports. Studies have suggested that video or observer confirmation of head impact sensor data is required to remove false positives. In addition, manufacturer filtering algorithms may be ineffective in identifying true positives and removing true negatives. Purpose: To (1) identify the percentage of video-confirmed events recorded by headband-mounted sensors in high school soccer through video analysis, overall and by sex; (2) compare video-confirmed events with the classification by the manufacturer filtering algorithms; and (3) quantify and compare the kinematics of true- and false-positive events. Study Design: Cohort study; Level of evidence, 2. Methods: Adolescent female and male soccer teams were instrumented with headband-mounted impact sensors (SIM-G; Triax Technologies) during games over 2 seasons of suburban high school competition. Sensor data were sequentially reduced to remove events recorded outside of game times, associated with players not on the pitch (ie, field) and players outside the field of view of the camera. With video analysis, the remaining sensor-recorded events were identified as an impact event, trivial event, or nonevent. The mechanisms of impact events were identified. The classifications of sensor-recorded events by the SIM-G algorithm were analyzed. Results: A total of 6796 sensor events were recorded during scheduled varsity game times, of which 1893 (20%) were sensor-recorded events associated with players on the pitch in the field of view of the camera during verified game times. Most video-confirmed events were impact events (n = 1316, 70%), followed by trivial events (n = 396, 21%) and nonevents (n = 181, 10%). Female athletes had a significantly higher percentage of trivial events and nonevents with a significantly lower percentage of impact events. Most impact events were head-to-ball impacts (n = 1032, 78%), followed by player contact (n = 144, 11%) and falls (n = 129, 10%) with no significant differences between male and female teams. The SIM-G algorithm correctly identified 70%, 52%, and 66% of video-confirmed impact events, trivial events, and nonevents, respectively. Conclusion: Video confirmation is critical to the processing of head impact sensor data. Percentages of video-confirmed impact events, trivial events, and nonevents vary by sex in high school soccer. Current manufacturer filtering algorithms and magnitude thresholds are ineffective at correctly classifying sensor-recorded events and should be used with caution.

Download Full-text

Football concussion case series using biomechanical and video analysis

Neurology ◽

10.1212/01.wnl.0000550623.36010.20 ◽

2018 ◽

Vol 91 (23 Supplement 1) ◽

pp. S2.2-S2

Author(s):

Mirellie Kelley ◽

Jillian Urban ◽

Derek Jones ◽

Alexander Powers ◽

Christopher T. Whitlow ◽

...

Keyword(s):

Video Analysis ◽

Case Series ◽

Linear Acceleration ◽

The United States ◽

Head Impact ◽

Rotational Acceleration ◽

Impact Location ◽

Injury Mechanisms ◽

The Mean ◽

Impact Data

Approximately 1.1–1.9 million sport-related concussions among athletes ≤18 years of age occur annually in the United States, but there is limited understanding of the biomechanics and injury mechanisms associated with concussions among lower level football athletes. Therefore, the objective of this study was to combine biomechanical head impact data with video analysis to characterize youth and HS football concussion injury mechanisms. Head impact data were collected from athletes participating on 22 youth and 6 HS football teams between 2012 and 2017. Video was recorded, and head impact data were collected during all practices and games by instrumenting players with the Head Impact Telemetry (HIT) System. For each clinically diagnosed concussion, a video abstraction form was completed, which included questions concerning the context in which the injury occurred. Linear acceleration, rotational acceleration, and impact location were used to characterize the concussive event and each injured athlete's head impact exposure on the day of the concussion. A total of 9 (5 HS and 4 youth) concussions with biomechanics and video of the event were included in this study. The mean [range] linear and rotational acceleration of the concussive impacts were 62.9 [29.3–118.4] g and 3,056.7 [1,046.8–6,954.6] rad/s2, respectively. Concussive impacts were the highest magnitude impacts for 6 players and in the top quartile of impacts for 3 players on the day of injury. Concussions occurred in both practices (N = 4) and games (N = 5). The most common injury contact surface was helmet-to-helmet (N = 5), followed by helmet-to-ground (N = 3) and helmet-to-body (N = 1). All injuries occurred during player-to-player contact scenarios, including tackling (N = 4), blocking (N = 4), and collision with other players (N = 1). The biomechanics and injury mechanisms of concussions varied among athletes in our study; however, concussive impacts were among the highest severity for each player and all concussions occurred as a result of player-to-player contact.

Download Full-text

Laboratory and field evaluation of a small form factor head impact sensor in un-helmeted play

Proceedings of the Institution of Mechanical Engineers Part P Journal of Sports Engineering and Technology ◽

10.1177/1754337117739458 ◽

2017 ◽

Vol 232 (3) ◽

pp. 242-254 ◽

Cited By ~ 3

Author(s):

Derek Nevins ◽

Kasee Hildenbrand ◽

Jeff Kensrud ◽

Anita Vasavada ◽

Lloyd Smith

Keyword(s):

Form Factor ◽

Center Of Mass ◽

False Negative ◽

Angular Acceleration ◽

Linear Acceleration ◽

Field Evaluation ◽

Head Impact ◽

Sensor Data ◽

Small Form ◽

Small Form Factor

Head impact sensors are increasingly used to quantify the frequency and magnitude of head impacts in sports. A dearth of information exists regarding head impact in un-helmeted sport, despite the substantial number of concussions experienced in these sports. This study evaluated the performance of one small form factor head impact sensor in both laboratory and field environments. In laboratory tests, sensor performance was assessed using a Hybrid III headform and neck. The headform assembly was mounted on a low-friction sled and impacted with three sports balls over a range of velocities (10–31 m/s) at two locations and from three directions. Measures of linear and angular acceleration obtained from the small form factor wireless sensor were compared to measures of linear and angular acceleration obtained by wired sensors mounted at the headform center of mass. Accuracy of the sensor varied inversely with impact magnitude, with relative differences across test conditions ranging from 0.1% to 266.0% for peak linear acceleration and 4.7% to 94.6% for peak angular acceleration when compared to a wired reference system. In the field evaluation, eight male high school soccer players were instrumented with the head impact sensor in seven games. Video of the games was synchronized with sensor data and reviewed to determine the number of false positive and false negative head acceleration event classifications. Of the 98 events classified as valid by the sensor, 20.5% (20 impacts) did not result from contact with the ball, another player, the ground or player motion and were therefore considered false positives. Video review of events classified as invalid or spurious by the sensor found 77.8% (14 of 18 impacts) to be due to contact with the ball, another player or player motion and were considered false negatives.

Download Full-text

Player-Driven Video Analysis to Enhance Reflective Soccer Practice in Talent Development

International Journal of Game-Based Learning ◽

10.4018/ijgbl.2018040103 ◽

2018 ◽

Vol 8 (2) ◽

pp. 29-43 ◽

Cited By ~ 1

Author(s):

Anders Hjort ◽

Kristoffer Henriksen ◽

Lars Elbæk

Keyword(s):

Video Analysis ◽

Role Models ◽

Deliberate Practice ◽

Reflective Learning ◽

Soccer Players ◽

Youth Soccer ◽

Analysis Process ◽

Analysis Platform ◽

Analytical Platforms ◽

Game Performance

In the present article, we investigate the introduction of a cloud-based video analysis platform called Player Universe (PU). Video analysis is not a new performance-enhancing element in sports, but PU is innovative in how it facilitates reflective learning. Video analysis is executed in the PU platform by involving the players in the analysis process, in the sense that they are encouraged to tag game actions in video-documented soccer matches. Following this, players can get virtual feedback from their coach. Findings show that PU can improve youth soccer players' reflection skills through consistent video analyses and tagging; coaches are important as role models and providers of feedback; and that the use of the platform primarily stimulated deliberate practice activities. PU can be seen as a source of inspiration for soccer players and clubs as to how analytical platforms can motivate and enhance reflective learning for better in-game performance.

Download Full-text

Head impacts in semiprofessional male Soccer players: a prospective video analysis over one season of competitive games

Brain Injury ◽

10.1080/02699052.2020.1831067 ◽

2020 ◽

Vol 34 (12) ◽

pp. 1685-1690

Author(s):

Hélène Cassoudesalle ◽

Maxime Bildet ◽

Hervé Petit ◽

Patrick Dehail

Keyword(s):

Video Analysis ◽

Soccer Players ◽

Head Impacts ◽

Competitive Games

Download Full-text

Characterization of On-Field Head Impact Exposure in Youth Soccer

Journal of Applied Biomechanics ◽

10.1123/jab.2020-0071 ◽

2020 ◽

pp. 1-7

Author(s):

Brian T. Tomblin ◽

N. Stewart Pritchard ◽

Tanner M. Filben ◽

Logan E. Miller ◽

Christopher M. Miles ◽

...

Keyword(s):

Linear Acceleration ◽

Head Impact ◽

Video Data ◽

Soccer Players ◽

Youth Soccer ◽

Head Impacts ◽

Head Kinematics ◽

Frequency Of Contact ◽

Ball Contact

The objective of this research was to characterize head impacts with a validated mouthpiece sensor in competitive youth female soccer players during a single season with a validated mouthpiece sensor. Participants included 14 youth female soccer athletes across 2 club-level teams at different age levels (team 1, ages 12–13 y; team 2, ages 14–15 y). Head impact and time-synchronized video data were collected for 66 practices and games. Video data were reviewed to characterize the type and frequency of contact experienced by each athlete. A total of 2216 contact scenarios were observed; heading the ball (n = 681, 30.7%) was most common. Other observed contact scenarios included collisions, dives, falls, and unintentional ball contact. Team 1 experienced a higher rate of headers per player per hour of play than team 2, while team 2 experienced a higher rate of collisions and dives. A total of 935 video-verified contact scenarios were concurrent with recorded head kinematics. While headers resulted in a maximum linear acceleration of 56.1g, the less frequent head-to-head collisions (n = 6) resulted in a maximum of 113.5g. The results of this study improve the understanding of head impact exposure in youth female soccer players and inform head impact exposure reduction in youth soccer.

Download Full-text

Head Impact Exposure and Mechanisms in Female High School Lacrosse via an Instrumented Mouthguard

Neurology ◽

10.1212/01.wnl.0000801856.45976.d2 ◽

2021 ◽

Vol 98 (1 Supplement 1) ◽

pp. S13.2-S14

Author(s):

Colin M. Huber ◽

Declan A. Patton ◽

Susan Margulies ◽

Christina Master ◽

Kristy Arbogast

Keyword(s):

High School ◽

Angular Acceleration ◽

Head Impact ◽

Sensor Data ◽

Current Debate ◽

Protective Equipment ◽

Impact Mechanism ◽

Head Impacts ◽

Impact Biomechanics ◽

Female High School

ObjectiveTo quantify the head impact biomechanics, by impact mechanism, of female high school lacrosse players during games using an instrumented mouthguard.BackgroundThere is growing concern for the neurologic effects of repetitive head impacts in sports, which have been linked with several short-term neurophysiologic deficits. Girls' lacrosse represents a popular but understudied sport with regard to head impact exposure and current debate exists as to the need for enhanced protective equipment.Design/MethodsA female high school varsity lacrosse team wore the Stanford Instrumented Mouthguard during competitive games for the 2019 season. Video footage was reviewed to confirm head impact events and remove false-positive recordings. For each impact event, the mechanism was coded as stick contact, player contact, fall, or ball contact. Head impact rates were calculated per athlete exposure (AE, defined as a single player participating in a single game).ResultsSensor data were recorded for 15 female varsity lacrosse players for 14 games and 97 AEs. During games, 31 sensor-recorded head impacts were video-confirmed resulting in a pooled average head impact rate of 0.32 impacts/AE. The video-confirmed impacts were distributed between stick contact (17, 54.8%), player contact (12, 38.7%), and falls (2, 6.5%). There were no ball impacts. Overall peak kinematics were 34.0 ± 26.6 g, 12.0 ± 9.1 rad/s, and 3,666.5 ± 2,987.6 rad/s2. Stick contacts had the highest peak linear acceleration (42.7 ± 32.2 g), angular velocity (14.5 ± 11.1 rad/s), and angular acceleration (4,242.4 ± 3,634.9 rad/s2).ConclusionsStick impacts were the most common impact mechanism and resulted in the highest peak linear and angular kinematics, which may help explain why they are the most common cause of head injury in female lacrosse. By quantifying the head impact exposure, kinematics and mechanisms in female high school lacrosse, targeted injury preventions can be developed, such as rule changes and protective equipment.

Download Full-text

Video Analysis Verification of Head Impact Events Measured by Wearable Sensors

The American Journal of Sports Medicine ◽

10.1177/0363546517706703 ◽

2017 ◽

Vol 45 (10) ◽

pp. 2379-2387 ◽

Cited By ~ 36

Author(s):

Nelson Cortes ◽

Andrew E. Lincoln ◽

Gregory D. Myer ◽

Lisa Hepburn ◽

Michael Higgins ◽

...

Keyword(s):

Video Analysis ◽

Rotational Velocity ◽

Wearable Sensors ◽

Linear Acceleration ◽

Current Data ◽

Head Impact ◽

Accelerometer Data ◽

Level Of Evidence ◽

Head Impacts ◽

Impact Events

Background: Wearable sensors are increasingly used to quantify the frequency and magnitude of head impact events in multiple sports. There is a paucity of evidence that verifies head impact events recorded by wearable sensors. Purpose: To utilize video analysis to verify head impact events recorded by wearable sensors and describe the respective frequency and magnitude. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Thirty male (mean age, 16.6 ± 1.2 years; mean height, 1.77 ± 0.06 m; mean weight, 73.4 ± 12.2 kg) and 35 female (mean age, 16.2 ± 1.3 years; mean height, 1.66 ± 0.05 m; mean weight, 61.2 ± 6.4 kg) players volunteered to participate in this study during the 2014 and 2015 lacrosse seasons. Participants were instrumented with GForceTracker (GFT; boys) and X-Patch sensors (girls). Simultaneous game video was recorded by a trained videographer using a single camera located at the highest midfield location. One-third of the field was framed and panned to follow the ball during games. Videographic and accelerometer data were time synchronized. Head impact counts were compared with video recordings and were deemed valid if (1) the linear acceleration was ≥20 g, (2) the player was identified on the field, (3) the player was in camera view, and (4) the head impact mechanism could be clearly identified. Descriptive statistics of peak linear acceleration (PLA) and peak rotational velocity (PRV) for all verified head impacts ≥20 g were calculated. Results: For the boys, a total recorded 1063 impacts (2014: n = 545; 2015: n = 518) were logged by the GFT between game start and end times (mean PLA, 46 ± 31 g; mean PRV, 1093 ± 661 deg/s) during 368 player-games. Of these impacts, 690 were verified via video analysis (65%; mean PLA, 48 ± 34 g; mean PRV, 1242 ± 617 deg/s). The X-Patch sensors, worn by the girls, recorded a total 180 impacts during the course of the games, and 58 (2014: n = 33; 2015: n = 25) were verified via video analysis (32%; mean PLA, 39 ± 21 g; mean PRV, 1664 ± 619 rad/s). Conclusion: The current data indicate that existing wearable sensor technologies may substantially overestimate head impact events. Further, while the wearable sensors always estimated a head impact location, only 48% of the impacts were a result of direct contact to the head as characterized on video. Using wearable sensors and video to verify head impacts may decrease the inclusion of false-positive impacts during game activity in the analysis.

Download Full-text

Heading in Soccer: Does Kinematics of the Head‐Neck‐Torso Alignment Influence Head Acceleration?

Journal of Human Kinetics ◽

10.2478/hukin-2021-0012 ◽

2021 ◽

Vol 77 (1) ◽

pp. 71-80

Author(s):

Stephan Becker ◽

Joshua Berger ◽

Oliver Ludwig ◽

Daniel Günther ◽

Jens Kelm ◽

...

Keyword(s):

Scientific Evidence ◽

Cumulative Effect ◽

Head Impact ◽

Soccer Players ◽

Head Acceleration ◽

Ball Speed ◽

Significant Difference ◽

Potential Risks ◽

The Relationship ◽

Head Neck

Abstract There is little scientific evidence regarding the cumulative effect of purposeful heading. The head-neck-torso alignment is considered to be of great importance when it comes to minimizing potential risks when heading. Therefore, this study determined the relationship between head-neck-torso alignment (cervical spine, head, thoracic spine) and the acceleration of the head, the relationship between head acceleration and maximum ball speed after head impact and differences between head accelerations throughout different heading approaches (standing, jumping, running). A total of 60 male soccer players (18.9 ± 4.0 years, 177.6 ± 14.9 cm, 73.1 ± 8.6 kg) participated in the study. Head accelerations were measured by a telemetric Noraxon DTS 3D Sensor, whereas angles for the head-neck-torso alignment and ball speed were analyzed with a Qualisys Track Manager program. No relationship at all was found for the standing, jumping and running approaches. Concerning the relationship between head acceleration and maximum ball speed after head impact only for the standing header a significant result was calculated (p = 0.024, R2 = .085). A significant difference in head acceleration (p < .001) was identified between standing, jumping and running headers. To sum up, the relationship between head acceleration and head-neck-torso alignment is more complex than initially assumed and could not be proven in this study. Furthermore first data were generated to check whether the acceleration of the head is a predictor for the resulting maximum ball speed after head impact, but further investigations have to follow. Lastly, we confirmed the results that the head acceleration differs with the approach.

Download Full-text