Wearable Devices and Digital Biomarkers for Optimizing Training Tolerances and Athlete Performance: A Case Study of a National Collegiate Athletic Association Division III Soccer Team over a One-Year Period.
Dhruv R SeshadriHelina D VanBibberMaia P SethiEthan R HarlowJames E VoosPublished in: Sensors (Basel, Switzerland) (2024)
Wearable devices in sports have been used at the professional and higher collegiate levels, but not much research has been conducted at lower collegiate division levels. The objective of this retrospective study was to gather big data using the Catapult wearable technology, develop an algorithm for musculoskeletal modeling, and longitudinally determine the workloads of male college soccer (football) athletes at the Division III (DIII) level over the course of a 12-week season. The results showed that over the course of a season, (1) the average match workload (432 ± 47.7) was 1.5× greater than the average training workload (252.9 ± 23.3) for all positions, (2) the forward position showed the lowest workloads throughout the season, and (3) the highest mean workload was in week 8 (370.1 ± 177.2), while the lowest was in week 4 (219.1 ± 26.4). These results provide the impetus to enable the interoperability of data gathered from wearable devices into data management systems for optimizing performance and health.
Keyphrases
- big data
- body composition
- machine learning
- heart rate
- artificial intelligence
- high school
- electronic health record
- healthcare
- quality improvement
- public health
- mental health
- deep learning
- virtual reality
- blood pressure
- placebo controlled
- clinical trial
- randomized controlled trial
- health information
- risk assessment
- neural network
- social media