Technology-driven athlete monitoring in volleyball: a systematic review of sensor-based systems and performance evaluation

Abstract

This systematic review gives an overview of studies dealing with the use of technology to monitor volleyball athletes during the time span from January 2015 to April 2026. By following PRISMA 2020 guidelines, we initially retrieved 2, 449 records from Scopus through a Boolean search. After stepwise screening, 29 documents ended up being reviewed. Methodological quality was, firstly, measured by the FICO framework (threshold ≥ 2/4), and AMSTAR-2 for systematic reviews was used; the reliability of the results across the reviewers was excellent (Cohen's κ = 0.81, 95% CI: 0.74, 0.88, i.e. strong agreement). Three major technology categories were identified: (1) wearable IMU-based systems, (2) GPS/LPS optical tracking, and (3) AI and machine learning analytics. Wearable devices were consistent in measuring jump load and player load (ICC > 0.87, 95% CI: 0.82, 0.93), whereas machine learning classifiers were able to recognize actions with accuracies of 85, 97%. Publication bias was very low (Egger's test, p = 0.21). The major problems identified were differences in cross-device standardization, female and youth players being, largely, absent from the studies, and laboratory sensor validation hardly reflecting real-life use.