Skip to main navigation Skip to search Skip to main content

Longitudinal cohort study on subsequent injury risk in professional football players in the Qatar Stars League: a probabilistic approach using basic learning

  • Montassar Tabben
  • , Karim Chamari
  • , Khalid Alkhelaifi
  • , Tanvir Alam
  • , Jassim Mohammed Almulla*
  • *Corresponding author for this work
  • Aspetar Orthopaedic and Sports Medicine Hospital
  • Qatar Olympic Committee
  • Wellness and Recovery Center
  • University of Manouba
  • Hamad bin Khalifa University
  • Qatar Football Association

Research output: Contribution to journalArticlepeer-review

Abstract

Better understanding of the biomechanical and physiological mechanisms underlying subsequent injuries could have substantial implications for clinical practice in sports medicine. We investigated subsequent injury risk among professional football players in the Qatar Stars League (QSL), focusing on injury recurrence patterns over nine competitive seasons (2013–2021). Through an observational cohort study, we collected data on time-loss injuries from 1,258 players, recording 4,700 injuries categorized by body part, injury type, and recurrence. Utilizing Markov model, we explored probabilistic links between initial/index and subsequent injuries (defined as those occurring within the same season), highlighting patterns of recurrence in muscle groups prone to biomechanical strain. Our analysis identified 1,599 injuries (34% of total) as subsequent, primarily affecting the thigh (notably hamstrings) and groin. For instance, hamstring injuries exhibited an 7.5% (± 1.3%) probability of recurrence within the same season, while groin injuries had a 2.9% (± 0.82%) probability of resulting in subsequent hamstring injury. Our findings suggest that even basic probabilistic modeling, such as Markov chains, can enhance targeted injury prevention strategies. The high rate of recurrence, particularly in lower limb muscles, underscores the need for tailored rehabilitation programs emphasizing biomechanical stability. This comprehensive study offers a robust evidence base for injury mitigation strategies in elite football, recommending proactive monitoring and data-driven interventions to reduce injury recurrence and enhance player health, availability, and long-term performance.

Original languageEnglish
Pages (from-to)489-498
Number of pages10
JournalBiology of Sport
Volume43
Issue number1
DOIs
Publication statusPublished - 2026

Keywords

  • Artificial intelligence
  • Athletic injury
  • Machine learning
  • Markov chains
  • Prevention
  • Reinjury
  • Soccer
  • Subsequent injury

Fingerprint

Dive into the research topics of 'Longitudinal cohort study on subsequent injury risk in professional football players in the Qatar Stars League: a probabilistic approach using basic learning'. Together they form a unique fingerprint.

Cite this