Objective The return-to-sport (RTS) process is multifaceted and complex, as multiple variables may interact and influence the time to RTS. These variables include intrinsic factors of the player, such as anthropometrics and playing position, or extrinsic factors, such as competitive pressure. Providing an individualised estimation is often challenging, and yet clinical decision support tools are often rare in the industry. This study aims to demonstrate the functions of a Bayesian network by the use of a set of basic epidemiological data.

Methods To exemplify the use of Bayesian network in sports medicine, such as providing an individualised estimation time to RTS for individual players, we applied Bayesian network to a set of basic epidemiological data. Bayesian network was used as a decision support tool to model the epidemiological data and to integrate clinical data, non-clinical factors and expert knowledge. Specifically, we used the Bayesian network to capture the interaction between variables in order to 1) classify days to RTS and 2) injury severity (minimal, mild, moderate and severe).

Results Retrospective injury data of 3374 player seasons and 6143 time-loss injuries from seven seasons of the professional German football league (Bundesliga, 2014/2015 through 2020/2021) were collected from public databases and media resources. A total of twelve variables from three main categories (player’s characteristics and anthropometrics, match information and injury information) were included. The key response variables are 1) days to RTS (1-3, 4-7, 8-14, 15-28, 29-60, >60, and 2) severity (minimal, mild, moderate and severe). As there are more than two categories, producer’s and user’s accuracy was used to reflect the sensitivity and specificity of the model. The producer’s accuracy of the model for days to RTS ranges from 0.24 to 0.97, while for severity categories range from 0.73 to 1.00. The user’s accuracy of the model for days to RTS ranges from 0.52 to 0.83, while for severity categories, it ranges from 0.67 to 1.00.

Conclusions The Bayesian network can help to capture different types of data to model the probability of an outcome, such as days to return to sports. In our study, the result from the BN may support coaches and players in predicting days to RTS given an injury, 2) support team planning via assessment of scenarios based on player’s characteristics and injury risk and 3) provide evidence-based support of understanding relationships between factors and RTS. This study shows the key functions and applications of the Bayesian network in RTS, and we suggest further experimenting and developing the Bayesian network into a decision-supporting aid.

The authors have declared no competing interest.

The author(s) received no specific funding for this work.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

As the study data stems from publicly available media data, no ethical approval was needed. A consent to participate was not necessary as the study does not contain any person’s individual data.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Dataset cannot be shared publicly because it is currently in use for another research project. However, the data would be available on reasonable request.