Introduction: Return-to-sport (RTS) decision-making is often challenging, as rehabilitation is complex and non-linear. With advances in technology, an increasing volume of data is being collected at multiple time points during rehabilitation to track the progression. Computer-based analytical methods, such as change point (CP) detection, can leverage the data collected longitudinally to inform clinicians of the time points when there were meaningful changes. Here, we exemplify how longitudinal data in wellness and rehabilitation running performance data could be analysed with the CP approach. The CP approach holds promises for informing clinicians the rate of progression in rehabilitation and thus allowing clinicians to quantify and evaluate the RTS process.
Methods: The case was a professional football player who sustained a lower limb muscle injury during training. Data were prospectively collected during the 2021/2022 A-League season. Four variables from wellness (mood, sleep quality, muscle soreness, and stress) and five variables from rehabilitation running performance (total distance, maximum speed, high speed running, acceleration and deceleration) were collected over 97 days. Change point algorithm, performed in the R Studio, was then used to identify meaningful changes during the rehabilitation. The CPs were determined based on the mean and variance of the segments.
Results: Two types of analysis were performed, univariate and multivariate analysis. In the univariate analysis, the change points for mood, sleep, soreness and stress were located on days 30, 47, 50 and 50 respectively. The change points for total distance, acceleration, maximum speed, deceleration and high-speed running were located on days 32, 34, 37, 41 and 41 respectively. The multivariate analysis resulted in a single change point for the wellness variables and running performance variables, on days 50 and 67 respectively.
Discussion: The univariate approach provided information specific to each of the nine wellness and running performance variables, which could help clinicians to understand the rate of progression based on a single variable. The multivariate approach has the advantage to aggregate information regarding changes from multiple variables into a common change point. The common change point could simplify multiple time series data into relatively simple output for clinicians, providing an overall impression of the rehabilitation. Furthermore, although the wellness and running performance variables in this study were from different sources and of various data formats, all the variables can be visualised together in the same panel. Clinicians are encouraged to adapt similar analytics to quantify and evaluate rehabilitation programs.
Impact and application to the field:
- •Clinicians working in RTS could use univariate change points to determine when a single performance variable has progressed or regressed.
- •Multivariate change point detection allows clinicians to simplify the information input and be less likely to be overwhelmed by the high volume and different types of data.
Conflict of interest statement: My co-authors and I acknowledge that we have no conflict of interest of relevance to the submission of this abstract