Wednesday, December 3 | 10:10 a.m.-10:20 a.m. | W3-SSMK08-5 | Room E450A
In this Wednesday morning session, researchers will share results from a study that explored whether MRI-based classification systems -- augmented by AI -- can improve clinicians' ability to predict time to return to play in professional athletes.
The team, led by presenter Sherif Elhennawy, PhD, of Saudi German Hospital in Cairo, investigated whether the combination of AI and MRI could help classify sports-related thigh muscle injuries according to the British Athletics muscle injury classification (BAMIC) and MLG-R (Mechanism of injury, Location of injury, Grading of severity, and number of muscle Re-injuries) categorization systems.
Elhennawy and colleagues conducted a study that included 40 professional athletes who experienced thigh muscle injuries between 2018 and 2025. All participants underwent 1.5-tesla MRI within 72 hours of sustaining the injury, and the injuries were categorized with both the BAMIC and MLG-R classifications.
The researchers defined the reference standard for time to return to play as the time from injury to full team training clearance -- confirmed by the team physician and rehabilitation staff.
Overall, the group reported that the BAMIC model showed the highest correlation with time to return to play, with an area under the receiver operating curve (AUC) of 0.984. BAMIC's sensitivity was 95.5% and its specificity was 94.4%. A combination of both BAMIC and MLG-R also showed a high AUC of 0.984, a sensitivity of 96.4%, and a specificity of 94.4%.
"MRI-based classification systems like BAMIC and MLG-R … especially when augmented by AI, enables improved prediction of time to return to play in professional athletes, facilitating evidence-based rehabilitation planning and return-to-sport decisions," the researchers concluded.
