MICRO-DOPPLER RADAR CAN IDENTIFY PREVIOUS ANTERIOR CRUCIATE LIGAMENT INJURY VERSUS CONTROL

PURPOSE: Anterior Cruciate Ligament (ACL) injuries account for one of the most devastating injuries seen commonly in sport. Current ACL injury risk prediction methods consist of mostly clinical observation and lack accuracy to identify injury risk. Micro-Doppler radar technology provides a solution as it is small, portable, inexpensive, and has been shown to distinguish very small differences between movement patterns in our preliminary work. METHODS: This is an IRB approved case control study comparing MDR signatures on a series of functional movements performed by those who had undergone ACL reconstruction vs healthy control. Subjects between 18 and 40 y/o were recruited at least 9 months post-operative and no further out than 6 years. An age and sex matched control group was also recruited. The data sets were then analyzed using established machine learning techniques with 80/20 training/test split over 10 runs to establish the accuracy of the model. RESULTS: A total of 150 subjects were successfully consented, enrolled, and completed data collection. The analysis included 59 ACL subjects and 91 controls. Five MDR “sit to stand” trials were collected for each participant and saved as 5 data files. The training set included 430 control files and 270 ACL injury files. The model was then tested with 25 ACL and 25 control trials. Ten independent validation runs were performed yielding an average accuracy of 80% classifying them as either a control or ACL reconstructed. CONCLUSIONS: We successfully identified the ACLI reconstruction and control groups 80% of the time with a sit to stand test observed by MDR. The ACLI group is at risk for having a subsequent surgery 25% of the time demonstrating that MDR is able to identify “at risk” patient populations. Subsequent research should seek to use MDR to prospectively identify those “at risk” for ACLI prior to the injury, so that limited preventative resources can be implemented to the highest risk population. Supported by: This work was supported by the Department of Defense through the FY21, Peer Reviewed Orthopaedic Research Program under Award No. W81XWH2210684. Opinions, interpretations, CONCLUSIONS and recommendations are those of the author and are not necessarily endorsed by the Department of Defense.