TY - JOUR
T1 - Advanced treatment monitoring for olympic-level athletes using unsupervised modeling techniques
AU - Siedlik, Jacob A.
AU - Bergeron, Charles
AU - Cooper, Michael
AU - Emmons, Russell
AU - Moreau, William
AU - Nabhan, Dustin
AU - Gallagher, Philip
AU - Vardiman, John P.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Context: Analysis of injury and illness data collected at large international competitions provides the US Olympic Committee and the national governing bodies for each sport with information to best prepare for future competitions. Research in which authors have evaluated medical contacts to provide the expected level of medical care and sports medicine services at international competitions is limited. Objective: To analyze the medical-contact data for athletes, staff, and coaches who participated in the 2011 Pan American Games in Guadalajara, Mexico, using unsupervised modeling techniques to identify underlying treatment patterns. Design: Descriptive epidemiology study. Setting: Pan American Games. Patients or Other Participants: A total of 618 US athletes (337 males, 281 females) participated in the 2011 Pan American Games. Main Outcome Measure(s): Medical data were recorded from the injury-evaluation and injury-treatment forms used by clinicians assigned to the central US Olympic Committee Sport Medicine Clinic and satellite locations during the operational 17-day period of the 2011 Pan American Games. We used principal components analysis and agglomerative clustering algorithms to identify and define grouped modalities. Lift statistics were calculated for within-cluster subgroups. Results: Principal component analyses identified 3 components, accounting for 72.3% of the variability in datasets. Plots of the principal components showed that individual contacts focused on 4 treatment clusters: massage, paired manipulation and mobilization, soft tissue therapy, and general medical. Conclusions: Unsupervised modeling techniques were useful for visualizing complex treatment data and provided insights for improved treatment modeling in athletes. Given its ability to detect clinically relevant treatment pairings in large datasets, unsupervised modeling should be considered a feasible option for future analyses of medical-contact data from international competitions.
AB - Context: Analysis of injury and illness data collected at large international competitions provides the US Olympic Committee and the national governing bodies for each sport with information to best prepare for future competitions. Research in which authors have evaluated medical contacts to provide the expected level of medical care and sports medicine services at international competitions is limited. Objective: To analyze the medical-contact data for athletes, staff, and coaches who participated in the 2011 Pan American Games in Guadalajara, Mexico, using unsupervised modeling techniques to identify underlying treatment patterns. Design: Descriptive epidemiology study. Setting: Pan American Games. Patients or Other Participants: A total of 618 US athletes (337 males, 281 females) participated in the 2011 Pan American Games. Main Outcome Measure(s): Medical data were recorded from the injury-evaluation and injury-treatment forms used by clinicians assigned to the central US Olympic Committee Sport Medicine Clinic and satellite locations during the operational 17-day period of the 2011 Pan American Games. We used principal components analysis and agglomerative clustering algorithms to identify and define grouped modalities. Lift statistics were calculated for within-cluster subgroups. Results: Principal component analyses identified 3 components, accounting for 72.3% of the variability in datasets. Plots of the principal components showed that individual contacts focused on 4 treatment clusters: massage, paired manipulation and mobilization, soft tissue therapy, and general medical. Conclusions: Unsupervised modeling techniques were useful for visualizing complex treatment data and provided insights for improved treatment modeling in athletes. Given its ability to detect clinically relevant treatment pairings in large datasets, unsupervised modeling should be considered a feasible option for future analyses of medical-contact data from international competitions.
UR - http://www.scopus.com/inward/record.url?scp=84961575166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961575166&partnerID=8YFLogxK
U2 - 10.4085/1062-6050-51.2.02
DO - 10.4085/1062-6050-51.2.02
M3 - Article
C2 - 26794628
AN - SCOPUS:84961575166
VL - 51
SP - 74
EP - 81
JO - Journal of Athletic Training
JF - Journal of Athletic Training
SN - 1062-6050
IS - 1
ER -