Validation of a Machine Learning Brain Electrical Activity-Based Index to Aid in Diagnosing Concussion Among Athletes.

Importance: An objective, reliable indicator of the presence and severity of concussive brain injury and of the readiness for the return to activity has the potential to reduce concussion-related disability. Objective: To validate the classification accuracy of a previously derived, machine learning, multimodal, brain electrical activity-based Concussion Index in an independent cohort of athletes with concussion. Design, Setting, and Participants: This prospective diagnostic cohort study was conducted at 10 clinical sites (ie, US universities and high schools) between February 4, 2017, and March 20, 2019. A cohort comprising a consecutive sample of 207 athletes aged 13 to 25 years with concussion and 373 matched athlete controls without concussion were assessed with electroencephalography, cognitive testing, and symptom inventories within 72 hours of injury, at return to play, and 45 days after return to play. Variables from the multimodal assessment were used to generate a Concussion Index at each time point. Athletes with concussion had experienced a witnessed head impact, were removed from play for 5 days or more, and had an initial Glasgow Coma Scale score of 13 to 15. Participants were excluded for known neurologic disease or history within the last year of traumatic brain injury. Athlete controls were matched to athletes with concussion for age, sex, and type of sport played. Main Outcomes and Measures: Classification accuracy of the Concussion Index at time of injury using a prespecified cutoff of 70 or less (total range, 0-100, where ≤70 indicates it is likely the individual has a concussion and >70 indicates it is likely the individual does not have a concussion). Results: Of 580 eligible participants with analyzable data, 207 had concussion (124 male participants [59.9%]; mean [SD] age, 19.4 [2.5] years), and 373 were athlete controls (187 male participants [50.1%]; mean [SD] age, 19.6 [2.2] years). The Concussion Index had a sensitivity of 86.0% (95% CI, 80.5%-90.4%), specificity of 70.8% (95% CI, 65.9%-75.4%), negative predictive value of 90.1% (95% CI, 86.1%-93.3%), positive predictive value of 62.0% (95% CI, 56.1%-67.7%), and area under receiver operator characteristic curve of 0.89. At day 0, the mean (SD) Concussion Index among athletes with concussion was significantly lower than among athletes without concussion (75.0 [14.0] vs 32.7 [27.2]; P < .001). Among athletes with concussion, there was a significant increase in the Concussion Index between day 0 and return to play, with a mean (SD) paired difference between these time points of -41.2 (27.0) (P < .001). Conclusions and Relevance: These results suggest that the multimodal brain activity-based Concussion Index has high classification accuracy for identification of the likelihood of concussion at time of injury and may be associated with the return to control values at the time of recovery. The Concussion Index has the potential to aid in the clinical diagnosis of concussion and in the assessment of athletes' readiness to return to play.

Outcome of motorcycle riders at one year post-injury.

OBJECTIVE: There is little information about the long-term effects of injury on victims of motorcycle crashes. Following the repeal of the mandatory helmet law in Florida, we studied the impact of crashes on riders and their outcomes one year post-injury. SUBJECTS: All patients involved in a motorcycle crash over a six-month time period were assessed at one year post-injury. Demographic information, health status, motorcycle and helmet usage, and employability were surveyed. RESULTS: There were 94 patients evaluated at our center for the first six-month period following the repeal of the helmet law, where 50 (56%) were wearing a helmet at the time of injury. Of the 94, we were able to contact 45 (48%) at one-year follow up. Fourteen (31%) of those contacted were not wearing a helmet at the time of their crash. At one year post-injury, 23 (51%) reported physical deficits, while 39 (86%) were working. Only 12 (27%) were riding a motorcycle again, and 11 (92%) were wearing a helmet. CONCLUSIONS: Motorcycle riders at one year post-injury continue to experience physical deficits related to their accidents. There is a small percentage of riders that resume riding a motorcycle after injury. Being involved in a motorcycle accident has deterred the injured rider from riding a motorcycle again at one year post-injury.

Pediatric pedestrian trauma study: a pilot project.

OBJECTIVE: To evaluate the implementation of the WalkSafe Program, a school based educational injury prevention program for children grades Kindergarten through 5. METHODS: A randomized comparative design was used for this study. The study was conducted in two high-risk urban school districts, which were chosen based on the geographic areas with the highest pedestrian injury and fatality rates. Four elementary schools (two in each district) were identified as potential study sites. Two intervention schools, one in each school district, were randomly chosen to receive the WalkSafe program; the other two schools served as controls, and received no intervention. The data was collected within the classroom setting for both the intervention and control schools. All elementary school children were administered the same pedestrian safety questionnaire as a pre-test, post-test and at three months following the intervention. RESULTS: A total of 2300 children participated in the WalkSafe program. The intervention (I) schools showed significant improvement in post-test scores then the control (C) schools (p = 0.012), and the (I) schools were able to maintain their test scores as reflected in a three-month follow-up evaluation (p = 0.47). Grades 3-5 of the (I) schools showed significant improvement in their test scores over grades K-2 (p < 0.0001). CONCLUSION: The WalkSafe program was shown to improve the pedestrian safety knowledge of elementary school children. Future research will include implementing the WalkSafe program at each elementary school within a single high-risk district.

Developing a trauma critical care and rehab hospital in Haiti: a year after the earthquake.

OBJECTIVE: Prior to the devastating earthquake in Haiti, January 12, 2010, a group of Haitian physicians, leaders and members of Project Medishare for Haiti, a Non-governmental Organization, had developed plans for a Trauma Critical Care Network for Haiti. DESIGN: One year after the earthquake stands a 50-bed trauma critical care and rehab hospital that employs more than 165 Haitian doctors, nurses and allied healthcare professionals, and administrative and support staff in Port-Au-Prince. Hospital Bernard Mevs Project Medishare (HBMPM) has been operating with the following two primary goals: 1) to provide critical-care- and trauma-related medical and rehabilitation services and 2) to provide clinical education and training to Haitian healthcare professionals.(1) RESULTS: These goals have been successfully accomplished, with more than 43,000 outpatients seen, 6,500 emergency room visits, and about 2,300 surgical procedures performed. Daily patient care has been managed by Haitian medical staff as well as more than 2,400 international volunteers including physicians, nurses, and allied healthcare professionals. With the continued assistance of weekly volunteers, many programs and services have been developed; however, many challenges remain. CONCLUSIONS: This article highlights the development and progress of HBMPM over the last year with emphasis on developing inpatient and outpatient services, which include surgical, clinical laboratory, wound care, radiology, rehabilitation, and prosthesis/orthotics programs. Some of the challenges faced and how they were managed will be discussed as well as future plans to conduct more training and education to increase the building of medical capacity for Haiti.

Factors associated with inpatient mortality in a field hospital following the Haiti earthquake, January-May 2010.

OBJECTIVE: To describe factors associated with inpatient mortality in a field hospital established following the 2010 Haiti earthquake. DESIGN: Data were abstracted from medical records of patients admitted to the University of Miami Global Institute/Project Medishare hospital. Decedents were compared to survivors in terms of age, sex, length of stay, admission ward, diagnosis, and where relevant, injury mechanism and surgical procedure. Three multivariate logistic regression models were constructed to determine predictors of death among all patients, injured patients, and noninjured patients. RESULTS: During the study period, 1,339 patients were admitted to the hospital with 100 inpatient deaths (7.5 percent). The highest proportion of deaths occurred among patients aged < or = 15 years. Among all patients, adult intensive care unit (ICU) admission (adjusted odds ratio [AOR] = 7.6 and 95% confidence interval [CI] = 3.4-16.8), neonatal ICU/pediatric ICU (NICU/PICU) admission (AOR = 7.8 and 95% CI = 2.7-22.9), and cardiac/respiratory diagnoses (AOR = 8.5 and 95% CI = 4.9-14.8) were significantly associated with death. Among injured patients, adult ICU admission (AOR = 7.4 and 95% CI = 1.7-33.3) and penetrating injury (AOR = 3.3 and 95% CI = 1.004-11.1) were significantly associated with death. Among noninjured patients, adult ICU admission (AOR = 6.6 and 95% CI = 2.7-16.4), NICU/PICU admission (AOR = 8.2 and 95% CI = 2.1-31.8), and cardiac/ respiratory diagnoses (AOR = 6.5 and 95% CI = 3.6-12.0) were significantly associated with death. CONCLUSIONS: Following earthquakes in resource-limited settings, survivors may require care in field hospitals for injuries or exacerbation of chronic medical conditions. Planning for sustained post-earthquake response should address these needs and include pediatric-specific preparation and long-term critical care requirements.

Snoezelen: a controlled multi-sensory stimulation therapy for children recovering from severe brain injury.

OBJECTIVE: To investigate the effects of Snoezelen therapy on physiological, cognitive and behavioural changes in children recovering from severe traumatic brain injury (TBI). METHODS: An observational study was conducted to assess the physiological, cognitive and behavioural changes of children recovering from severe TBI while receiving Snoezelen therapy. Fifteen subjects completed the pre- and post-Snoezelen treatment measurements computed over 10 consecutive sessions. Physiological, cognitive and behavioural measures were administered. Data was collected prospectively on each session in the Snoezelen room and were analysed by calculating the difference between pre- and post-treatment measurements for each Snoezelen session. RESULTS: Results revealed significant changes on physiological measures. Heart rates decreased for each subject in each treatment session and were found to be significant (p = 0.032). Muscle tone was decreased in all the affected extremities (right upper extremity p = 0.009, left upper extremity p = 0.020, right lower extremity p = 0.036 and left lower extremity p = 0.018). Agitation levels decreased over time and the overall cognitive outcome measures showed significant improvement when comparing the beginning of treatment with the end. CONCLUSION: This study revealed a beneficial use of Snoezelen therapy with children recovering from severe brain injury. However, there continues to be a critical need for evidenced-based research for this patient population and others in this multi-sensory environment.

The impact of a repealed motorcycle helmet law in Miami-Dade County.

OBJECTIVE: To study the impact of helmet nonuse in motorcycle crashes after the repeal of a mandatory helmet law in the state of Florida. METHODS: We prospectively studied all patients evaluated at the University of Miami/Jackson Memorial Medical Center from July 1, 2000, through December 31, 2000, involved in motorcycle crashes, and compared them with those seen during the same time period the year before the helmet law change. RESULTS: In 1999, before the repeal of the helmet law, there were 52 cases evaluated at our center compared with 94 after the law change. Helmet usage decreased from 1999 (83%) to 2000 (56%). The number of brain injuries (Abbreviated Injury Scale score > or = 2) during this same time period increased from 18 to 35, and the number of fatalities from 2 to 8. CONCLUSION: The repeal of a motorcycle helmet law significantly increased the number and severity of brain injuries admitted to our trauma center.