Sensitivity and specificity of an eye movement tracking-based biomarker for concussion
Uzma Samadani,
Meng Li,
Meng Qian,
Eugene Laska,
Robert Ritlop,
Radek Kolecki,
Marleen Reyes,
Lindsey Altomare,
Je Yeong Sone,
Aylin Adem,
Paul Huang,
Douglas Kondziolka,
Stephen Wall,
Spiros Frangos,
Charles Marmar
Affiliations
Uzma Samadani
1Department of Neurosurgery, New York Harbor Health Care System, NY, USA
Meng Li
3Steven & Alexandra Cohen Veterans Center for Post-Traumatic Stress & Traumatic Brain Injury, New York University Langone Medical Center, NY, USA
Meng Qian
3Steven & Alexandra Cohen Veterans Center for Post-Traumatic Stress & Traumatic Brain Injury, New York University Langone Medical Center, NY, USA
Eugene Laska
3Steven & Alexandra Cohen Veterans Center for Post-Traumatic Stress & Traumatic Brain Injury, New York University Langone Medical Center, NY, USA
Robert Ritlop
5Oculogica Inc., NY, USA
Radek Kolecki
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Marleen Reyes
1Department of Neurosurgery, New York Harbor Health Care System, NY, USA
Lindsey Altomare
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Je Yeong Sone
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Aylin Adem
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Paul Huang
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Douglas Kondziolka
2Department of Neurosurgery, New York University, School of Medicine, NY, USA
Stephen Wall
6Department of Emergency Medicine, New York University School of Medicine, NY, USA
Spiros Frangos
7Department of Trauma Surgery, New York University School of Medicine, NY, USA
Charles Marmar
3Steven & Alexandra Cohen Veterans Center for Post-Traumatic Stress & Traumatic Brain Injury, New York University Langone Medical Center, NY, USA
Object: The purpose of the current study is to determine the sensitivity and specificity of an eye tracking method as a classifier for identifying concussion. Methods: Brain injured and control subjects prospectively underwent both eye tracking and Sport Concussion Assessment Tool 3. The results of eye tracking biomarker based classifier models were then validated against a dataset of individuals not used in building a model. The area under the curve (AUC) of receiver operating characteristics was examined. Results: An optimal classifier based on best subset had an AUC of 0.878, and a cross-validated AUC of 0.852 in CT- subjects and an AUC of 0.831 in a validation dataset. The optimal misclassification rate in an external dataset (n = 254) was 13%. Conclusion: If one defines concussion based on history, examination, radiographic and Sport Concussion Assessment Tool 3 criteria, it is possible to generate an eye tracking based biomarker that enables detection of concussion with reasonably high sensitivity and specificity.
