Smartphone-Based Pupillometry Using Machine Learning for the Diagnosis of Sports-Related Concussion
The DOI matches its Crossref record.
Abstract
Background: Quantitative pupillometry has been proposed as an objective means to diagnose acute sports-related concussion (SRC). Objective: To assess the diagnostic accuracy of a smartphone-based quantitative pupillometer in the acute diagnosis of SRC. Methods: Division I college football players had baseline pupillometry including pupillary light reflex (PLR) parameters of maximum resting diameter, minimum diameter after light stimulus, percent change in pupil diameter, latency of pupil constriction onset, mean constriction velocity, maximum constriction velocity, and mean dilation velocity using a smartphone-based app. When an SRC occurred, athletes had the smartphone pupillometry repeated as part of their concussion testing. All combinations of the seven PLR parameters were tested in machine learning binary classification models to determine the optimal combination for differentiating between non-concussed and concussed athletes. Results: 93 football athletes underwent baseline pupillometry testing. Among these athletes, 11 suffered future SRC and had pupillometry recordings repeated at the time of diagnosis. In the machine learning pupillometry analysis that used the synthetic minority oversampling technique to account for the significant class imbalance in our dataset, the best-performing model was a random forest algorithm with the combination of latency, maximum diameter, minimum diameter, mean constriction velocity, and maximum constriction velocity PLR parameters as feature inputs. This model produced 91% overall accuracy, 98% sensitivity, 84.2% specificity, area under the curve (AUC) of 0.91, and an F1 score of 91.6% in differentiating between baseline and SRC recordings. In the machine learning analysis prior to oversampling of our imbalanced dataset, the best-performing model was k-nearest neighbors using latency, maximum diameter, maximum constriction velocity, and mean dilation velocity to produce 82% accuracy, 40% sensitivity, 87% specificity, AUC of 0.64, and F1 score of 24%. Conclusions: Smartphone pupillometry in combination with machine learning may provide fast and objective SRC diagnosis in football athletes.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Moreover, one study revealed that the utilization of pupillary response patterns in differentiating acute neurological conditions may be beneficial in emergency department triage (26).”
From Pupil and Pupillary Light Reflex (2025) · cites this paper as [26]
In the citing paper
“The clinical utility of mobile pupillometry has been reported in the early differentiation of sports-related concussion and acute neurological conditions (26).”
From Pupil and Pupillary Light Reflex (2025) · cites this paper as [26]
In the citing paper
“These systems allow pupil assessment to be performed in ambulances, field settings, and healthcare facilities with limited resources (26).”
From Pupil and Pupillary Light Reflex (2025) · cites this paper as [26]
In the citing paper
“Studies have demonstrated the applicability of these technologies in distinguishing sportrelated concussion (SRC) and acute ischemic-hemorrhagic stroke (10,26).”
From Pupil and Pupillary Light Reflex (2025) · cites this paper as [26]
In the citing paper
“Today, smartphone-based pupillometry systems and artificial intelligence-assisted analytical techniques have shown promising results in the rapid and accurate differentiation of acute neurological conditions.”
From Pupil and Pupillary Light Reflex (2025) · cites this paper as [26]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 42
- Bryan, 2016, Sports- and Recreation-Related Concussions in US Youth, Pediatrics, 138, e20154635, 10.1542/peds.2015-4635 · DOI · Paper page
- Stemper, 2022, Association between Preseason/Regular Season Head Impact Exposure and Concussion Incidence in NCAA Football, Med. Sci. Sports Exerc., 54, 912, 10.1249/MSS.0000000000002874 · DOI
- Harmon, 2019, American Medical Society for Sports Medicine position statement on concussion in sport, Br. J. Sports Med., 53, 213, 10.1136/bjsports-2018-100338 · DOI · Paper page
- Harmon, 2024, Diagnosis of Sports-Related Concussion Using Symptom Report or Standardized Assessment of Concussion, JAMA Netw. Open, 7, e2416223, 10.1001/jamanetworkopen.2024.16223 · DOI
- Kroshus, 2015, Concussion under-reporting and pressure from coaches, teammates, fans, and parents, Soc. Sci. Med., 134, 66, 10.1016/j.socscimed.2015.04.011 · DOI · Paper page
- Echemendia, 2023, Acute evaluation of sport-related concussion and implications for the Sport Concussion Assessment Tool (SCAT6) for adults, adolescents and children: A systematic review, Br. J. Sports Med., 57, 722, 10.1136/bjsports-2022-106661 · DOI
- Bruce, 2020, Use of the Sport Concussion Assessment Tool 5 (SCAT5) in professional hockey, part 2: Which components differentiate concussed and non-concussed players?, Br. J. Sports Med., 55, 557, 10.1136/bjsports-2020-102072 · DOI
- Harmon, 2022, Diagnostic accuracy and reliability of sideline concussion evaluation: A prospective, case-controlled study in college athletes comparing newer tools Ma and established tests, Br. J. Sports Med., 56, 144, 10.1136/bjsports-2020-103840 · DOI
- King, 2024, Comparative Performance of Three Eye-Tracking Devices in Detection of Mild Traumatic Brain Injury in Acute Versus Chronic Subject Populations, Mil. Med., 189, 628, 10.1093/milmed/usae205 · doi:10.1093/milmed/usae205
- Meier, 2024, Association of Blood Biomarkers of Inflammation with Acute Concussion in Collegiate Athletes and Military Service Academy Cadets, Neurology, 102, e207991, 10.1212/WNL.0000000000207991 · DOI
- Carrick, F.R., Azzolino, S.F., Hunfalvay, M., Pagnacco, G., Oggero, E., D’Arcy, R.C.N., Abdulrahman, M., and Sugaya, K. (2021). The Pupillary Light Reflex as a Biomarker of Concussion. Life, 11. · DOI
- Urosevich, 2013, Pupillary Light Reflex as an Objective Biomarker for Early Identification of Blast-Induced mTBI, J. Spine, S4, 1
- Thiagarajan, 2015, Pupillary responses to light in chronic non-blast-induced mTBI, Brain Inj, 29, 1420, 10.3109/02699052.2015.1045029 · DOI
- Truong, 2016, Comparison of pupillary dynamics to light in the mild traumatic brain injury (mTBI) and normal populations, Brain Inj, 30, 1378, 10.1080/02699052.2016.1195922 · DOI
- Beltran, 2018, Validation of Visual Objective Biomarkers for Acute Concussion, Mil. Med., 183, 9, 10.1093/milmed/usx166 · DOI
- Hsu, 2021, Concussion Alters Dynamic Pupillary Light Responses in Children, J. Child. Neurol., 36, 195, 10.1177/0883073820964040 · DOI
- Master, 2020, Utility of Pupillary Light Reflex Metrics as a Physiologic Biomarker for Adolescent Sport-Related Concussion, JAMA Ophthalmol., 138, 1135, 10.1001/jamaophthalmol.2020.3466 · DOI
- Bower, 2021, Quantitative Pupillometry in the Intensive Care Unit, J. Intensive Care Med., 36, 383, 10.1177/0885066619881124 · doi:10.1177/0885066619881124
- Signoretti, 2011, The pathophysiology of concussion, PM R, 3, S359, 10.1016/j.pmrj.2011.07.018 · DOI · Paper page
- McAnany, 2018, iPhone-based Pupillometry: A Novel Approach for Assessing the Pupillary Light Reflex, Optom. Vis. Sci., 95, 953, 10.1097/OPX.0000000000001289 · DOI
- Piaggio, 2021, Pupillometry via smartphone for low-resource settings, Biocybern. Biomed. Eng., 41, 891, 10.1016/j.bbe.2021.05.012 · DOI
- McGrath, L.B., Eaton, J., Abecassis, I.J., Maxin, A., Kelly, C., Chesnut, R.M., and Levitt, M.R. (2022). Mobile smartphone-based digital pupillometry curves in the diagnosis of traumatic brain injury. Front. Neurosci., 16. · DOI
- Maxin, 2024, Smartphone Pupillometry and Machine Learning for Detection of Acute Mild Traumatic Brain Injury: Cohort Study, JMIR Neurotech, 3, e58398, 10.2196/58398 · DOI
- Memmini, 2023, Premorbid Risk Factors and Acute Injury Characteristics of Sport-Related Concussion Across the National Collegiate Athletic Association: Findings from the Concussion Assessment, Research, and Education (CARE) Consortium, Sports Med., 53, 1457, 10.1007/s40279-023-01830-3 · DOI
- Patricios, 2023, Consensus statement on concussion in sport: The 6th International Conference on Concussion in Sport-Amsterdam, October 2022, Br. J. Sports Med., 57, 695, 10.1136/bjsports-2023-106898 · DOI · Paper page
- Maxin, 2023, Validation of a Smartphone Pupillometry Application in Diagnosing Severe Traumatic Brain Injury, J. Neurotrauma, 40, 2118, 10.1089/neu.2022.0516 · DOI
- Maxin, 2024, Smartphone pupillometry for detection of cerebral vasospasm after aneurysmal subarachnoid hemorrhage, J. Stroke Cerebrovasc. Dis., 33, 107922, 10.1016/j.jstrokecerebrovasdis.2024.107922 · doi:10.1016/j.jstrokecerebrovasdis.2024.107922
- Maxin, 2023, A smartphone pupillometry tool for detection of acute large vessel occlusion, J. Stroke Cerebrovasc. Dis., 32, 107430, 10.1016/j.jstrokecerebrovasdis.2023.107430 · doi:10.1016/j.jstrokecerebrovasdis.2023.107430
- Mariakakis, 2017, PupilScreen: Using smartphones to assess traumatic brain injury, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 1, 81, 10.1145/3131896 · DOI
- Rashidi, 2019, Artificial Intelligence and Machine Learning in Pathology: The Present Landscape of Supervised Methods, Acad. Pathol., 6, 2374289519873088, 10.1177/2374289519873088 · DOI · Paper page
- Chawla, 2002, SMOTE: Synthetic minority over-sampling technique, J. Artif. Intell. Res., 16, 321, 10.1613/jair.953 · DOI · Paper page
- Garcia, 2018, Quantifying the Value of Multidimensional Assessment Models for Acute Concussion: An Analysis of Data from the NCAA-DoD Care Consortium, Sports Med., 48, 1739, 10.1007/s40279-018-0880-x · DOI
- Resch, 2016, The sensitivity and specificity of clinical measures of sport concussion: Three tests are better than one, BMJ Open Sport Exerc. Med., 2, e000012, 10.1136/bmjsem-2015-000012 · DOI
- Patricios, 2023, Sport Concussion Office Assessment Tool—6, Br. J. Sports Med., 57, 651, 10.1136/bjsports-2023-106860 · DOI
- Naidu, 2018, Sideline Concussion Assessment: The King-Devick Test in Canadian Professional Football, J. Neurotrauma, 35, 2283, 10.1089/neu.2017.5490 · DOI
- Fuller, 2019, King-Devick concussion test performs poorly as a screening tool in elite rugby union players: A prospective cohort study of two screening tests versus a clinical reference standard, Br. J. Sports Med., 53, 1526, 10.1136/bjsports-2017-098560 · DOI
- Heyming, 2024, Evaluation of Quantitative Pupillometry in Acute Postinjury Pediatric Concussion, Pediatr. Neurol., 153, 103, 10.1016/j.pediatrneurol.2024.01.016 · DOI
- Oeur, A., Mull, M., Riccobono, G., Arbogast, K.B., Ciuffreda, K.J., Joshi, N., Fedonni, D., Master, C.L., and Margulies, S.S. (2023). Pupillary Light Response Deficits in 4-Week-Old Piglets and Adolescent Children after Low-Velocity Head Rotations and Sports-Related Concussions. Biomedicines, 11. · DOI
- Lee, 2018, The use and uptake of pupillometers in the Intensive Care Unit, Aust. Crit. Care, 31, 199, 10.1016/j.aucc.2017.06.003 · doi:10.1016/j.aucc.2017.06.003
- Gramkow, 2024, Diagnostic performance of light reflex pupillometry in Alzheimer’s disease, Alzheimers. Dement., 16, e12628
- Kaifie, 2021, The pupillary light reflex (PLR) as a marker for the ability to work or drive—A feasibility study, J. Occup. Med. Toxicol., 16, 39, 10.1186/s12995-021-00330-2 · DOI
- Huyghe, 2024, Pupillometry as a new window to player fatigue? A glimpse inside the eyes of a Euro Cup Women’s Basketball team, Biol. Sport, 41, 3, 10.5114/biolsport.2024.125590 · DOI
Cited by
Pupil and Pupillary Light Reflex
Özdağ, D., & Oztas, B. (2025) · Sakarya Üniversitesi Holistik Sağlık Dergisi · doi:10.54803/sauhsd.1767753 · Cited by 1
Metadata
- Authors
- Maxin, A. J., Whelan, B. M., Levitt, M. R., McGrath, L. B., & Harmon, K. G.
- Venue
- Diagnostics
- Publisher
- MDPI AG
- Published
- 2024-12-03
- Volume
- 14
- Issue
- 23
- Pages
- 2723
- ISSN
- 2075-4418
- Cited by
- 6
- References
- 0
- Language
- en
- Funders
- University of Washington alumni Jack and Luellen Cherneski
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.