Download fulltext
1.
Yang C, Wang J, Verniani L, Ghalehei M, Chen L, Lin K. Clinical Validation of a Handheld Deep Learning Tool for Identification of Glaucoma Medications. JOVR [Internet]. 2024Jun.21 [cited 2024Jun.30];19(2):172–182. Available from: https://knepublishing.com/index.php/JOVR/article/view/13983

https://doi.org/10.18502/jovr.v19i2.13983

statistics

  • 18 Abstract Views
  • 15 PDF Views

authors

  • Christopher D. Yang

    Christopher D. Yang

    University of California, Irvine School of Medicine, Irvine, California
    https://orcid.org/0000-0002-2090-1880
  • Jasmine Wang

    Jasmine Wang

    University of California, Irvine School of Medicine, Irvine, California
    https://orcid.org/0009-0002-1171-6445
  • Ludovico Verniani

    Ludovico Verniani

    Department of Computer Science, UC Irvine, California
  • Melika Ghalehei

    Melika Ghalehei

    Gavin Herbert Eye Institute, Department of Ophthalmology, UC Irvine, California
    https://orcid.org/0009-0002-9036-626X
  • Lauren E. Chen

    Lauren E. Chen

    Gavin Herbert Eye Institute, Department of Ophthalmology, UC Irvine, California
    https://orcid.org/0000-0001-5835-5646
  • Ken Y. Lin

    Ken Y. Lin

    Gavin Herbert Eye Institute, Department of Ophthalmology, UC Irvine, California, 92697
    https://orcid.org/0000-0002-6467-7219

Published Date

  • Jun 21, 2024
This journal is publishing all the articles under Creative Commons Attribution License CC BY 4.0.

Clinical Validation of a Handheld Deep Learning Tool for Identification of Glaucoma Medications

Journal of Ophthalmic and Vision Research (JOVR) / Apr–Jun 2024, Volume 19, Issue 2 / Pages 172–182

Abstract

Purpose: To validate a convolutional neural network (CNN)-based smartphone application for the identification of glaucoma eye drop medications in patients with normal and impaired vision.


Methods: Sixty-eight patients with visual acuity (VA) of 20/70 or worse in at least one eye who presented to an academic glaucoma clinic from January 2021 through August 2022 were included. Non-English-speaking patients were excluded. Enrolled subjects participated in an activity in which they identified a predetermined and preordered set of six topical glaucoma medications, first without the CNN and then with the CNN for a total of six sequential measurements per subject. Responses to a standardized survey were collected during and after the activity. Primary quantitative outcomes were medication identification accuracy and time. Primary qualitative outcomes were subjective ratings of ease of smartphone application use.


Results: Topical glaucoma medication identification accuracy (OR = 12.005, P < 0.001) and time (OR = 0.007, P < 0.001) both independently improved with CNN use. CNN use significantly improved medication accuracy in patients with glaucoma (OR = 4.771, P = 0.036) or VA ≤ 20/70 in at least one eye (OR = 4.463, P = 0.013) and medication identification time in patients with glaucoma (OR = 0.065, P = 0.017). CNN use had a significant positive association with subjectreported ease of medication identification (X2(1) = 66.117, P < 0.001).


Conclusion: Our CNN-based smartphone application is efficacious at improving glaucoma eye drop identification accuracy and time. This tool can be used in the outpatient setting to avert preventable vision loss by improving medication adherence in patients with glaucoma.

Keywords:

Convolutional Neural Network, Deep Learning, Glaucoma, Medication Tools

References
1. Heijl A, Leske MC, Bengtsson B, Hyman L, Bengtsson B, Hussein M; Early Manifest Glaucoma Trial Group. Reduction of intraocular pressure and glaucoma progression: Results from the Early Manifest Glaucoma Trial. Arch Ophthalmol 2002;120:1268–1279.

2. Li T, Lindsley K, Rouse B, Hong H, Shi Q, Friedman DS, et al. Comparative effectiveness of first-line medications for primary open-angle glaucoma: A systematic review and network meta-analysis. Ophthalmology 2016;123:129– 140.

3. Hou CH, Pu C. Medication adherence in patients with glaucoma and disability. JAMA Ophthalmol 2021;139:1292–1298.

4. Sleath B, Ballinger R, Covert D, Robin AL, Byrd JE, Tudor G. Self-reported prevalence and factors associated with nonadherence with glaucoma medications in veteran outpatients. Am J Geriatr Pharmacother 2009;7:67–73.

5. Paul J, Hammer JD, Akhtari R, Skillings B, Moore DB. Effect of glaucoma on identification of bottle cap color in ophthalmic medications. Int J Ophthalmol 2019;12:169– 171.

6. Gatwood J, Brooks C, Meacham R, Abou-Rahma J, Cernasev A, Brown E, et al. Facilitators and Barriers to Glaucoma Medication Adherence. J Glaucoma 2022;31:31–36.

7. Chen HY, Lin CL. Comparison of medical comorbidity between patients with primary angle-closure glaucoma and a control cohort: A population-based study from Taiwan. BMJ Open 2019;9:e024209.

8. Rossi GC, Pasinetti GM, Scudeller L, Radaelli R, Bianchi PE. Do adherence rates and glaucomatous visual field progression correlate? Eur J Ophthalmol 2011;21:410– 414.

9. Sleath B, Blalock S, Covert D, Stone JL, Skinner AC, Muir K, et al. The relationship between glaucoma medication adherence, eye drop technique, and visual field defect severity. Ophthalmology 2011;118:2398–2402.

10. Electronic article on the internet: California Department of Motor Vehicles, Vision Standards. California DMV 2020. https://www.dmv.ca.gov/portal/driver-educationand- safety/educational-materials/fast-facts/visionstandards- ffdl-14/

11. Grewal PS, Oloumi F, Rubin U, Tennant MT. Deep learning in ophthalmology: A review. Can J Ophthalmol 2018;53:309–313.

12. Larios Delgado N, Usuyama N, Hall AK, Hazen RJ, Ma M, Sahu S, et al. Fast and accurate medication identification. NPJ Digit Med 2019;2:10.

13. Tran TT, Richardson AJ, Chen VM, Lin KY. Fast and accurate ophthalmic medication bottle identification using deep learning on a smartphone device. Ophthalmol Glaucoma 2022;5:188–194.

14. Olthoff CM, Schouten JS, van de Borne BW, Webers CA. Noncompliance with ocular hypotensive treatment in patients with glaucoma or ocular hypertension an evidence-based review. Ophthalmology 2005;112:953– 961.

15. Tsai JC. A comprehensive perspective on patient adherence to topical glaucoma therapy. Ophthalmology 2009;116:S30–S36.

16. Newman-Casey PA, Robin AL, Blachley T, Farris K, Heisler M, Resnicow K, et al. The most common barriers to glaucoma medication adherence: A cross-sectional survey. Ophthalmology 2015;122:1308–1316.

17. Spencer SK, Shulruf B, McPherson ZE, Zhang H, Lee MB, Francis IC, et al. Factors affecting adherence to topical glaucoma therapy: A quantitative and qualitative pilot study analysis in Sydney, Australia. Ophthalmol Glaucoma 2019;2:86–93.

18. Lai Y, Wu Y, Chai C, Yen CC, Ho Y, Eng TC, et al. The effect of patient education and telemedicine reminders on adherence to eye drops for glaucoma. Ophthalmol Glaucoma 2020;3:369–376.

19. Davis SA, Carpenter DM, Blalock SJ, Budenz DL, Lee C, Muir KW, et al. A randomized controlled trial of an online educational video intervention to improve glaucoma eye drop technique. Patient Educ Couns 2019;102:937–943.

20. Buehne KL, Rosdahl JA, Muir KW. Aiding adherence to glaucoma medications: A systematic review. Semin Ophthalmol 2022;37:313–323.

21. Merabet LB, Pascual-Leone A. Neural reorganization following sensory loss: The opportunity of change. Nat Rev Neurosci 2010;11:44–52.

22. Lee YY, Lin JL. Do patient autonomy preferences matter? Linking patient-centered care to patientphysician relationships and health outcomes. Soc Sci Med 2010;71:1811–1818.