Application of Bayes’ to the prediction of referral decisions made by specialist optometrists in relation to chronic open angle glaucoma

J. C. Gurney, E. Ansari, D. Harle, N. O’kane, R. V. Sagar, M. C. M. Dunne

Research output: Contribution to journalArticle

Abstract

Purpose
To determine the accuracy of a Bayesian learning scheme (Bayes’) applied to the prediction of clinical decisions made by specialist optometrists in relation to the referral refinement of chronic open angle glaucoma.

Methods
This cross-sectional observational study involved collection of data from the worst affected or right eyes of a consecutive sample of cases (n = 1,006) referred into the West Kent Clinical Commissioning Group Community Ophthalmology Team (COT) by high street optometrists. Multilevel classification of each case was based on race, sex, age, family history of chronic open angle glaucoma, reason for referral, Goldmann Applanation Tonometry (intraocular pressure and interocular asymmetry), optic nerve head assessment (vertical size, cup disc ratio and interocular asymmetry), central corneal thickness and visual field analysis (Hodapp–Parrish–Anderson classification). Randomised stratified tenfold cross-validation was applied to determine the accuracy of Bayes’ by comparing its output to the clinical decisions of three COT specialist optometrists; namely, the decision to discharge, follow-up or refer each case.

Results
Outcomes of cross-validation, expressed as means and standard deviations, showed that the accuracy of Bayes’ was high (95%, 2.0%) but that it falsely discharged (3.4%, 1.6%) or referred (3.1%, 1.5%) some cases.

Conclusions
The results indicate that Bayes’ has the potential to augment the decisions of specialist optometrists.
LanguageEnglish
JournalEye
Early online date9 Feb 2018
DOIs
Publication statusE-pub ahead of print - 9 Feb 2018

Fingerprint

Open Angle Glaucoma
Referral and Consultation
Ophthalmology
Optic Disk
Manometry
Visual Fields
Intraocular Pressure
Observational Studies
Cross-Sectional Studies
Learning
Optometrists

Bibliographical note

Copyright © 2018, Springer Nature

Cite this

@article{bfad9e5d1c0f4199bcbe20f8710e17ca,
title = "Application of Bayes’ to the prediction of referral decisions made by specialist optometrists in relation to chronic open angle glaucoma",
abstract = "PurposeTo determine the accuracy of a Bayesian learning scheme (Bayes’) applied to the prediction of clinical decisions made by specialist optometrists in relation to the referral refinement of chronic open angle glaucoma.MethodsThis cross-sectional observational study involved collection of data from the worst affected or right eyes of a consecutive sample of cases (n = 1,006) referred into the West Kent Clinical Commissioning Group Community Ophthalmology Team (COT) by high street optometrists. Multilevel classification of each case was based on race, sex, age, family history of chronic open angle glaucoma, reason for referral, Goldmann Applanation Tonometry (intraocular pressure and interocular asymmetry), optic nerve head assessment (vertical size, cup disc ratio and interocular asymmetry), central corneal thickness and visual field analysis (Hodapp–Parrish–Anderson classification). Randomised stratified tenfold cross-validation was applied to determine the accuracy of Bayes’ by comparing its output to the clinical decisions of three COT specialist optometrists; namely, the decision to discharge, follow-up or refer each case.ResultsOutcomes of cross-validation, expressed as means and standard deviations, showed that the accuracy of Bayes’ was high (95{\%}, 2.0{\%}) but that it falsely discharged (3.4{\%}, 1.6{\%}) or referred (3.1{\%}, 1.5{\%}) some cases.ConclusionsThe results indicate that Bayes’ has the potential to augment the decisions of specialist optometrists.",
author = "Gurney, {J. C.} and E. Ansari and D. Harle and N. O’kane and Sagar, {R. V.} and Dunne, {M. C. M.}",
note = "Copyright {\circledC} 2018, Springer Nature",
year = "2018",
month = "2",
day = "9",
doi = "10.1038/s41433-018-0023-5",
language = "English",
journal = "Eye",
issn = "0950-222X",
publisher = "Nature Publishing Group",

}

Application of Bayes’ to the prediction of referral decisions made by specialist optometrists in relation to chronic open angle glaucoma. / Gurney, J. C.; Ansari, E.; Harle, D.; O’kane, N.; Sagar, R. V.; Dunne, M. C. M.

In: Eye, 09.02.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of Bayes’ to the prediction of referral decisions made by specialist optometrists in relation to chronic open angle glaucoma

AU - Gurney, J. C.

AU - Ansari, E.

AU - Harle, D.

AU - O’kane, N.

AU - Sagar, R. V.

AU - Dunne, M. C. M.

N1 - Copyright © 2018, Springer Nature

PY - 2018/2/9

Y1 - 2018/2/9

N2 - PurposeTo determine the accuracy of a Bayesian learning scheme (Bayes’) applied to the prediction of clinical decisions made by specialist optometrists in relation to the referral refinement of chronic open angle glaucoma.MethodsThis cross-sectional observational study involved collection of data from the worst affected or right eyes of a consecutive sample of cases (n = 1,006) referred into the West Kent Clinical Commissioning Group Community Ophthalmology Team (COT) by high street optometrists. Multilevel classification of each case was based on race, sex, age, family history of chronic open angle glaucoma, reason for referral, Goldmann Applanation Tonometry (intraocular pressure and interocular asymmetry), optic nerve head assessment (vertical size, cup disc ratio and interocular asymmetry), central corneal thickness and visual field analysis (Hodapp–Parrish–Anderson classification). Randomised stratified tenfold cross-validation was applied to determine the accuracy of Bayes’ by comparing its output to the clinical decisions of three COT specialist optometrists; namely, the decision to discharge, follow-up or refer each case.ResultsOutcomes of cross-validation, expressed as means and standard deviations, showed that the accuracy of Bayes’ was high (95%, 2.0%) but that it falsely discharged (3.4%, 1.6%) or referred (3.1%, 1.5%) some cases.ConclusionsThe results indicate that Bayes’ has the potential to augment the decisions of specialist optometrists.

AB - PurposeTo determine the accuracy of a Bayesian learning scheme (Bayes’) applied to the prediction of clinical decisions made by specialist optometrists in relation to the referral refinement of chronic open angle glaucoma.MethodsThis cross-sectional observational study involved collection of data from the worst affected or right eyes of a consecutive sample of cases (n = 1,006) referred into the West Kent Clinical Commissioning Group Community Ophthalmology Team (COT) by high street optometrists. Multilevel classification of each case was based on race, sex, age, family history of chronic open angle glaucoma, reason for referral, Goldmann Applanation Tonometry (intraocular pressure and interocular asymmetry), optic nerve head assessment (vertical size, cup disc ratio and interocular asymmetry), central corneal thickness and visual field analysis (Hodapp–Parrish–Anderson classification). Randomised stratified tenfold cross-validation was applied to determine the accuracy of Bayes’ by comparing its output to the clinical decisions of three COT specialist optometrists; namely, the decision to discharge, follow-up or refer each case.ResultsOutcomes of cross-validation, expressed as means and standard deviations, showed that the accuracy of Bayes’ was high (95%, 2.0%) but that it falsely discharged (3.4%, 1.6%) or referred (3.1%, 1.5%) some cases.ConclusionsThe results indicate that Bayes’ has the potential to augment the decisions of specialist optometrists.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85041533115&origin=SingleRecordEmailAlert&dgcid=raven_sc_search_en_us_email&txGid=6ced6419cdc101f3818477779e4a7ec2

UR - http://www.nature.com/articles/s41433-018-0023-5

U2 - 10.1038/s41433-018-0023-5

DO - 10.1038/s41433-018-0023-5

M3 - Article

JO - Eye

T2 - Eye

JF - Eye

SN - 0950-222X

ER -