Development and validation of an improved neurological hemifield test to identify chiasmal and postchiasmal lesions by automated perimetry

Allison N. McCoy, Harry A Quigley, Jiangxia Wang, Neil R Miller, Prem S. Subramanian, Pradeep Ramulu, Michael Boland

Research output: Contribution to journalArticle

Abstract

Purpose. To improve the neurological hemifield test (NHT) using visual field data from both eyes to detect and classify visual field loss caused by chiasmal or postchiasmal lesions. Methods. Visual field and clinical data for 633 patients were divided into a training set (474 cases) and a validation set (159 cases). Each set had equal numbers of neurological, glaucoma, or glaucoma suspect cases, matched for age and for mean deviation between neurological and glaucoma cases. NHT scores as previously described and a new NHT laterality score were calculated. The ability of these scores to distinguish neurological from other fields was assessed with receiver operating characteristic (ROC) analysis. Three machine classifier algorithms were also evaluated: decision tree, random forest, and least absolute shrinkage and selection operator (LASSO). We also evaluated the ability of NHT to identify the type of neurological field defect (homonymous or bitemporal). Results. The area under the ROC curve (AUC) for the maximum NHT score was 0.92 (confidence interval [CI]: 0.87, 0.97). Using NHT laterality scores from each eye combined with the sum of NHT scores, the AUC improved to 0.93 (CI: 0.88, 0.98). The largest AUC for machine learning algorithms was for the LASSO method (0.96, CI: 0.92, 0.99). The NHT scores identified the type of neurological defect in 96% (158/164) of patients. Conclusions. The new NHT distinguished neurological field defects from those of glaucoma and glaucoma suspects, providing accurate categorization of defect type. Its implementation may identify unsuspected neurological disease in clinical visual field testing.

Original languageEnglish (US)
Pages (from-to)1017-1023
Number of pages7
JournalInvestigative Ophthalmology and Visual Science
Volume55
Issue number2
DOIs
StatePublished - Jan 21 2014

Fingerprint

Visual Field Tests
ROC Curve
Visual Fields
Glaucoma
Ocular Hypertension
Aptitude
Confidence Intervals
Area Under Curve
Decision Trees

Keywords

  • Algorithm
  • Bitemporal
  • Chiasm
  • Glaucoma
  • Homonymous
  • Neuro-ophthalmology
  • Neurological disease
  • Visual field

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems
  • Cellular and Molecular Neuroscience

Cite this

@article{a2d09f8a57a54988bb15c05c8e7e3ea1,
title = "Development and validation of an improved neurological hemifield test to identify chiasmal and postchiasmal lesions by automated perimetry",
abstract = "Purpose. To improve the neurological hemifield test (NHT) using visual field data from both eyes to detect and classify visual field loss caused by chiasmal or postchiasmal lesions. Methods. Visual field and clinical data for 633 patients were divided into a training set (474 cases) and a validation set (159 cases). Each set had equal numbers of neurological, glaucoma, or glaucoma suspect cases, matched for age and for mean deviation between neurological and glaucoma cases. NHT scores as previously described and a new NHT laterality score were calculated. The ability of these scores to distinguish neurological from other fields was assessed with receiver operating characteristic (ROC) analysis. Three machine classifier algorithms were also evaluated: decision tree, random forest, and least absolute shrinkage and selection operator (LASSO). We also evaluated the ability of NHT to identify the type of neurological field defect (homonymous or bitemporal). Results. The area under the ROC curve (AUC) for the maximum NHT score was 0.92 (confidence interval [CI]: 0.87, 0.97). Using NHT laterality scores from each eye combined with the sum of NHT scores, the AUC improved to 0.93 (CI: 0.88, 0.98). The largest AUC for machine learning algorithms was for the LASSO method (0.96, CI: 0.92, 0.99). The NHT scores identified the type of neurological defect in 96{\%} (158/164) of patients. Conclusions. The new NHT distinguished neurological field defects from those of glaucoma and glaucoma suspects, providing accurate categorization of defect type. Its implementation may identify unsuspected neurological disease in clinical visual field testing.",
keywords = "Algorithm, Bitemporal, Chiasm, Glaucoma, Homonymous, Neuro-ophthalmology, Neurological disease, Visual field",
author = "McCoy, {Allison N.} and Quigley, {Harry A} and Jiangxia Wang and Miller, {Neil R} and Subramanian, {Prem S.} and Pradeep Ramulu and Michael Boland",
year = "2014",
month = "1",
day = "21",
doi = "10.1167/iovs.13-13702",
language = "English (US)",
volume = "55",
pages = "1017--1023",
journal = "Investigative Ophthalmology and Visual Science",
issn = "0146-0404",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "2",

}

TY - JOUR

T1 - Development and validation of an improved neurological hemifield test to identify chiasmal and postchiasmal lesions by automated perimetry

AU - McCoy, Allison N.

AU - Quigley, Harry A

AU - Wang, Jiangxia

AU - Miller, Neil R

AU - Subramanian, Prem S.

AU - Ramulu, Pradeep

AU - Boland, Michael

PY - 2014/1/21

Y1 - 2014/1/21

N2 - Purpose. To improve the neurological hemifield test (NHT) using visual field data from both eyes to detect and classify visual field loss caused by chiasmal or postchiasmal lesions. Methods. Visual field and clinical data for 633 patients were divided into a training set (474 cases) and a validation set (159 cases). Each set had equal numbers of neurological, glaucoma, or glaucoma suspect cases, matched for age and for mean deviation between neurological and glaucoma cases. NHT scores as previously described and a new NHT laterality score were calculated. The ability of these scores to distinguish neurological from other fields was assessed with receiver operating characteristic (ROC) analysis. Three machine classifier algorithms were also evaluated: decision tree, random forest, and least absolute shrinkage and selection operator (LASSO). We also evaluated the ability of NHT to identify the type of neurological field defect (homonymous or bitemporal). Results. The area under the ROC curve (AUC) for the maximum NHT score was 0.92 (confidence interval [CI]: 0.87, 0.97). Using NHT laterality scores from each eye combined with the sum of NHT scores, the AUC improved to 0.93 (CI: 0.88, 0.98). The largest AUC for machine learning algorithms was for the LASSO method (0.96, CI: 0.92, 0.99). The NHT scores identified the type of neurological defect in 96% (158/164) of patients. Conclusions. The new NHT distinguished neurological field defects from those of glaucoma and glaucoma suspects, providing accurate categorization of defect type. Its implementation may identify unsuspected neurological disease in clinical visual field testing.

AB - Purpose. To improve the neurological hemifield test (NHT) using visual field data from both eyes to detect and classify visual field loss caused by chiasmal or postchiasmal lesions. Methods. Visual field and clinical data for 633 patients were divided into a training set (474 cases) and a validation set (159 cases). Each set had equal numbers of neurological, glaucoma, or glaucoma suspect cases, matched for age and for mean deviation between neurological and glaucoma cases. NHT scores as previously described and a new NHT laterality score were calculated. The ability of these scores to distinguish neurological from other fields was assessed with receiver operating characteristic (ROC) analysis. Three machine classifier algorithms were also evaluated: decision tree, random forest, and least absolute shrinkage and selection operator (LASSO). We also evaluated the ability of NHT to identify the type of neurological field defect (homonymous or bitemporal). Results. The area under the ROC curve (AUC) for the maximum NHT score was 0.92 (confidence interval [CI]: 0.87, 0.97). Using NHT laterality scores from each eye combined with the sum of NHT scores, the AUC improved to 0.93 (CI: 0.88, 0.98). The largest AUC for machine learning algorithms was for the LASSO method (0.96, CI: 0.92, 0.99). The NHT scores identified the type of neurological defect in 96% (158/164) of patients. Conclusions. The new NHT distinguished neurological field defects from those of glaucoma and glaucoma suspects, providing accurate categorization of defect type. Its implementation may identify unsuspected neurological disease in clinical visual field testing.

KW - Algorithm

KW - Bitemporal

KW - Chiasm

KW - Glaucoma

KW - Homonymous

KW - Neuro-ophthalmology

KW - Neurological disease

KW - Visual field

UR - http://www.scopus.com/inward/record.url?scp=84896722778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896722778&partnerID=8YFLogxK

U2 - 10.1167/iovs.13-13702

DO - 10.1167/iovs.13-13702

M3 - Article

VL - 55

SP - 1017

EP - 1023

JO - Investigative Ophthalmology and Visual Science

JF - Investigative Ophthalmology and Visual Science

SN - 0146-0404

IS - 2

ER -