Literature DB >> 35764402

The Role of Optical Coherence Tomography Criteria and Machine Learning in Multiple Sclerosis and Optic Neuritis Diagnosis.

Rachel C Kenney1, Mengling Liu1, Lisena Hasanaj1, Binu Joseph1, Abdullah Abu Al-Hassan1, Lisanne J Balk1, Raed Behbehani1, Alexander Brandt1, Peter A Calabresi1, Elliot Frohman1, Teresa C Frohman1, Joachim Havla1, Bernhard Hemmer1, Hong Jiang1, Benjamin Knier1, Thomas Korn1, Letizia Leocani1, Elena Hernandez Martinez-Lapiscina1, Athina Papadopoulou1, Friedemann Paul1, Axel Petzold1, Marco Pisa1, Pablo Villoslada1, Hanna Zimmermann1, Lorna E Thorpe1, Hiroshi Ishikawa1, Joel S Schuman1, Gadi Wollstein1, Yu Chen1, Shiv Saidha1, Steven Galetta1, Laura J Balcer2.   

Abstract

BACKGROUND AND OBJECTIVES: Recent studies have suggested that intereye differences (IEDs) in peripapillary retinal nerve fiber layer (pRNFL) or ganglion cell + inner plexiform (GCIPL) thickness by spectral domain optical coherence tomography (SD-OCT) may identify people with a history of unilateral optic neuritis (ON). However, this requires further validation. Machine learning classification may be useful for validating thresholds for OCT IEDs and for examining added utility for visual function tests, such as low-contrast letter acuity (LCLA), in the diagnosis of people with multiple sclerosis (PwMS) and for unilateral ON history.
METHODS: Participants were from 11 sites within the International Multiple Sclerosis Visual System consortium. pRNFL and GCIPL thicknesses were measured using SD-OCT. A composite score combining OCT and visual measures was compared individual measurements to determine the best model to distinguish PwMS from controls. These methods were also used to distinguish those with a history of ON among PwMS. Receiver operating characteristic (ROC) curve analysis was performed on a training data set (2/3 of cohort) and then applied to a testing data set (1/3 of cohort). Support vector machine (SVM) analysis was used to assess whether machine learning models improved diagnostic capability of OCT.
RESULTS: Among 1,568 PwMS and 552 controls, variable selection models identified GCIPL IED, average GCIPL thickness (both eyes), and binocular 2.5% LCLA as most important for classifying PwMS vs controls. This composite score performed best, with area under the curve (AUC) = 0.89 (95% CI 0.85-0.93), sensitivity = 81%, and specificity = 80%. The composite score ROC curve performed better than any of the individual measures from the model (p < 0.0001). GCIPL IED remained the best single discriminator of unilateral ON history among PwMS (AUC = 0.77, 95% CI 0.71-0.83, sensitivity = 68%, specificity = 77%). SVM analysis performed comparably with standard logistic regression models. DISCUSSION: A composite score combining visual structure and function improved the capacity of SD-OCT to distinguish PwMS from controls. GCIPL IED best distinguished those with a history of unilateral ON. SVM performed as well as standard statistical models for these classifications. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that SD-OCT accurately distinguishes multiple sclerosis from normal controls as compared with clinical criteria.
© 2022 American Academy of Neurology.

Entities:  

Mesh:

Year:  2022        PMID: 35764402      PMCID: PMC9536738          DOI: 10.1212/WNL.0000000000200883

Source DB:  PubMed          Journal:  Neurology        ISSN: 0028-3878            Impact factor:   11.800


  15 in total

1.  Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry.

Authors:  Fabrício R Silva; Vanessa G Vidotti; Fernanda Cremasco; Marcelo Dias; Edson S Gomi; Vital P Costa
Journal:  Arq Bras Oftalmol       Date:  2013 May-Jun       Impact factor: 0.872

2.  Optimal intereye difference thresholds by optical coherence tomography in multiple sclerosis: An international study.

Authors:  Rachel C Nolan-Kenney; Mengling Liu; Omar Akhand; Peter A Calabresi; Friedemann Paul; Axel Petzold; Lisanne Balk; Alexander U Brandt; Elena H Martínez-Lapiscina; Shiv Saidha; Pablo Villoslada; Abdullah Abu Al-Hassan; Raed Behbehani; Elliot M Frohman; Teresa Frohman; Joachim Havla; Bernhard Hemmer; Hong Jiang; Benjamin Knier; Thomas Korn; Letizia Leocani; Athina Papadopoulou; Marco Pisa; Hanna Zimmermann; Steven L Galetta; Laura J Balcer
Journal:  Ann Neurol       Date:  2019-04-10       Impact factor: 10.422

3.  Diagnostic accuracy of optical coherence tomography inter-eye percentage difference for optic neuritis in multiple sclerosis.

Authors:  D Coric; L J Balk; B M J Uitdehaag; A Petzold
Journal:  Eur J Neurol       Date:  2017-10-09       Impact factor: 6.089

4.  APOSTEL 2.0 Recommendations for Reporting Quantitative Optical Coherence Tomography Studies.

Authors:  Aykut Aytulun; Andrés Cruz-Herranz; Orhan Aktas; Laura J Balcer; Lisanne Balk; Piero Barboni; Augusto Azuara Blanco; Peter A Calabresi; Fiona Costello; Bernardo Sanchez-Dalmau; Delia Cabrera DeBuc; Nicolas Feltgen; Robert P Finger; Jette Lautrup Frederiksen; Elliot Frohman; Teresa Frohman; David Garway-Heath; Iñigo Gabilondo; Jennifer S Graves; Ari J Green; Hans-Peter Hartung; Joachim Havla; Frank G Holz; Jaime Imitola; Rachel Kenney; Alexander Klistorner; Benjamin Knier; Thomas Korn; Scott Kolbe; Julia Krämer; Wolf A Lagrèze; Letizia Leocani; Oliver Maier; Elena H Martínez-Lapiscina; Sven Meuth; Olivier Outteryck; Friedemann Paul; Axel Petzold; Gorm Pihl-Jensen; Jana Lizrova Preiningerova; Gema Rebolleda; Marius Ringelstein; Shiv Saidha; Sven Schippling; Joel S Schuman; Robert C Sergott; Ahmed Toosy; Pablo Villoslada; Sebastian Wolf; E Ann Yeh; Patrick Yu-Wai-Man; Hanna G Zimmermann; Alexander U Brandt; Philipp Albrecht
Journal:  Neurology       Date:  2021-04-28       Impact factor: 9.910

5.  Development of machine learning models for diagnosis of glaucoma.

Authors:  Seong Jae Kim; Kyong Jin Cho; Sejong Oh
Journal:  PLoS One       Date:  2017-05-23       Impact factor: 3.240

6.  Automated algorithms combining structure and function outperform general ophthalmologists in diagnosing glaucoma.

Authors:  Leonardo Seidi Shigueoka; José Paulo Cabral de Vasconcellos; Rui Barroso Schimiti; Alexandre Soares Castro Reis; Gabriel Ozeas de Oliveira; Edson Satoshi Gomi; Jayme Augusto Rocha Vianna; Renato Dichetti Dos Reis Lisboa; Felipe Andrade Medeiros; Vital Paulino Costa
Journal:  PLoS One       Date:  2018-12-05       Impact factor: 3.240

7.  Computer-Aided Diagnosis of Multiple Sclerosis Using a Support Vector Machine and Optical Coherence Tomography Features.

Authors:  Carlo Cavaliere; Elisa Vilades; Mª C Alonso-Rodríguez; María Jesús Rodrigo; Luis Emilio Pablo; Juan Manuel Miguel; Elena López-Guillén; Eva Mª Sánchez Morla; Luciano Boquete; Elena Garcia-Martin
Journal:  Sensors (Basel)       Date:  2019-12-03       Impact factor: 3.576

8.  Optimal Intereye Difference Thresholds in Retinal Nerve Fiber Layer Thickness for Predicting a Unilateral Optic Nerve Lesion in Multiple Sclerosis.

Authors:  Rachel C Nolan; Steven L Galetta; Teresa C Frohman; Elliot M Frohman; Peter A Calabresi; Carmen Castrillo-Viguera; Diego Cadavid; Laura J Balcer
Journal:  J Neuroophthalmol       Date:  2018-12       Impact factor: 3.042

Review 9.  Artificial intelligence extension of the OSCAR-IB criteria.

Authors:  Axel Petzold; Philipp Albrecht; Laura Balcer; Erik Bekkers; Alexander U Brandt; Peter A Calabresi; Orla Galvin Deborah; Jennifer S Graves; Ari Green; Pearse A Keane; Jenny A Nij Bijvank; Josemir W Sander; Friedemann Paul; Shiv Saidha; Pablo Villoslada; Siegfried K Wagner; E Ann Yeh
Journal:  Ann Clin Transl Neurol       Date:  2021-05-19       Impact factor: 4.511

10.  Swept source optical coherence tomography to early detect multiple sclerosis disease. The use of machine learning techniques.

Authors:  Amaya Pérez Del Palomar; José Cegoñino; Alberto Montolío; Elvira Orduna; Elisa Vilades; Berta Sebastián; Luis E Pablo; Elena Garcia-Martin
Journal:  PLoS One       Date:  2019-05-06       Impact factor: 3.240

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.