Cargando…

Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation

The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination inc...

Descripción completa

Detalles Bibliográficos
Autores principales: Oh, Sejong, Park, Yuli, Cho, Kyong Jin, Kim, Seong Jae
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8001225/
https://www.ncbi.nlm.nih.gov/pubmed/33805685
http://dx.doi.org/10.3390/diagnostics11030510
_version_ 1783671180223315968
author Oh, Sejong
Park, Yuli
Cho, Kyong Jin
Kim, Seong Jae
author_facet Oh, Sejong
Park, Yuli
Cho, Kyong Jin
Kim, Seong Jae
author_sort Oh, Sejong
collection PubMed
description The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination including an intraocular pressure (IOP) measurement, and fundus photography were provided for the feature selection process. Five selected features (variables) were used to develop a machine learning prediction model. The support vector machine, C5.0, random forest, and XGboost algorithms were tested for the prediction model. The performance of the prediction models was tested with 10-fold cross-validation. Statistical charts, such as gauge, radar, and Shapley Additive Explanations (SHAP), were used to explain the prediction case. All four models achieved similarly high diagnostic performance, with accuracy values ranging from 0.903 to 0.947. The XGboost model is the best model with an accuracy of 0.947, sensitivity of 0.941, specificity of 0.950, and AUC of 0.945. Three statistical charts were established to explain the prediction based on the characteristics of the XGboost model. Higher diagnostic performance was achieved with the XGboost model. These three statistical charts can help us understand why the machine learning model produces a specific prediction result. This may be the first attempt to apply “explainable artificial intelligence” to eye disease diagnosis.
format Online
Article
Text
id pubmed-8001225
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80012252021-03-28 Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation Oh, Sejong Park, Yuli Cho, Kyong Jin Kim, Seong Jae Diagnostics (Basel) Article The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination including an intraocular pressure (IOP) measurement, and fundus photography were provided for the feature selection process. Five selected features (variables) were used to develop a machine learning prediction model. The support vector machine, C5.0, random forest, and XGboost algorithms were tested for the prediction model. The performance of the prediction models was tested with 10-fold cross-validation. Statistical charts, such as gauge, radar, and Shapley Additive Explanations (SHAP), were used to explain the prediction case. All four models achieved similarly high diagnostic performance, with accuracy values ranging from 0.903 to 0.947. The XGboost model is the best model with an accuracy of 0.947, sensitivity of 0.941, specificity of 0.950, and AUC of 0.945. Three statistical charts were established to explain the prediction based on the characteristics of the XGboost model. Higher diagnostic performance was achieved with the XGboost model. These three statistical charts can help us understand why the machine learning model produces a specific prediction result. This may be the first attempt to apply “explainable artificial intelligence” to eye disease diagnosis. MDPI 2021-03-13 /pmc/articles/PMC8001225/ /pubmed/33805685 http://dx.doi.org/10.3390/diagnostics11030510 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Oh, Sejong
Park, Yuli
Cho, Kyong Jin
Kim, Seong Jae
Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title_full Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title_fullStr Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title_full_unstemmed Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title_short Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation
title_sort explainable machine learning model for glaucoma diagnosis and its interpretation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8001225/
https://www.ncbi.nlm.nih.gov/pubmed/33805685
http://dx.doi.org/10.3390/diagnostics11030510
work_keys_str_mv AT ohsejong explainablemachinelearningmodelforglaucomadiagnosisanditsinterpretation
AT parkyuli explainablemachinelearningmodelforglaucomadiagnosisanditsinterpretation
AT chokyongjin explainablemachinelearningmodelforglaucomadiagnosisanditsinterpretation
AT kimseongjae explainablemachinelearningmodelforglaucomadiagnosisanditsinterpretation