Application of Random Forests Methods to Diabetic Retinopathy Classification Analyses

Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:PloS one Ročník 9; číslo 6; s. e98587
Hlavní autori: Casanova, Ramon, Saldana, Santiago, Chew, Emily Y., Danis, Ronald P., Greven, Craig M., Ambrosius, Walter T.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Public Library of Science 18.06.2014
Public Library of Science (PLoS)
Predmet:
Aged
Alzheimer's disease
Artificial intelligence
Automation
Blindness
Brain research
Classification
Classifiers
Computer and Information Sciences
Data processing
Decision Trees
Diabetes
Diabetes mellitus
Diabetes Mellitus, Type 2 - complications
Diabetic retinopathy
Diabetic Retinopathy - classification
Diabetic Retinopathy - diagnosis
Diagnostic Techniques, Ophthalmological
Humans
Medicine
Medicine and Health Sciences
Middle Aged
Model accuracy
Photography
Physical Sciences
Regression analysis
Retinopathy
Risk assessment
ROC Curve
Statistical analysis
Studies
Teaching methods
Therapeutic applications
ISSN:1932-6203, 1932-6203
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects. Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance. Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables. We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Conceived and designed the experiments: RC RD. Performed the experiments: SS RC. Analyzed the data: RC SS WA EC RD CG. Wrote the paper: RC SS WA EC RD CG.
Competing Interests: The authors have declared that no competing interests exist.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0098587