Dataset Information

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

ABSTRACT:

Purpose

To test the ability of machine learning classifiers (MLCs) using optical coherence tomography (OCT) and standard automated perimetry (SAP) parameters to discriminate between healthy and glaucomatous individuals, and to compare it to the diagnostic ability of the combined structure-function index (CSFI), general ophthalmologists and glaucoma specialists.

Design

Cross-sectional prospective study.

Methods

Fifty eight eyes of 58 patients with early to moderate glaucoma (median value of the mean deviation = -3.44 dB; interquartile range, -6.0 to -2.4 dB) and 66 eyes of 66 healthy individuals underwent OCT and SAP tests. The diagnostic accuracy (area under the ROC curve-AUC) of 10 MLCs was compared to those obtained with the CSFI, 3 general ophthalmologists and 3 glaucoma specialists exposed to the same OCT and SAP data.

Results

The AUCs obtained with MLCs ranged from 0.805 (Classification Tree) to 0.931 (Radial Basis Function Network, RBF). The sensitivity at 90% specificity ranged from 51.6% (Classification Tree) to 82.8% (Bagging, Multilayer Perceptron and Support Vector Machine Gaussian). The CSFI had a sensitivity of 79.3% at 90% specificity, and the highest AUC (0.948). General ophthalmologists and glaucoma specialists' grading had sensitivities of 66.2% and 83.8% at 90% specificity, and AUCs of 0.879 and 0.921, respectively. RBF (the best MLC), the CSFI, and glaucoma specialists showed significantly higher AUCs than that obtained by general ophthalmologists (P<0.05). However, there were no significant differences between the AUCs obtained by RBF, the CSFI, and glaucoma specialists (P>0.25).

Conclusion

Our findings suggest that both MLCs and the CSFI can be helpful in clinical practice and effectively improve glaucoma diagnosis in the primary eye care setting, when there is no glaucoma specialist available.

SUBMITTER: Shigueoka LS

PROVIDER: S-EPMC6281287 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Shigueoka Leonardo Seidi LS Vasconcellos José Paulo Cabral de JPC Schimiti Rui Barroso RB Reis Alexandre Soares Castro ASC Oliveira Gabriel Ozeas de GO Gomi Edson Satoshi ES Vianna Jayme Augusto Rocha JAR Lisboa Renato Dichetti Dos Reis RDDR Medeiros Felipe Andrade FA Costa Vital Paulino VP

PloS one 20181205 12

<h4>Purpose</h4>To test the ability of machine learning classifiers (MLCs) using optical coherence tomography (OCT) and standard automated perimetry (SAP) parameters to discriminate between healthy and glaucomatous individuals, and to compare it to the diagnostic ability of the combined structure-function index (CSFI), general ophthalmologists and glaucoma specialists.<h4>Design</h4>Cross-sectional prospective study.<h4>Methods</h4>Fifty eight eyes of 58 patients with early to moderate glaucoma ...[more]

PMID: 30517157

Similar Datasets

Project description:PurposeTo investigate the relationship between longitudinal changes in macular thickness measurements from OCT and changes in central visual field (VF) in patients with glaucoma with central or advanced damage at baseline.DesignLongitudinal cohort study.ParticipantsA total of 116 eyes with ≥3 years of follow-up and ≥5 macular OCT images and central 10° VF tests were selected.MethodsOCT superpixels and VF locations were matched correcting for retinal ganglion cell (RGC) displacement. Superpixel thickness and VF total deviation (TD) values, in both logarithmic and linear scales, were averaged within 3 eccentricities (3.4°, 5.6°, and 6.8°) and superior and inferior hemiretinas and hemifields. We estimated pointwise TD rates of change and rates of change at superpixels for full macular thickness (FMT), ganglion cell complex (GCC), ganglion cell inner plexiform layer (GCIPL), and ganglion cell layer (GCL). Correlation of structure-function (SF) rates of change was investigated with parametric tests. We compared the proportion of worsening and positive slopes for superpixels and VF test locations (negative vs. positive rates of change with P < 0.05) throughout the follow-up period. Permutation analyses were used to control specificity.Main outcome measuresMagnitude of correlation between structural and functional rates of change and proportion of worsening and positive slopes as a function of follow-up time.ResultsThe median (interquartile range) follow-up and number of exams were 4.2 (3.7-4.6) years and 8 (7-9), respectively. The highest correlation of change rates was observed at 3.4° and 5.6° eccentricities (r = 0.24, 0.41, 0.40, and 0.40 for FMT, GCC, GCIPL, and GCL for 3.4° eccentricity and r = 0.28, 0.32, 0.31, and 0.32 for FMT, GCC, GCIPL, and GCL for 5.6° eccentricity, respectively). Although GCC measures demonstrated the highest overall longitudinal SF correlations, the differences were not statistically significant. Significant structural worsening was more frequently detected than functional deterioration at 3- and 5-year time points (P < 0.025). Permutation analyses also confirmed this finding.ConclusionsCorrelations between central structural and functional rates of change were weak to fair in this cohort. Structural changes were detected more frequently than functional changes. Measurements of both structure and function are required for optimal detection of central progression.

Project description:OBJECTIVES:Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine-learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine-learning algorithms. METHODS:We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine-learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared with the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis, and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. RESULTS:After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95% confidence interval (CI) 0.56-0.67), whereas the machine-learning algorithm had a c-statistic of 0.64 (95% CI 0.60-0.69) in the validation cohort. The HALT-C model had a c-statistic of 0.60 (95% CI 0.50-0.70) in the validation cohort and was outperformed by the machine-learning algorithm. The machine-learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (P<0.001) and integrated discrimination improvement (P=0.04). CONCLUSIONS:Machine-learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC.

Dataset Information

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

Purpose

Design

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets