Predicting glaucomatous progression in glaucoma suspect eyes using relevance vector machine classifiers for combined structural and functional measurements

Abstract

Purpose: The goal of this study was to determine if glaucomatous progression in suspect eyes can be predicted from baseline confocal scanning laser ophthalmoscope (CSLO) and standard automated perimetry (SAP) measurements analyzed with relevance vector machine (RVM) classifiers.

Methods: Two hundred sixty-four eyes of 193 participants were included. All eyes had normal SAP results at baseline with five or more SAP tests over time. Eyes were labeled progressed (n = 47) or stable (n = 217) during follow-up based on SAP Guided Progression Analysis or serial stereophotograph assessment. Baseline CSLO-measured topographic parameters (n = 117) and baseline total deviation values from the 24-2 SAP test-grid (n = 52) were selected from each eye. Ten-fold cross-validation was used to train and test RVMs using the CSLO and SAP features. Receiver operating characteristic (ROC) curve areas were calculated using full and optimized feature sets. ROC curve results from RVM analyses of CSLO, SAP, and CSLO and SAP combined were compared to CSLO and SAP global indices (Glaucoma Probability Score, mean deviation and pattern standard deviation).

Results: The areas under the ROC curves (AUROCs) for RVMs trained on optimized feature sets of CSLO parameters, SAP parameters, and CSLO and SAP parameters combined were 0.640, 0.762, and 0.805, respectively. AUROCs for CSLO Glaucoma Probability Score, SAP mean deviation (MD), and SAP pattern standard deviation (PSD) were 0.517, 0.513, and 0.620, respectively. No CSLO or SAP global indices discriminated between baseline measurements from progressed and stable eyes better than chance.

Conclusions: In our sample, RVM analyses of baseline CSLO and SAP measurements could identify eyes that showed future glaucomatous progression with a higher accuracy than the CSLO and SAP global indices. (ClinicalTrials.gov numbers, NCT00221897, NCT00221923.).

Conflict of interest statement

Disclosure: C. Bowd, None; I. Lee, None; M.H. Goldbaum, None; F.A. Medeiros, Alcon Laboratories Inc. (F,C,R), Allergan Inc. (F,C), Carl Zeiss Meditec Inc. (F,R), Merck Inc. (F,R), Pfizer Inc. (F,C,R), Reichert Inc. (R); M. Balasubramanian, None; L.M. Zangwill, Carl Zeiss Meditec Inc. (F), Heidelberg Engineering GmbH (F,R), Optovue Inc. (F), Topcon Medical Systems Inc. (F); C.A. Girkin, Alcon Laboratories Inc. (C), Allergan Inc. (C), Carl Zeiss Meditec Inc. (R), Pfizer Inc. (C), Heidelberg Engineering GmbH (R), Merck Inc. (R), Optovue Inc. (R), Topcon Medical Systems Inc. (R); J.M. Liebmann, Alcon Laboratories Inc. (C), Allergan Inc. (C), Carl Zeiss Meditec Inc. (F), Diopsys Corp. (F,C), Heidelberg Engineering GmbH (F), Optovue Inc. (F,C), Pfizer Inc. (C), Topcon Medical Systems Inc. (F,C); R.N. Weinreb, Alcon Laboratories Inc. (C), Allergan Inc. (C), Carl Zeiss Meditec Inc. (F,C), Heidelberg Engineering GmbH (F), Optovue Inc. (F,C), Merck Inc. (C), Novartis (F), Pfizer Inc. (F), Topcon Medical Systems Inc. (F)

Figures

Figure 1.

ROC curves for global HRT and SAP parameters and optimized RVM results. AUROCs are provided in the Legend.

Figure 2.

Percentage of progressed or stable eyes assigned by relevance vector machine classifier (RVM) to each 10% probability bin. Thirty percent of progressed eyes and 4% of stable eyes were assigned a probability at or over 0.50 (sensitivity was 0.30 and specificity was 0.96). When the RVM cut-off P value was set to result in a specificity of 0.85 (RVM P value cut-off = 0.274), sensitivity increased to 0.58.