Comparison of Different Machine Learning Classifiers for Glaucoma Diagnosis Based on Spectralis OCT

Abstract

Early detection is important in glaucoma management. By using optical coherence tomography (OCT), the subtle structural changes caused by glaucoma can be detected. Though OCT provided abundant parameters for comprehensive information, clinicians may be confused once the results conflict. Machine learning classifiers (MLCs) are good tools for considering numerous parameters and generating reliable diagnoses in glaucoma practice. Here we aim to compare different MLCs based on Spectralis OCT parameters, including circumpapillary retinal nerve fiber layer (cRNFL) thickness, Bruch’s membrane opening-minimum rim width (BMO-MRW), Early Treatment Diabetes Retinopathy Study (ETDRS) macular thickness, and posterior pole asymmetry analysis (PPAA), in discriminating normal from glaucomatous eyes. Five MLCs were proposed, namely conditional inference trees (CIT), logistic model tree (LMT), C5.0 decision tree, random forest (RF), and extreme gradient boosting (XGBoost). Logistic regression (LGR) was used as a benchmark for comparison. RF was shown to be the best model. Ganglion cell layer measurements were the most important predictors in early glaucoma detection and cRNFL measurements were more important as the glaucoma severity increased. The global, temporal, inferior, superotemporal, and inferotemporal sites were relatively influential locations among all parameters. Clinicians should cautiously integrate the Spectralis OCT results into the entire clinical picture when diagnosing glaucoma.

Decision Trees for Glaucoma Screening Based on the Asymmetry of the Retinal Nerve Fiber Layer in Optical Coherence Tomography

“…They allow for rapid classification of new observations, since it is much simpler to evaluate just one or two logical conditions than to compute scores using complex nonlinear equations for each group. For example, in [42] complex machine learning classifiers (conditional inference trees, logistic model tree, C5.0 decision tree, random forest and extreme gradient boosting XGBoost) use OCT parameters to diagnose glaucoma, achieving slightly better performances (average accuracy 0.8818, average sensitivity 0.9166, average specificity 0.8507 and average area under the curve 0.9459) than decision trees. However, these models can be seen as black boxes which produce results based solely on the input data using an algorithm, which prevents clinicians from understanding how variables are being combined to make such predictions.…”

Comparing Multiple Linear Regression and Machine Learning in Predicting Diabetic Urine Albumin–Creatinine Ratio in a 4-Year Follow-Up Study

“…This research proposed a scheme based on four machine learning methods, namely classification and regression tree (CART), random forest (RF), stochastic gradient boosting (SGB), and eXtreme gradient boosting (XGBoost), to construct predictive models for predicting diabetic uACR and to identify the importance of these risk factors. These ML methods have been applied in various healthcare applications and do not have prior assumptions regarding data distribution [19][20][21][22][23][24][25][26][27][28]. MLR was used as the benchmark for comparison.…”

Important Risk Factors in Patients with Nonvalvular Atrial Fibrillation Taking Dabigatran Using Integrated Machine Learning Scheme—A Post Hoc Analysis

“…Although the CHA 2 DS 2 -VASc score has been widely used for years with convenience and reliability [ 14 , 15 ], insufficient prediction performance (C statistic of 0.679) has remained a concern [ 16 ]. Machine learning (ML) methods have been recently used as well-constructed analytical, classification and prediction tools for medical problems [ 17 , 18 , 19 , 20 , 21 , 22 ]. Their advantage and performance in demonstrating complex relationships between risk factors and outcomes and analyzing important information hidden in the vast amount of medical data have made them an emerging research topic.…”