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

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.

Avaliação do uso de colírio no paciente portador de glaucoma / Evaluation of the use of eye drops in patients with glaucoma

OBJETIVO: Identificação das principais variáveis que interferem na qualidade de instilação correta de colírio antiglaucomatoso. MÉTODOS: Realizou-se estudo transversal em 40 pacientes glaucomatosos sob tratamento clínico com uso de colírio, aplicando-se um questionário e realizando-se observações quanto à instilação. Foram investigadas as seguintes variáveis: sexo; escolaridade; idade; condições sócioeconômicas; lavagem das mãos; número de gotas por aplicação; alteração motora; pessoa que aplica o colírio; local da aplicação; contato do frasco com as pálpebras, a conjuntiva e a córnea; instrução pregressa; posição de aplicação; ardor, dor ou irritação ocular após a aplicação e acuidade visual. A partir do questionário e das observações, as variáveis citadas foram correlacionadas com a qualidade de instilação. O modelo de análise foi a regressão logística binária. RESULTADOS: Dentre todas as variáveis em questão, apenas a pessoa que aplica o colírio e a sensação de ardor, dor ou irritação ocular mostraram-se estatisticamente significativas para uma adequada instilação de colírio. CONCLUSÃO: A presença de um acompanhante e o ardor à instilação do colírio influenciaram significativamente na qualidade de instilação do mesmo.

PURPOSE:To identify the most important variables interfering with the correct topical administration of antiglaucomatous drugs. METHODS: Forty glaucomatous patients under clinical treatment were interviewed and observed while applying antiglaucomatous drugs. The following variables were analyzed: sex; age; income; washing of the hands; number of drops; motor abnormalities; availability of another person to apply the drug; place of the globe reached; bottle-eye contact; previous instruction; positioning for application; development of a burning sensation, pain or irritation. Using the questionary, the variables were correlated with the quality of instillation. RESULTS: Among all variables, only the availability of another person to apply the drug and the existence of a burning sensation, pain or eye irritation showed statistically important correlation to proper instillation. CONCLUSION: The presence of a companion and the development of burning sensation affected the quality of instillation.