Comparison of Blended Learning With Traditional Dermatology Learning for Medical Students: Prospective Evaluation Study.

BACKGROUND: Novel internet-based applications and associated technologies have influenced all aspects of society, ranging from commerce and business to entertainment and health care, and education is no exception. In this context, this study was designed to evaluate the impact of a dermatology e-learning program on the academic performance of medical students in dermatology. OBJECTIVE: The aim of this study is to develop a dermatology blended-learning course for undergraduate medical students, evaluate the knowledge gained by students exposed to this course, and compare the results to those of traditional teaching methods. METHODS: In this prospective study, we evaluated the performance of fourth-semester medical students at the Federal University of Bahia, Brazil. Students who had been in their second year of the medical course in 2019 were considered the control group, while students in their second year in 2020 were considered the blended or hybrid group. The first group attended traditional classes, using printed material (books and handouts), while the second group used our web-based course and e-book as a supplement in a hybrid web-plus-traditional fashion. Neither participants nor evaluators were blinded. The students in both groups were subjected to the same pre- and postcourse face-to-face, multiple-choice, paper-based evaluations, and we compared their performances. The content of the classes was the same for both groups. All didactic activities were developed by a team of certified dermatologists and professors from the university. RESULTS: A total of 129 students were selected and divided into 2 groups: the control group (n=57) and the hybrid group (n=72). The precourse tests did not indicate any difference between the control group (mean score 2.74, SD 1.25) and the hybrid group (mean score 3.2, SD 1.22 SD; P>.05). The hybrid group had better final-term grades (mean 8.18, SD 1.26) than the traditional group (mean 7.11, SD 1.04). This difference was statistically significant (P<.05). CONCLUSIONS: This study explores pedagogical possibilities in the field of dermatology teaching for medical school students. The results suggest that the performance of undergraduate students who attended the course with additional e-learning material was superior when compared to the performance of those who participated in the traditional course alone.

Relationship between the biomechanical properties of the cornea and anterior segment measurements.

OBJECTIVE: To evaluate the relationship of biomechanical properties, corneal hysteresis and corneal resistance factor with age, sex and various corneal parameters measured with a Pentacam in normal subjects. METHODS: A total of 226 eyes from 113 patients were enrolled in this study. The subjects underwent Ocular Response Analyzer and Pentacam evaluations. A varying-intercept multilevel regression was implemented using Bayesian inference. The predictor variables were age, sex, central corneal thickness, corneal volume at a 7-mm diameter, anterior chamber angle and volume, anterior chamber depth, mean radius of the corneal curvature and corneal astigmatism. RESULTS: Corneal hysteresis ranged from 5.5 to 14.8 mmHg (mean 10.42±1.74 mmHg), and the corneal resistance factor ranged from 5.7 to 15.5 mmHg (mean 10.23±1.88 mmHg). No predictor variable other than gender and central corneal thickness had a significant correlation with either corneal hysteresis or corneal resistance factor. Corneal hysteresis was positively associated with female sex and with central corneal thickness, and corneal resistance factor was positively associated with central corneal thickness. CONCLUSION: Despite the associations found, only a small fraction of the variance in biomechanical measurements could be explained by the descriptors that were evaluated, indicating the influence of other corneal aspects on the biomechanical characteristics.

Relationship between the biomechanical properties of the cornea and anterior segment measurements

OBJECTIVE: To evaluate the relationship of biomechanical properties, corneal hysteresis and corneal resistance factor with age, sex and various corneal parameters measured with a Pentacam in normal subjects. METHODS: A total of 226 eyes from 113 patients were enrolled in this study. The subjects underwent Ocular Response Analyzer and Pentacam evaluations. A varying-intercept multilevel regression was implemented using Bayesian inference. The predictor variables were age, sex, central corneal thickness, corneal volume at a 7-mm diameter, anterior chamber angle and volume, anterior chamber depth, mean radius of the corneal curvature and corneal astigmatism. RESULTS: Corneal hysteresis ranged from 5.5 to 14.8 mmHg (mean 10.42±1.74 mmHg), and the corneal resistance factor ranged from 5.7 to 15.5 mmHg (mean 10.23±1.88 mmHg). No predictor variable other than gender and central corneal thickness had a significant correlation with either corneal hysteresis or corneal resistance factor. Corneal hysteresis was positively associated with female sex and with central corneal thickness, and corneal resistance factor was positively associated with central corneal thickness. CONCLUSION: Despite the associations found, only a small fraction of the variance in biomechanical measurements could be explained by the descriptors that were evaluated, indicating the influence of other corneal aspects on the biomechanical characteristics.

E-learning program for medical students in dermatology.

INTRODUCTION: Dermatological disorders are common in medical practice. In medical school, however, the time devoted to teaching dermatology is usually very limited. Therefore, online educational systems have increasingly been used in medical education settings to enhance exposure to dermatology. OBJECTIVE: The present study was designed to develop a e-learning program for medical students in dermatology and evaluate the impact of this program on learning. METHODS: This prospective study included second year medical students at the University of Technology and Science, Salvador, Brazil. All students attended discussion seminars and practical activities, and half of the students had adjunct online seminars (blended learning). Tests were given to all students before and after the courses, and test scores were evaluated. RESULTS: Students who participated in online discussions associated with face-to-face activities (blended learning) had significantly higher posttest scores (9.0 ± 0.8) than those who only participated in classes (7.75±1.8, p <0.01). CONCLUSIONS: The results indicate that an associated online course might improve the learning of medical students in dermatology.

Oculometric parameters of hyperopia in children with esotropic amblyopia.

PURPOSE: To study the oculometric parameters of hyperopia in children with esotropic amblyopia, comparing amblyopic eyes with fellow eyes. METHODS: Thirty-seven patients (5-8 years old) with bilateral hyperopia and esotropic amblyopia underwent a comprehensive ophthalmic examination, including cycloplegic refraction, keratometry and A-scan ultrasonography. Anterior chamber depth, lens thickness, vitreous chamber depth and total axial length were recorded. The refractive power of the crystalline lens was calculated using Bennett's equations. Paired Student's t-tests were used to compare ocular biometric measurements between amblyopic eyes and their fellow eyes. The associations of biometric parameters with refractive errors were assessed using Pearson correlation coefficients and linear regression. Multivariable models including axial length, corneal power and lens power were also constructed. RESULTS: Amblyopic eyes were found to have significantly more hyperopic refraction, less corneal power, greater lens power, shorter vitreous chamber depth and shorter axial length, despite similar anterior chamber depth and lens thickness. The strongest correlation with refractive error was observed for the axial length/corneal radius ratio (r(36) = -0.92, p < 0.001 for amblyopic and r(36) = -0.87, p < 0.001 for fellow eyes). Axial length accounted for 39.2% (R(2)) of the refractive error variance in amblyopic eyes and 35.5% in fellow eyes. Adding corneal power to the model increased R(2) to 85.7% and 79.6%, respectively. A statistically significant correlation was found between axial length and corneal power, indicating decreasing corneal power with increasing axial length, and they were similar for amblyopic eyes (r(36) = -0.53, p < 0.001) and fellow eyes (r(36) = -0.57, p < 0.001). A statistically significant correlation was also found between axial length and lens power, indicating decreasing lens power with increasing axial length (r(36) = -0.72, p < 0.001 for amblyopic eyes and r(36) = -0.69, p < 0.001 for fellow eyes). CONCLUSIONS: We observed that the correlation among the major oculometric parameters and their individual contribution to hyperopia in esotropic children were similar in amblyopic and non-amblyopic eyes. This finding suggests that the counterbalancing effect of greater corneal and lens power associated with shorter axial length is similar in both eyes of patients with esotropic amblyopia.

Rede de aprendizado supervisionado como método de auxilio na detecção do ceratocone / Supervised learning neural networks in the support to the diagnosis of keratoconus

INTRODUÇÃO: O ceratocone é uma doença não inflamatória, sem etiologia definida, caracterizada pelo afilamento estromal e protrusão da córnea. Geralmente esta doença torna-se clinicamente evidente na adolescência. Apesar de possuir sinais clínicos bem conhecidos, a detecção do ceratocone em estádios iniciais pode representar uma tarefa de difícil execução, mesmo quando a videoceratografia computadorizada ou outros métodos são utilizados para avaliar a córnea. Anteriormente, diagnosticar o ceratocone apenas após a identificação de sinais clínicos inequívocos era uma conduta aceitável. Com o advento da cirurgia refrativa porém, a identificação precoce do ceratocone tornou-se um procedimento de vital importância para evitar complicações pós-operatórias. O objetivo principal deste estudo é avaliar o uso de máquinas de vetor de suporte e redes neurais artificiais como métodos auxiliares para identificação de ceratocone e suspeita de ceratocone em exames realizados com o Orbscan II. MÉTODOS: Foram avaliados retrospectivamente dados de 344 pacientes. Os exames selecionados foram classificados em 6 categorias: normal (n=172), astigmatismo (n=89), ceratocone (n=46), ceratocone forma frustra (n=10), suspeita de ceratocone (n=16) e cirurgia refrativa (n=11). Para cada paciente 10 atributos foram obtidos ou calculados a partir de dados fornecidos pelo Orbscan II. O método do holdout e da validação cruzada foram utilizados para encontrar a melhor configuração, treinar e testar os classificadores. Além da acurácia, sensibilidade e especificidade, curvas ROC foram obtidas para cada classificador, e as áreas sob as curvas ROC foram calculadas. RESULTADOS: Os dois classificadores selecionados alcançaram um bom desempenho, com áreas sob as curvas ROC de 0,99. Não houve diferença estatística entre as suas performances. O desempenho dos classificadores foi superior ao desempenho de todos os atributos individuais do Orbscan II. (p<0,05). CONCLUSÃO: Os resultados alcançados...

PURPOSE: Keratoconus is a bilateral and non-inflammatory condition characterized by progressive thinning, protrusion and scarring of the córnea. The disease usually becomes clinically evident at puberty, and its etiology remains unknown. Although it has well-described clinical signs, early forms of the disease may be undetected, even when computer-assisted videokeratography techniques or other methods are used to evaluate the cornea. Prior to the development of refractive surgery, it was considered sufficient to diagnose clinically evident keratoconus. However, given the spread of refractive surgery, a careful differentiation between normal and early keratoconus cases is essential to avoid postoperative complications. This study evaluated the performance of support vector machine and multilayer perceptron neural network, as auxiliary tools to identify keratoconus from Orbscan II maps. METHODS: A total of 344 maps were retrospectively selected and classified into six categories: normal (n=172), astigmatism (n=89), keratoconus (n=46), forme fruste keratoconus (n=10), keratoconus suspect (n=16), and photorefractive keratectomy (n=11). For each map 10 attributes were obtained or calculated from data provided by the Orbscan II. Holdout method and ten-fold cross-validation was used to train and test the classifiers. Besides accuracy, sensitivity and specificity, ROC curves for each classifier were generated and the areas under the curves were calculated. RESULTS: The two selected classifiers provided a good performance and there were no differences between their performances. The area under the ROC curve of the support vector machine and multi-layer perceptron were significantly larger than those for all individual Orbscan II attributes evaluated (p<0.05). CONCLUSION: Overall, our results suggest that support vector machine and multi-layer perceptron classifiers, trained on Orbscan II data, could represent useful techniques for keratoconus detection.

E-learning program for medical students in dermatology

INTRODUCTION: Dermatological disorders are common in medical practice. In medical school, however, the time devoted to teaching dermatology is usually very limited. Therefore, online educational systems have increasingly been used in medical education settings to enhance exposure to dermatology. OBJECTIVE: The present study was designed to develop a e-learning program for medical students in dermatology and evaluate the impact of this program on learning. METHODS: This prospective study included second year medical students at the University of Technology and Science, Salvador, Brazil. All students attended discussion seminars and practical activities, and half of the students had adjunct online seminars (blended learning). Tests were given to all students before and after the courses, and test scores were evaluated. RESULTS: Students who participated in online discussions associated with face-to-face activities (blended learning) had significantly higher posttest scores (9.0 + 0.8) than those who only participated in classes (7.75+1.8, p <0.01). CONCLUSIONS: The results indicate that an associated online course might improve the learning of medical students in dermatology.

Chlorambucil and cyclosporine A in Brazilian patients with Behçet's disease uveitis: a retrospective study.

PURPOSE: To assess the efficacy and side effects of immunosuppressive therapy in patients with Behçet's disease uveitis. METHODS: A nonrandomized retrospective case-series study analyzed data from 22 patients with Behçet's disease uveitis, from a single Uveitis Service, São Paulo, Brazil (period 1978-2007), under systemic chlorambucil and/or cyclosporine A, for at least 6 months with a minimum one-year follow-up. Drug efficacy was measured by reduction in relapse rate and reduction of prednisone dose. RESULTS: Patients (10M/12F) mean age was 29 (range 10-43) years-old at the onset of uveitis. The median duration of followup was 11 (range 1-29) years-old. Chlorambucil (2-6 mg/day) was used in 13 patients and cyclosporine A (3-5 mg/kg/day) in 9 patients at initiation. Drugs were switched because of no effectiveness or side-effects. Chlorambucil was effective in 78.5% (11/14) and induced disease remission in 43% (6/14) of patients, whereas cyclosporine A was effective in 57% (8/14) of patients. Chlorambucil and cyclosporine A were discontinued due to side effects in 21% (leucopenia) and in 57% of patients (nephrotoxicity, 36% and gastrointestinal complications, 21%), respectively. No case of late malignancy was observed. 36% (16/44) of eyes had final visual acuity < or =0.1, among which 69% (11/16) had already this visual acuity at the first visit. CONCLUSION: This study reiterates previous data that chlorambucil can induce long-term remission of Behçet's disease uveitis, whereas cyclosporine is effective but side effects limit its use. Chlorambucil therapy may still be a reasonable option in patients with intractable, sight-threatening Behçet's disease uveitis.

Chlorambucil and cyclosporine A in Brazilian patients with Behçet's disease uveitis: a retrospective study / Clorambucil e ciclosporina A em pacientes brasileiros com doença de Behçet e uveíte: estudo retrospectivo

PURPOSE: To assess the efficacy and side effects of immunosuppressive therapy in patients with Behçet's disease uveitis. METHODS: A nonrandomized retrospective case-series study analyzed data from 22 patients with Behçet's disease uveitis, from a single Uveitis Service, São Paulo, Brazil (period 1978-2007), under systemic chlorambucil and/or cyclosporine A, for at least 6 months with a minimum one-year follow-up. Drug efficacy was measured by reduction in relapse rate and reduction of prednisone dose. RESULTS: Patients (10M/12F) mean age was 29 (range 10-43) years-old at the onset of uveitis. The median duration of followup was 11 (range 1-29) years-old. Chlorambucil (2-6 mg/day) was used in 13 patients and cyclosporine A (3-5 mg/kg/day) in 9 patients at initiation. Drugs were switched because of no effectiveness or side-effects. Chlorambucil was effective in 78.5 percent (11/14) and induced disease remission in 43 percent (6/14) of patients, whereas cyclosporine A was effective in 57 percent (8/14) of patients. Chlorambucil and cyclosporine A were discontinued due to side effects in 21 percent (leucopenia) and in 57 percent of patients (nephrotoxicity, 36 percent and gastrointestinal complications, 21 percent), respectively. No case of late malignancy was observed. 36 percent (16/44) of eyes had final visual acuity <0.1, among which 69 percent (11/16) had already this visual acuity at the first visit. CONCLUSION: This study reiterates previous data that chlorambucil can induce long-term remission of Behçet's disease uveitis, whereas cyclosporine is effective but side effects limit its use. Chlorambucil therapy may still be a reasonable option in patients with intractable, sight-threatening Behçet's disease uveitis.

OBJETIVOS: Avaliar a eficácia e efeitos colaterais da terapia imunossupressora em pacientes com uveíte associada à doença de Behçet. MÉTODOS: Estudo retrospectivo não randomizado no qual são analisados dados de 22 pacientes com uveíte associada à doença de Behçet que utilizaram clorambucil e/ou ciclosporina A sistêmica por período mínimo de 6 meses, acompanhados pelo período mínimo de 1 ano, num único Serviço de Uveíte, São Paulo, Brasil (período 1978-2007). A eficácia do tratamento foi avaliada pela redução no número de recidivas da inflamação e pela redução na dose diária de prednisona. RESULTADOS: Vinte e dois pacientes (10 M/12 F), com idade média de 29 (variação 10-43) anos, apresentaram tempo mediano de acompanhamento de 11 (variação 1-29) anos. Clorambucil (2-6 mg/dia) foi utilizado em 13 pacientes e ciclosporina A (3-5 mg/kg/dia) em 9 pacientes como droga de primeira escolha. As drogas foram substituídas quando não eficazes ou não toleradas devido a efeitos colaterais. Clorambucil foi eficaz em 78,5 por cento (11/14) e induziu remissão da doença em 43 por cento (6/14) dos pacientes; ciclosporina foi eficaz em 57 por cento (8/14) dos pacientes. Clorambucil e ciclosporina A foram suspensos devido a efeitos colaterais em 21 por cento (leucopenia) e em 57 por cento (nefrotoxicidade, 36 por cento e complicações gastrointestinais, 21 por cento) dos pacientes, respectivamente. Nenhum caso de malignidade foi observado. 36 por cento (16/44) olhos tiveram acuidade visual final <0,1, sendo que 69 por cento (11/16) já apresentavam esta acuidade na primeira consulta. CONCLUSÃO: Este estudo reforça dados de literatura que o clorambucil induz remissão da doença de Behçet enquanto a ciclosporina A é efetiva, porém efeitos colaterais limitam o seu uso. A terapia com clorambucil pode ser uma opção a ser considerada em pacientes com uveíte refratária associada à doença de Behçet.

Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations.

PURPOSE: To evaluate the performance of support vector machine, multi-layer perceptron and radial basis function neural network as auxiliary tools to identify keratoconus from Orbscan II maps. METHODS: A total of 318 maps were selected and classified into four categories: normal (n = 172), astigmatism (n = 89), keratoconus (n = 46) and photorefractive keratectomy (n = 11). For each map, 11 attributes were obtained or calculated from data provided by the Orbscan II. Ten-fold cross-validation was used to train and test the classifiers. Besides accuracy, sensitivity and specificity, receiver operating characteristic (ROC) curves for each classifier were generated, and the areas under the curves were calculated. RESULTS: The three selected classifiers provided a good performance, and there were no differences between their performances. The area under the ROC curve of the support vector machine, multi-layer perceptron and radial basis function neural network were significantly larger than those for all individual Orbscan II attributes evaluated (p < 0.05). CONCLUSION: Overall, the results suggest that using a support vector machine, multi-layer perceptron classifiers and radial basis function neural network, these classifiers, trained on Orbscan II data, could represent useful techniques for keratoconus detection.

Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations

PURPOSE: To evaluate the performance of support vector machine, multi-layer perceptron and radial basis function neural network as auxiliary tools to identify keratoconus from Orbscan II maps. METHODS: A total of 318 maps were selected and classified into four categories: normal (n = 172), astigmatism (n = 89), keratoconus (n = 46) and photorefractive keratectomy (n = 11). For each map, 11 attributes were obtained or calculated from data provided by the Orbscan II. Ten-fold cross-validation was used to train and test the classifiers. Besides accuracy, sensitivity and specificity, receiver operating characteristic (ROC) curves for each classifier were generated, and the areas under the curves were calculated. RESULTS: The three selected classifiers provided a good performance, and there were no differences between their performances. The area under the ROC curve of the support vector machine, multi-layer perceptron and radial basis function neural network were significantly larger than those for all individual Orbscan II attributes evaluated (p<0.05). CONCLUSION: Overall, the results suggest that using a support vector machine, multi-layer perceptron classifiers and radial basis function neural network, these classifiers, trained on Orbscan II data, could represent useful techniques for keratoconus detection.

Teledermatologia: correlação diagnóstica em serviço primário de saúde / Teledermatology: diagnostic correlation in a primary care service

FUNDAMENTOS: O termo telemedicina faz referência ao uso de tecnologias de comunicação para a transmissão a distância de informações relacionadas à saúde. Esse recurso é utilizado em várias especialidades médicas, principalmente naquelas em que a interpretação de imagens representa uma etapa fundamental na formulação diagnóstica. OBJETIVO: Avaliar a concordância entre o diagnóstico presencial e o diagnóstico a distância de lesões cutâneas, utilizando a teledermatologia, em pacientes atendidos em uma unidade básica de saúde. MÉTODOS: Foi realizado um estudo prospectivo envolvendo pacientes atendidos no serviço de dermatologia da clínica FTC em Salvador - BA. Participaram do estudo um dermatologista responsável pela consulta presencial e dois dermatologistas responsáveis pela consulta a distância. Os diagnósticos obtidos através da teleconsulta foram avaliados quanto à concordância e comparados com os diagnósticos da consulta presencial. RESULTADOS: Foram incluídos neste estudo 60 pacientes. Observou-se um grau de concordância total variando de 86,6 por cento a 91,6 por cento com índice Kappa de 0,62. CONCLUSÃO: A teledermatologia é uma forma de assistência com um grande potencial de uso na dermatologia, podendo representar uma ferramenta útil principalmente em casos clínicos de baixa complexidade, oriundos de unidades básicas de saúde.

BACKGROUND: Telemedicine can be defined as the use of telecommunication technologies for the transmission of health data. It has been described in different medical specialties, especially those in which interpretation of images represents a fundamental key in formulating diagnosis. OBJECTIVE: To evaluate the role of teledermatology in primary care system. METHODS: A prospective analysis included 60 patients seen in a primary care unit. All patients were seen by a dermatologist as regular outpatient dermatology consultation. A medical student obtained digital images and a brief clinical history of all patients. Using a Telemedicine system these data were reviewed by two dermatologists for distance diagnosis. Agreement between the diagnoses was assessed. RESULTS: Good agreement, ranging from 86.6 percent to 91.6 percent, was achieved between direct observation and teleconsultation. Good agreement was also achieved between two telemedicine diagnosis (Kappa = 0.62). CONCLUSION: Teledermatology is a form of care with great potential for use in dermatology, and could represent a useful tool in cases of low complexity from primary health units.

[Generalized eruptive syringoma: case report]. / Siringoma eruptivo disseminado: Relato de caso.

Syringomas are benign adnexal tumors derived from the intraepidermal portion of eccrine sweat ducts. Clinically, they usually appear as small yellow or skin-colored papules ranging from 1-3 mm in diameter on the lower eyelids. The condition of eruptive syringomas is a clinically distinct, uncommon variant of syringomas. This entity was first recognized by Darier and Jacquet in 1887. Since the initial description, less than 100 cases have been reported to date. Although eruptive syringomas can develop on various sites of the body, instances of widespread involvement, known as generalized eruptive syringoma, are rare. In this paper, we present a case of generalized eruptive syringoma on a 26-year-woman. She exhibited multiple, eruptive asymptomatic papules, symmetrically distributed on the face, scalp, upper and lower extremities, chest, and abdomen.

[Teledermatology: diagnostic correlation in a primary care service]. / Teledermatologia: correlação diagnóstica em serviço primário de saúde.

BACKGROUND: Telemedicine can be defined as the use of telecommunication technologies for the transmission of health data. It has been described in different medical specialties, especially those in which interpretation of images represents a fundamental key in formulating diagnosis. OBJECTIVE: To evaluate the role of teledermatology in primary care system. METHODS: A prospective analysis included 60 patients seen in a primary care unit. All patients were seen by a dermatologist as regular outpatient dermatology consultation. A medical student obtained digital images and a brief clinical history of all patients. Using a Telemedicine system these data were reviewed by two dermatologists for distance diagnosis. Agreement between the diagnoses was assessed. RESULTS: Good agreement, ranging from 86.6% to 91.6%, was achieved between direct observation and teleconsultation. Good agreement was also achieved between two telemedicine diagnosis (Kappa = 0.62). CONCLUSION: Teledermatology is a form of care with great potential for use in dermatology, and could represent a useful tool in cases of low complexity from primary health units.

Doenças do segmento anterior ocular associadas a lentes de contato: [revisão] / Contact lens-associated ocular anterior segment diseases: [review]

A disponibilidade de lentes de contato cada vez mais confortáveis e toleráveis favoreceu não só a ampliação das indicações, mas também o aumento do número de seus usuários. Como conseqüência deste fato as complicações associadas ao uso de lentes de contato são cada vez mais comuns, e representam um problema de grande prevalência na prática clínica. O objetivo deste estudo é revisar as principais doenças e alterações do segmento anterior e superfície ocular associadas ao uso de lentes de contato.

Nowadays, contact lenses have shown a larger variety of options in order to meet the needs of different patients. They have become more frequent in the clinical practice and, consequently, the complications related to contact lenses have been more common. This review attempted to describe the main alterations and diseases of the cornea and anterior segment associated with contact lens wearers.

Diagnóstico do ceratocone baseado no Orbscan com o auxílio de uma rede neural / Detection of keratoconus based on a neural network with Orbscan

OBJETIVO: Desenvolver uma rede neural artificial para classificar em normal ou portador de ceratocone os pacientes submetidos ao exame do Orbscan II TM. MÉTODOS: Foi realizado um estudo retrospectivo envolvendo 98 exames de 59 pacientes. Utilizando o programa Java Neural Network 1.1 foi criada uma rede neural artificial para classificar os exames entre os dois grupos (normais e portadores de ceratocone). Foram utilizados 73 exames para treinamento e validação da rede, e 25 para testar o seu funcionamento. RESULTADOS: Dos 73 exames utilizados no treinamento da rede, 59 eram normais e 14 mostravam alterações relacionadas ao ceratocone. O método utilizado para treinamento da rede foi o "backpropagation". A taxa de aprendizado utilizada foi de 0,2, e a taxa de tolerância de erro 0,05. Dos 25 exames utilizados para a avaliação da eficácia da rede, 19 eram normais, e 6 apresentavam ceratocone. Após o treinamento a rede apresentou sensibilidade e especificidade de 83 e 100 por cento, respectivamente. CONCLUSÃO: A rede neural artificial representa uma opção útil e viável para auxiliar na classificação de exames realizados com o Orbscan II TM.

PURPOSE: To evaluate an artificial neural network in order to correctly identify Orbscan II TM tests of patients with normal and keratoconus corneas. METHODS: A retrospective analysis included 98 Orbscan II TM tests of 59 subjects and an artificial neural network was created and trained based on the Java Neural Network 1.1 software. Seventy-three tests (59 normal tests and 14 keratoconus examinations) were applied to train the neural network and 25 eyes were used to test the method (19 normal eyes and 6 cases of keratoconus corneas). RESULTS: Backpropagation method was performed to train the neural network to 5 percent error and 0.2 learning rate. The trained neural network presented sensibility and specificity of 83 and 100 percent respectively. CONCLUSION: Artificial neural network can accurately help clinicians to classify keratoconus in Orbscan II TM tests.

[Contact lens-associated ocular anterior segment diseases]. / Doenças do segmento anterior ocular associadas a lentes de contato.

Nowadays, contact lenses have shown a larger variety of options in order to meet the needs of different patients. They have become more frequent in the clinical practice and, consequently, the complications related to contact lenses have been more common. This review attempted to describe the main alterations and diseases of the cornea and anterior segment associated with contact lens wearers.

[Detection of keratoconus based on a neural network with Orbscan]. / Diagnóstico do ceratocone baseado no Orbscan com o auxílio de uma rede neural.

PURPOSE: To evaluate an artificial neural network in order to correctly identify Orbscan II tests of patients with normal and keratoconus corneas. METHODS: A retrospective analysis included 98 Orbscan II tests of 59 subjects and an artificial neural network was created and trained based on the Java Neural Network 1.1 software. Seventy-three tests (59 normal tests and 14 keratoconus examinations) were applied to train the neural network and 25 eyes were used to test the method (19 normal eyes and 6 cases of keratoconus corneas). RESULTS: Backpropagation method was performed to train the neural network to 5% error and 0.2 learning rate. The trained neural network presented sensibility and specificity of 83 and 100% respectively. CONCLUSION: Artificial neural network can accurately help clinicians to classify keratoconus in Orbscan II tests.

[Palpebral cryptococcosis: case report]. / Criptococose palpebral: relato de caso.

This paper is about a patient with acquired immunodeficiency syndrome empirically treated for miliary tuberculosis. During the clinical evolution the patient presented lesions compromising the right eyelid and tarsal conjunctiva. The initial diagnostic hypothesis was ocular tuberculosis with conjunctival and eyelid involvement. The biopsy of the conjunctival lesion identified an encapsulated yeast-like fungus: Criptococcus neoformans. After starting treatment with B anfotericin, the cutaneus lesions cleared.

Criptococose palpebral: relato de caso / Palpebral cryptococcosis: case report

Relata-se o caso de uma paciente portadora de síndrome da imunodeficiência adquirida empiricamente tratada com esquema tríplice para tuberculose miliar. Durante a evolução clínica a paciente cursou com lesões comprometendo a pálpebra e conjuntiva tarsal à direita. A hipótese diagnóstica inicial foi de tuberculose ocular com comprometimento conjuntival e palpebral. A biópsia da lesão conjuntival mostrou presença do Criptococcus neoformans. Após o início do tratamento específico com anfotericina B, a paciente apresentou melhora das lesões cutâneas.