Search

Purpose: Despite progress in management of open‐angle glaucoma, early diagnosis remains difficult due to delayed ophthalmologist consultation. Early glaucoma treatment avoids vision loss, thus developing automated detection methods is of importance for public health. We used supervised machine learning models on medical insurance claims data to identify at‐risk patient profiles that would benefit from undergoing glaucoma diagnosis, leading to early detection. Methods: Using medical claims records from a Swiss health insurance company, we identified a "glaucoma group" composed by 2700 patients (18–65 yo) with at least 3 years of historical data in the database and at least one year of medications for lowering intraocular pressure. To complete the training dataset, we randomly selected a "non‐glaucoma control group" (N = 2700) with same age range and medical criteria. Random Forest models were then trained using patient medical consumption data (e.g. number of drugs, number of consultations, ocular tests) in order to estimate individual's probability of having glaucoma based on medical claims records. Population was split into training set (70%) and test set (30%) to estimate the model prediction performance. Results: The mean age of population with glaucoma was 55.3 (SD: 11.3), and had an average of 1.96 (SD: 2.8) eye visits within the 3 years period prior to their first glaucoma prescription. t‐test showed significant association between consumption of eye products (e.g. artificial tears) during the two years prior to glaucoma medication. The Random Forest classifier accuracy computed on the test set (N = 1600) showed a positive predictive value of 78.5%, a negative predictive value of 79.2%. Sensitivity and specificity were of 79.4% and 77.2% respectively. Conclusions: To our knowledge, this study is the first to attempt estimating glaucoma probabilities from medical consumption invoice data. Our preliminary results show that using supervised machine learning algorithms could identify high‐risk patient profiles of glaucoma with an accuracy of almost 80%. These patients may benefit from an early ocular examination. Automated screening based on medical claims data could thus allow improving open‐angle glaucoma‐related health outcomes, minimizing serious vision loss, and reducing health costs. [ABSTRACT FROM AUTHOR]

Purpose To study efficacy and tolerance of ophthalmic insert Mydriasert® versus standard treatment phenylephrine and tropicamide eye drops for fundus examination in neonates. Methods Prospective, randomised, single-blinded non-inferiority study of 80 premature and full-term babies and infants treated for fundus examination. Mydriasis was obtained with two groups randomly assigned. The eye drop group received three instillations of 2.5% phenylephrine and 0.5% tropicamide and the insert group received Mydriasert® containing phenylephrine and tropicamide. the mydriasis was evaluated 75 minutes after the introduction of the mydriatic agents. Results The mydriasis was successfully achieved in both eyes in 97.5% of infants in the insert group and 90% in the eye drop group at 75 minutes after dispensation. The efficacy of the insert was non-inferior compared to the eye drops. To reach effective mydriasis, the insert group required fewer nursing interventions for one patient comparing to the eye drop group. Good general and local tolerance was observed in the two groups. However two patients reported an adverse event as bradycardia and gastro-oesophageal reflux that could be related to neonate pathology. Conclusions Mydriasis obtained with the ophthalmic insert Mydriasert® was not inferior compared to standard eye drop treatment. Insert reduced the number of nursing interventions to obtain mydriasis for a fundus examination. [ABSTRACT FROM AUTHOR]

Purpose To evaluate a new quality of life questionnaire in children presenting a strabismus with abnormal retinal correspondence and amblyopia before and after reeducation. Methods Twenty children of a mean age of 4,2 yo (range 2‐7yo) were included with a strabismus with 3 type deviations. They presented amblyopia of at least 2 lines VA. They underwent a complete ocular and orthoptic examination with binocular quantification. At the consultation, parents and child completed a self‐administered questionnaire of quality of life. The questionnaire has three major items including a total of 10 criterions. Criterions were quoted by 4 colors corresponding to a score (from 0 to 30) reflecting the daily activity. Children were treated with optical correction, eye‐patching and orthoptic reeducation as needed. Six months after, examination and questionnaire was completed again to appreciate the progression of the children capacities. Results Of the twenty children, 16 presented an esotropia, 4 an exotropia and 10 an isolated or associated vertical hypertropia. The mean rate of the questionnaire at baseline was 18. The twenty patients who presented an amblyopia had an improvement of VA after treatment. After 6 months, rate of all questionnaires was improved with a mean score of 25. Conclusion Very few QOL questionnaires had been developed and even more in ophthalmology. This questionnaire appears simple to complete for parents and children, it can also be a basis to evaluate the progress of amblyopia reeducation. [ABSTRACT FROM AUTHOR]