Detection of subclinical keratoconus using an automated decision tree classification.

PURPOSE: To develop a method for automatizing the detection of subclinical keratoconus based on a tree classification. DESIGN: Retrospective case-control study. METHODS: setting: University Hospital of Bordeaux. participants: A total of 372 eyes of 197 patients were enrolled: 177 normal eyes of 95 subjects, 47 eyes of 47 patients with forme fruste keratoconus, and 148 eyes of 102 patients with keratoconus. observation procedure: All eyes were imaged with a dual Scheimpflug analyzer. Fifty-five parameters derived from anterior and posterior corneal measurements were analyzed for each eye and a machine learning algorithm, the classification and regression tree, was used to classify the eyes into the 3 above-mentioned conditions. main outcome measures: The performance of the machine learning algorithm for classifying eye conditions was evaluated, and the curvature, elevation, pachymetric, and wavefront parameters were analyzed in each group and compared. RESULTS: The discriminating rules generated with the automated decision tree classifier allowed for discrimination between normal and keratoconus with 100% sensitivity and 99.5% specificity, and between normal and forme fruste keratoconus with 93.6% sensitivity and 97.2% specificity. The algorithm selected as the most discriminant variables parameters related to posterior surface asymmetry and thickness spatial distribution. CONCLUSION: The machine learning classifier showed very good performance for discriminating between normal corneas and forme fruste keratoconus and provided a tool that is closer to an automated medical reasoning. This might help in the surgical decision before refractive surgery by providing a good sensitivity in detecting ectasia-susceptible corneas.

Assessment of patient satisfaction with outcomes of and ophthalmic care for cataract surgery.

PURPOSE: To assess patient satisfaction with cataract surgery care. SETTING: Private and public health ophthalmic centers, France. METHODS: This prospective longitudinal multicenter observational study enrolled patients attending consultation for a preoperative visit from September 2007 to February 2008. Patients were eligible if they had uncomplicated cataract and agreed to participate. At the preoperative visits, medical data and disease history were collected. At the first postoperative visit (at 1 to 7 days), the following data were collected: patient status, surgical procedure, and follow-up (patient management, complications, medications). Patients completed a questionnaire after each visit to assess satisfaction with their management and follow-up before, during, and after surgery (up to 30 days postoperatively). RESULTS: Of the 781 patients enrolled by 91 ophthalmologists, 41 were excluded for not meeting eligibility criteria, leaving 740 patients in the statistical analysis. Cataract extraction was by phacoemulsification. The incision was 2.2 to 3.2 mm in 94.7% of cases, and the intraocular lens was acrylic in 96.3% of cases. Anesthesia was mainly topical (56.8%) or local (42.1%). The most frequent postoperative treatments were nonsteroidal antiinflammatory eyedrops and combined steroidal and antibacterial eyedrops (95.9% and 94.7%, respectively). Most patients (96.4%) said the surgery results met their expectations, and 67.2% reported being able to perform activities they could not do preoperatively. Overall, 98.2% of patients said they were satisfied with their management. CONCLUSION: Assessment of the management and follow-up of patients having cataract surgery showed that the care provided was in accordance with the expectations of French patients. FINANCIAL DISCLOSURE: No author has a financial or proprietary interest in any material or method mentioned.