Developing an iOS application that uses machine learning for the automated diagnosis of blepharoptosis.

PURPOSE: To assess the performance of artificial intelligence in the automated classification of images taken with a tablet device of patients with blepharoptosis and subjects with normal eyelid. METHODS: This is a prospective and observational study. A total of 1276 eyelid images (624 images from 347 blepharoptosis cases and 652 images from 367 normal controls) from 606 participants were analyzed. In order to obtain a sufficient number of images for analysis, 1 to 4 eyelid images were obtained from each participant. We developed a model by fully retraining the pre-trained MobileNetV2 convolutional neural network. Subsequently, we verified whether the automatic diagnosis of blepharoptosis was possible using the images. In addition, we visualized how the model captured the features of the test data with Score-CAM. k-fold cross-validation (k = 5) was adopted for splitting the training and validation. Sensitivity, specificity, and the area under the curve (AUC) of the receiver operating characteristic curve for detecting blepharoptosis were examined. RESULTS: We found the model had a sensitivity of 83.0% (95% confidence interval [CI], 79.8-85.9) and a specificity of 82.5% (95% CI, 79.4-85.4). The accuracy of the validation data was 82.8%, and the AUC was 0.900 (95% CI, 0.882-0.917). CONCLUSION: Artificial intelligence was able to classify with high accuracy images of blepharoptosis and normal eyelids taken using a tablet device. Thus, the diagnosis of blepharoptosis with a tablet device is possible at a high level of accuracy. TRIAL REGISTRATION: Date of registration: 2021-06-25. TRIAL REGISTRATION NUMBER: UMIN000044660. Registration site: https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000051004.

Posterior callosotomy using a parietooccipital interhemispheric approach in the semi-prone park-bench position.

A 2-stage corpus callosotomy is accepted as a palliative procedure for patients older than 16 years with, in particular, medically intractable generalized epilepsy and drop attack seizures and is preferable for a lower risk of disconnection syndrome. Although the methods by which a previously performed craniotomy can be reopened for posterior callosotomy have already been reported, posterior corpus callosotomy using a parietooccipital interhemispheric approach with the patient in a semi-prone park-bench position has not been described in the literature. Here, the authors present a surgical technique for posterior callosotomy using a parietooccipital interhemispheric approach with a semi-prone park-bench position as a second surgery. Although this procedure requires an additional skin incision in the parietooccipital region, it makes the 2-stage callosotomy safer and easier to perform because of reduced intracranial adhesion, less bleeding, and an easier approach to the splenium of the corpus callosum.

Efficiency, safety, and patient preference of switching from dorzolamide 1%/timolol 0.5% to brinzolamide 1%/timolol 0.5% while maintaining the prostaglandin F2α analog.

BACKGROUND: We investigated the efficiency, safety and patient preference of switching from dorzolamide 1%/timolol 0.5% to brinzolamide 1%/timolol 0.5% while maintaining the prostaglandin F2α analog. METHODS: We initially enrolled 44 eyes from 44 primary open angle glaucoma patients, and a total of 42 patients completed the study. All patients were under treatment with various prostaglandin F2α analogs and dorzolamide 1%/timolol 0.5%. While maintaining the prostaglandin F2α analog, dorzolamide 1%/timolol 0.5% was switched to brinzolamide 1%/timolol 0.5%. Conjunctival hyperemia, superficial punctate keratopathy, and intraocular pressure (IOP) were evaluated at baseline and at 4, 12, and 24 weeks. Adverse events and patient preferences, measured using a questionnaire at study initiation and at 24 weeks, were also noted. RESULTS: The IOP was 17.7±1.7, 16.8±2.6, 16.7±2.2, and 16.7±2.4 mmHg at baseline and at 4, 12, and 24 weeks, respectively, with no significant differences in IOP values at any time point (P=0.117, one-way analysis of variance). In addition, no significant differences were found in the incidence of conjunctival hyperemia or SPK score at any time point (all P>0.5, by Kruskal-Wallis test). Based on the evaluation of side effects using the questionnaire, stinging/burning was less common (P=0.042), while blurred vision was more common (P=0.003), after switching to brinzolamide 1%/timolol 0.5%. Regarding patient preferences, 13 patients (31%) preferred dorzolamide 1%/timolol 0.5%, 12 patients (29%) preferred brinzolamide 1%/timolol 0.5%, and 17 patients (40%) preferred neither. CONCLUSION: When switching from dorzolamide 1%/timolol 0.5% to brinzolamide 1%/timolol 0.5%, the IOP values and incidence of superficial punctate keratopathy and conjunctival hyperemia were sustained throughout the 24-week observation period, and the patient preferences were similar for the two regimens. However, differences were observed in the ocular sensations of stinging/burning with dorzolamide 1%/timolol 0.5% and blurred vision with brinzolamide 1%/timolol 0.5%.

Cross-sectional study of the association between a deepening of the upper eyelid sulcus-like appearance and wide-open eyes.

BACKGROUND: Deepening of the upper eyelid sulcus (DUES) is a common complication of prostaglandin F2α analog treatment, which causes cosmetic problems. However, identifying this condition using photographs is difficult due to such problems as the camera flash effects, blepharoptosis or wide-open eyes. PURPOSE: We investigated the association between a DUES-like appearance and wide-open eyes regarding the presence of wide-open eyes as a cause for overestimating the incidence of DUES. SUBJECTS AND METHODS: One eye and the forehead in 100 subjects (31 younger subjects, 30 older subjects and 39 patients with blepharoptosis) were evaluated in the present study. Digital photographs of the subjects with natural open and wide-open eyes were taken with a flash. Five signs (a puffy eyelid, the presence/absence of the upper eyelid sulcus (UES), wrinkles on the forehead with natural open eyes and an increase in the number of wrinkles on the forehead and a DUES-like appearance with wide-open eyes) were judged to be negative or positive by three independent observers. Univariate and multivariate logistic regression analyses were performed to determine the independent predictor(s) of a DUES-like appearance with wide-open eyes. RESULTS: Fourteen subjects (four young, three old and seven subjects with blepharoptosis) were judged to have a DUES-like appearance with wide-open eyes (14%). The only predictive factor was the presence of UES in the patients with natural open eyes (odds ratio = 17.244, 95% confidence interval: 3.447-86.270, P<0.001). Among the 12 UES-positive subjects, six (50%) exhibited a DUES-like appearance with wide-open eyes. CONCLUSIONS: The presence of wide-open eyes can thus cause a DUES-like appearance. Blepharoptosis itself is not a predictive factor; however, care should be taken not to overestimate the incidence of DUES, especially in patients with UES with natural open eyes, as a DUES-like appearance can be caused by wide-open eyes, even in treatment-naïve patients. TRIAL REGISTRATION: UMIN000010500.

Formation of quaternary carbon center with a trifluoromethyl group using a Pd-catalyzed allylation reaction.

Synthesis of compounds with quaternary carbons is one of the most attractive reactions in the synthetic chemistry. However, there are only a few reports on synthesis of the compounds with a fluoroalkyl group at a quaternary carbon center. Recently, we reported the synthesis of alpha-trifluoromethylated ketones by the reaction of alpha,beta-unsaturated ketones with CF(3)-I using a Rh catalyst. When the alpha-trifluoromethylated ketones and allyl carbonates were treated with a Pd catalyst, the allylation reaction proceeded smoothly at the trifluoromethylated carbon to give the desired compounds with a trifluoromethylated quaternary carbon center in good to excellent yields.