A Clinical Trial Evaluating the Efficacy of Deep Learning-Based Facial Recognition for Patient Identification in Diverse Hospital Settings.

BACKGROUND: Facial recognition systems utilizing deep learning techniques can improve the accuracy of facial recognition technology. However, it remains unclear whether these systems should be available for patient identification in a hospital setting. METHODS: We evaluated a facial recognition system using deep learning and the built-in camera of an iPad to identify patients. We tested the system under different conditions to assess its authentication scores (AS) and determine its efficacy. Our evaluation included 100 patients in four postures: sitting, supine, and lateral positions, with and without masks, and under nighttime sleeping conditions. RESULTS: Our results show that the unmasked certification rate of 99.7% was significantly higher than the masked rate of 90.8% (p < 0.0001). In addition, we found that the authentication rate exceeded 99% even during nighttime sleeping. Furthermore, the facial recognition system was safe and acceptable for patient identification within a hospital environment. Even for patients wearing masks, we achieved a 100% success rate for authentication regardless of illumination if they were sitting with their eyes open. CONCLUSIONS: This is the first systematical study to evaluate facial recognition among hospitalized patients under different situations. The facial recognition system using deep learning for patient identification shows promising results, proving its safety and acceptability, especially in hospital settings where accurate patient identification is crucial.

Faricimab for Diabetic Macular Edema in Patients Refractory to Ranibizumab or Aflibercept.

Background and Objectives: Faricimab is the first intravitreal injection of vascular endothelial growth factor-A and angiopoietin-2 bispecific monoclonal antibody. Here, we evaluate the functional and anatomical outcomes of faricimab treatment in patients with diabetic macular edema (DME) that was refractory to ranibizumab or aflibercept. Materials and Methods: We performed a retrospective, observational, consecutive-case study of patients who had DME that was refractory to treatment with ranibizumab or aflibercept and were treated with faricimab between July 2022 and January 2023 under a pro re nata regimen. All the participants were followed for ≥4 months after the initiation of faricimab. The primary outcome was a recurrence interval of ≥12 weeks, and the secondary outcomes were the changes in best-corrected visual acuity (BCVA) and central macular thickness (CMT). Results: We analyzed 18 eyes of 18 patients. The mean recurrence interval of previous anti-VEGF injection was 5.8 ± 2.5 weeks, which was significantly extended to 10.8 ± 4.9 weeks (p = 0.0005) by the switch to faricimab. Eight patients (44.4%) achieved a recurrence interval of ≥12 weeks. A history of subtenon injection of triamcinolone acetonide (p = 0.0034) and the presence of disorganization of the retinal inner layers (p = 0.0326) were found to be significantly associated with a recurrence interval of <12 weeks. The mean BCVAs were 0.23 ± 0.28 logMAR and 0.19 ± 0.23 logMAR, and the mean CMTs were 473.8 ± 222.0 µm and 381.3 ± 219.4 µm at baseline and 4 months, respectively, but these changes were not statistically significant. None of the patients experienced serious adverse events. Conclusions: Faricimab may extend the treatment interval for patients with DME that is refractory to ranibizumab or aflibercept. DME previously treated with the subtenon injection of triamcinolone acetonide or associated with disorganization of the retinal inner layers may be less likely to be associated with a longer recurrence interval after switching to faricimab.

DRAINAGE RETINOTOMY IS A RISK FACTOR FOR SURGICAL FAILURE AFTER PARS PLANA VITRECTOMY IN PATIENTS WITH PRIMARY UNCOMPLICATED RHEGMATOGENOUS RETINAL DETACHMENT.

PURPOSE: To identify risk factors for recurrent retinal detachment after uncomplicated pars plana vitrectomy in patients with primary rhegmatogenous retinal detachment (RRD). METHODS: This single-center retrospective study included patients with primary RRD who underwent 23-gauge and 25-gauge pars plana vitrectomy at Hiroshima University Hospital between January 2016 and May 2021. All patients had ≥3 months of follow-up. Patients were excluded if they had preoperative proliferative vitreoretinopathy worse than Grade C1; giant retinal tears; tractional, exudative, or traumatic retinal detachment; or the use of perfluorocarbon liquid. Factors that influenced RRD treatment outcome and postoperative complications were evaluated. RESULTS: We analyzed 519 eyes of 509 patients who underwent pars plana vitrectomy for primary RRD. The primary and final success rates were 93.8% and 99.8%, respectively. Drainage retinotomy was a risk factor for surgical failure in both multivariate analysis (odds ratio 2.36, 95% confidence interval 1.08-5.15, P = 0.0314) and a propensity score-matching analysis (odds ratio 3.20, 95% confidence interval 1.14-9.04, P = 0.0277). Postoperative epiretinal membrane was associated with drainage retinotomy in multivariate analysis (odds ratio 1.93, 95% confidence interval 1.04-3.57, P = 0.0358). CONCLUSION: The avoidance of drainage retinotomy during small-gauge pars plana vitrectomy in patients with RRD may lead to better surgical success and less frequent epiretinal membrane formation.