Implementing and evaluating a fully functional AI-enabled model for chronic eye disease screening in a real clinical environment.

BACKGROUND: Artificial intelligence (AI) has the potential to increase the affordability and accessibility of eye disease screening, especially with the recent approval of AI-based diabetic retinopathy (DR) screening programs in several countries. METHODS: This study investigated the performance, feasibility, and user experience of a seamless hardware and software solution for screening chronic eye diseases in a real-world clinical environment in Germany. The solution integrated AI grading for DR, age-related macular degeneration (AMD), and glaucoma, along with specialist auditing and patient referral decision. The study comprised several components: (1) evaluating the entire system solution from recruitment to eye image capture and AI grading for DR, AMD, and glaucoma; (2) comparing specialist's grading results with AI grading results; (3) gathering user feedback on the solution. RESULTS: A total of 231 patients were recruited, and their consent forms were obtained. The sensitivity, specificity, and area under the curve for DR grading were 100.00%, 80.10%, and 90.00%, respectively. For AMD grading, the values were 90.91%, 78.79%, and 85.00%, and for glaucoma grading, the values were 93.26%, 76.76%, and 85.00%. The analysis of all false positive cases across the three diseases and their comparison with the final referral decisions revealed that only 17 patients were falsely referred among the 231 patients. The efficacy analysis of the system demonstrated the effectiveness of the AI grading process in the study's testing environment. Clinical staff involved in using the system provided positive feedback on the disease screening process, particularly praising the seamless workflow from patient registration to image transmission and obtaining the final result. Results from a questionnaire completed by 12 participants indicated that most found the system easy, quick, and highly satisfactory. The study also revealed room for improvement in the AMD model, suggesting the need to enhance its training data. Furthermore, the performance of the glaucoma model grading could be improved by incorporating additional measures such as intraocular pressure. CONCLUSIONS: The implementation of the AI-based approach for screening three chronic eye diseases proved effective in real-world settings, earning positive feedback on the usability of the integrated platform from both the screening staff and auditors. The auditing function has proven valuable for obtaining efficient second opinions from experts, pointing to its potential for enhancing remote screening capabilities. TRIAL REGISTRATION: Institutional Review Board of the Hamburg Medical Chamber (Ethik-Kommission der Ärztekammer Hamburg): 2021-10574-BO-ff.

Pupillotonia after endolaser retinopexy during vitrectomy for retinal detachment: a prospective cohort study comparing circumferential and focal retinopexy.

PURPOSE: To determine differences in postoperative pupil diameter in eyes that undergo pars plana vitrectomy (PPV) for rhegmatogenous retinal detachment (RRD) with endolaser retinopexy (ELR), comparing 360° vs focal ELR. METHODS: Patients with uncomplicated RRD who underwent PPV were prospectively analysed regarding the postoperative pupil diameter difference (PDD) between the affected eye and the partner eye. Group 1 underwent 360° ELR and group 2 received focal ELR. Postoperative vision and complications, including redetachment rate, macular oedema and epiretinal membrane formation, were also compared. RESULTS: A total of 72 patients, 42 in group 1 and 30 in group 2, were analysed. PDD, as observed at 6 weeks, was significantly greater than the preoperative values in both groups 1 and 2. It increased by a mean of 1±1.11 mm in group 1 and by 0.5±0.78 in group 2. This initial increase in PDD receded over time, but remained statistically significant in both groups, even at 6 months. The top 20% of patients with the largest PDD change comprised 13 out of 15 eyes from group 1, which was a statistically significant overrepresentation (p=0.0435). CONCLUSIONS: Moderate pupillotonia was induced post-ELR in vitrectomy and correlated to the extent of ELR. The pupillotonia effect of ELR was significantly less marked in pseudophakic eyes.

Continuous Intracorneal Ring Implantation in Keratoconus: Efficacy, Predictive Factors, and Complications.

Purpose: To examine the clinical outcomes, predictors of visual improvement and complications of continuous intracorneal ring (ICCR) implantation in patients with keratoconus and confirmed contact-lens intolerance (CLI). Methods: This nonrandomized, multi-centric, retrospective cohort study examined visual, keratometric and clinical outcomes evaluated after a minimum follow-up of 2 months. Among the inclusion criteria for the standard treatment group (STG) were corrected distance visual acuity (CDVA) <20/25 Snellen, no central corneal scars, minimum corneal thickness >350µm, and central mean keratometry reading (meanK) <55 diopters. All other eyes were classified as non-standard treatment group. Results: A total of 118 eyes of 118 patients with aged 32 ± 11 years were included in this study. At a median follow-up of 161 days (interquartile range: 111-372 days) ICCR implantation improved the CDVA from a mean of 0.38 to 0.15 logMAR (p<0.0001). Our correlation analysis showed lower preoperative CDVA to be the single best predictor of CDVA improvement, with eyes of a CDVA of 20/80 or lower improving by 4.3 ± 2.0 lines on average. Eyes with a meanK >55 diopters gained 9.04±4.83 lines in UDVA and 2.86±3.09 lines in CDVA. However, postoperatively these eyes had a CDVA of 0.32±0.21 logMAR which is significantly inferior to the STG outcome (p=0.001372). Fifteen eyes (12.7%) had to undergo a ring exchange procedure because of refractive under- (9 eyes) or overcorrection (6 eyes). Two eyes (1.7%) experienced medical complications. Conclusion: This study confirms the inclusion criteria of ICCR implantation in KC eyes with CDVA <20/25 and CLI. Particularly in eyes with a preoperative CDVA <20/80 and a meanK <55 diopters, ICCR implantation should be considered due to its reversibility and low rates of serious complications. The main challenge remains in the low predictability of the magnitude of this improvement in eyes with CDVA >20/30.