Objective evaluation of lens clarity after the intravitreal injection of sustained-release dexamethasone implant

Objective evaluation of changes in lens clarity after repeated injections of ranibizumab in patients with neovascular age-related macular degeneration

PURPOSE

To objectively evaluate changes in lens densitometry in eyes with neovascular age-related macular degeneration (n-AMD) treated with repeated intravitreal ranibizumab injections during a 12-month period and to compare the results with those in untreated healthy fellow eyes and healthy control eyes.

METHODS

In this prospective study, the 36 treated eyes and the 37 untreated fellow eyes of 38 patients with n-AMD and the 32 control eyes of 32 healthy individuals were analyzed. Lens densitometry was evaluated using the Scheimpflug imaging. All data in both groups regarding lens densitometry were recorded at baseline and 12 months.

RESULTS

The mean densitometry of zone 1 in the treated eyes of patients had increased significantly at 12 months compared with the baseline (baseline: 9.3 ± 1.5, 12 months: 11.9 ± 1.7, p = .004) and was significantly greater than those measurements in the fellow eyes (9.8 ± 1.6 p = .02) and control eyes (9.6 ± 1.9, p = .01) at 12 months as well. There were no significant differences in terms of densitometry values between the fellow and control eyes at baseline and 12 months (for all, p > .05).

CONCLUSIONS

Our results objectively demonstrate early nuclear lens density changes using with Scheimpflug images in eyes with n-AMD that were treated with repeated ranibizumab injections for 12 months.

Densitometric analysis of cornea in patients with neovascular age-related macular degeneration after intravitreal aflibercept loading dose

Purpose:

To evaluate the anatomic changes in the cornea and anterior segment following intravitreal aflibercept loading dose for neovascular age-related macular degeneration.

Methods:

The study included 40 eyes of 40 patients with neovascular age-related macular degeneration. Each patient underwent a loading dose of one injection per month for three consecutive doses of aflibercept (0.05 ml/2 mg). Before and after the loading dose, a record was made for each patient of corneal topography, anterior segment, corneal densitometry, and lens densitometry parameters with the Pentacam HR and specular microscopy parameters with a non-contact specular microscope. The data before and after the aflibercept loading dose were compared.

Results:

Corneal densitometry parameters in the 0- to 2-mm and 2- to 6-mm concentric zones of the posterior layer were significantly higher after the loading dose compared with baseline (p = 0.03, p = 0.04, respectively). Corneal densitometry parameters of the anterior, central, and total corneal layer in the 10- to 12-mm concentric zone were also significantly higher after the loading dose compared with baseline (p = 0.009, p = 0.02, and p = 0.007, respectively). No significant changes were determined in respect of corneal topography, anterior segment, lens densitometry, and specular microscopy parameters (p > 0.05 for all).

Conclusion:

The aflibercept loading dose caused slightly increased densitometric values in some corneal regions while it did not affect the corneal topography, anterior segment, lens densitometry, and specular microscopy parameters.

A Novel Machine Learning Algorithm to Automatically Predict Visual Outcomes in Intravitreal Ranibizumab-Treated Patients with Diabetic Macular Edema

Purpose: Artificial neural networks (ANNs) are one type of artificial intelligence. Here, we use an ANN-based machine learning algorithm to automatically predict visual outcomes after ranibizumab treatment in diabetic macular edema. Methods: Patient data were used to optimize ANNs for regression calculation. The target was established as the final visual acuity at 52, 78, or 104 weeks. The input baseline variables were sex, age, diabetes type or condition, systemic diseases, eye status and treatment time tables. Three groups were randomly devised to build, test and demonstrate the accuracy of the algorithms. Results: At 52, 78 and 104 weeks, 512, 483 and 464 eyes were included, respectively. For the training group, testing group and validation group, the respective correlation coefficients were 0.75, 0.77 and 0.70 (52 weeks); 0.79, 0.80 and 0.55 (78 weeks); and 0.83, 0.47 and 0.81 (104 weeks), while the mean standard errors of final visual acuity were 6.50, 6.11 and 6.40 (52 weeks); 5.91, 5.83 and 7.59; (78 weeks); and 5.39, 8.70 and 6.81 (104 weeks). Conclusions: Machine learning had good correlation coefficients for predicating prognosis with ranibizumab with just baseline characteristics. These models could be the useful clinical tools for prediction of success of the treatments.