Mariottoni Eduardo B

Jammal Alessandro A, Berchuck Samuel I, Mariottoni Eduardo B, Tanna Angelo P, Costa Vital P, Medeiros Felipe A

This study found lower mean and diastolic blood pressure, when adjusted for IOP, were linked to faster retinal nerve fiber layer loss in glaucoma, suggesting BP plays a role in progression.

Stagg Brian, Mariottoni Eduardo B, Berchuck Samuel, Jammal Alessandro, Elam Angela R, Hess Rachel et al.

This study found Black patients have greater visual field variability than White patients, especially with lower income, delaying glaucoma progression detection and potentially explaining outcome disparities.

Shigueoka Leonardo S, Mariottoni Eduardo B, Thompson Atalie C, Jammal Alessandro A, Costa Vital P, Medeiros Felipe A

Deep learning accurately predicted age from SD-OCT scans, revealing aging affects multiple posterior eye layers, not just the retinal nerve fiber layer, which could aid glaucoma assessment.

Lee Terry, Jammal Alessandro A, Mariottoni Eduardo B, Medeiros Felipe A

A deep learning algorithm using fundus photos to predict RNFL thickness effectively predicted glaucoma development in suspects, showing that longitudinal RNFL changes are key to identifying conversion risk.

Estrela Tais, Jammal Alessandro A, Mariottoni Eduardo B, Urata Carla N, Ogata Nara G, Berchuck Samuel I et al.

This study found that differences in corneal hysteresis between a glaucoma patient's eyes predicted asymmetric visual field loss, highlighting corneal hysteresis as a key risk factor for progression.

Medeiros Felipe A, Jammal Alessandro A, Mariottoni Eduardo B

Deep learning predicted RNFL thickness from fundus photos, correlating well with OCT. This offers a promising, accessible way to monitor progressive glaucomatous damage over time.

Jammal Alessandro A, Thompson Atalie C, Mariottoni Eduardo B, Estrela Tais, Shigueoka Leonardo S, Berchuck Samuel I et al.

This study found that better intraocular pressure control significantly slows retinal nerve fiber layer loss in glaucoma patients, emphasizing IOP management for preserving vision.

Jammal Alessandro A, Thompson Atalie C, Mariottoni Eduardo B, Urata Carla N, Estrela Tais, Berchuck Samuel I et al.

Studying glaucoma progression, researchers found many patients had slow rates, but a quarter showed moderate-to-fast structural (OCT) change. Both OCT and functional (SAP) tests are crucial for monitoring, with OCT detecting more early progression and SAP more advanced.

Thompson Atalie C, Jammal Alessandro A, Berchuck Samuel I, Mariottoni Eduardo B, Medeiros Felipe A

A segmentation-free deep learning algorithm for OCT glaucoma diagnosis outperformed conventional methods, particularly in early disease, offering improved diagnostic accuracy for clinicians.

Mariottoni Eduardo B, Datta Shounak, Dov David, Jammal Alessandro A, Berchuck Samuel I, Tavares Ivan M et al.

AI mapped glaucoma structure-function, predicting visual field loss from OCT nerve fiber layer damage. This improves understanding of how structural damage translates to functional loss.

Jammal Alessandro A, Thompson Atalie C, Mariottoni Eduardo B, Berchuck Samuel I, Urata Carla N, Estrela Tais et al.

A deep learning algorithm for glaucoma detection on fundus photos performed as well as or better than human graders, showing potential for efficient population screening.

Urata Carla N, Mariottoni Eduardo B, Jammal Alessandro A, Ogata Nara G, Thompson Atalie C, Berchuck Samuel I et al.

This study found long-term variability in glaucoma tests (SAP, SD-OCT) is significantly higher than short-term variability. This suggests current progression algorithms may overestimate glaucoma worsening by underestimating long-term variability.