Statistical Unsupervised Learning of Visual Fields in Neuro-Ophthalmology Clinical Trials (IIHTT, ONTT) (PI: Mark Kupersmith; subcontract PI: Tobias Elze)
Grant Number: R21 EY032522
Grant Duration: July 1, 2021 – June 30, 2023
Source: National Institutes of Health
Description: We will develop models of vision loss evolution over time for neuro-ophthalmological diseases depending on disease type and treatment.
Optimal Patient Recruitment Algorithms for Glaucoma Clinical Trials (PI: Tobias Elze)
Grant Duration: March 1, 2021 – February 28, 2022
Source: Genentech Inc.
Description: We will develop algorithms to optimally recruit glaucoma patients for clinical trials based on their expected individual disease progression.
Evaluation of Novel Endpoints for Glaucoma Clinical Trials (PI: David Friedman; subcontract PI: Tobias Elze)
Grant Duration: March 1, 2021 – February 28, 2022
Source: Genentech Inc.
Description: We investigate functional vision assessments currently not applied in clinical practice as an improvement or complement of clinical glaucoma testing.
STTR Phase I: A Pair of Linked Cartographic Maps of our Brain Derived from Clinical Glaucoma Data (PI: Dr. Gautam Thor and Dr. Tobias Elze)
Grant Number: STTR 2025322
Grant Duration: December 15, 2020 – Dec 31, 2021
Source: National Science Foundation
Description: Glaucoma is a major cause of irreversible blindness but can be addressed with early detection, but existing tests can be tiring and difficult and require specialized equipment. We develop an entirely novel approach to glaucomatous vision testing which is kinetic, binocular and based on neuroscientific models.
Personalizing Glaucoma Diagnosis by Disease Specific Patterns (PI: Dr. Tobias Elze)
Grant Number: NIH R01 EY030575
Grant Duration: September 30, 2019 – July 31, 2024
Source: National Institutes of Health
Description: Glaucoma is an ocular disease accompanied by vision loss which may progress over time up to total blindness, but the assessment of glaucomatous vision loss is noisy, and it is often hard for clinical practitioners to decide whether changes over time reflect true changes of functional vision or are the result of normal measurement variations or artifacts. This project contributes directly and immediately to public health by exploring the impact of individual anatomical parameters on the spatial patterns of glaucomatous vision loss in order to improve the diagnosis of vision loss and of its progression. Main objective of the project is the development of new quantitative diagnostic indices, implemented as publicly available software.
Associating Retinal Nerve Fiber Layer Thickness with Glucose Metabolism and Diabetic Retinopathy (PI: Dr. Tobias Elze)
Grant Number: NIH R21 EY030631
Grant Duration: September 01, 2019 – August 31, 2022
Source: National Institutes of Health
Description: Parameters related to glucose metabolism obtained by blood tests are clinically used to diagnose diabetes, a metabolic disease that affects over 300 million people worldwide and that can be accompanied by serious health complications, such as diabetic retinopathy (DR), the leading cause of blindness within the age group between 20 and 64 years. Decreased levels of blood glucose tolerance have been associated with retinal nerve fiber layer (RNFL) thinning, but these results were based on comparisons between small populations of diagnosed diabetics and healthy controls, and RNFL was typically represented by coarse summary parameters which neglect retinal anatomy. This project contributes directly and immediately to public health by exploring the relationship between spatial patterns of RNFL thickness, present and future DR severity, and diagnostic blood test results in 9,261 participants of a population based study, with the final goal to establish and quantify RNFL thickness as an alternative manifestation of diabetes that complements diagnostic blood tests and lays the foundations for the development of novel and more accurate disease progression monitoring or the prediction of DR onset.
A Hybrid Artificial Intelligence Framework for Glaucoma Monitoring (PI: Dr. Siamak Yousefi and Dr. Tobias Elze)
Grant Number: NIH R21 EY030142
Grant Duration: April 01, 2019 – March 31, 2021
Source: National Institutes of Health
Description: Leveraging big data in eye care is challenging. This study uses big functional and structural glaucoma data and develops hybrid machine learning models to identify glaucoma progression and its monitoring. Results could offer substantial improvements in prognosis of glaucoma and may provide surrogate endpoints for use in glaucoma clinical trials.
Relationship between Glaucoma and the Three-Dimensional Optic Nerve Head Related Structure (PI: Dr. Mengyu Wang)
Grant Number: K99/R00 EY028631
Grant Duration: Feb 01, 2019 – Jan 31, 2021
Source: National Institutes of Health
Description: This project will study the relationship between the three-dimensional (3D) optic nerve head (ONH) related structure and glaucoma. Our study will advance the current understanding of glaucoma pathogenesis and improve glaucoma diagnosis by gaining new insights into the structure-function relationships in glaucoma and establishing ocular anatomy specific norms of retinal nerve fiber layer profiles. Our research has high clinical relevance and can be potentially translated into clinical practice for better glaucoma diagnosis, monitoring and treatment.
Retinal Biomarkers for Cognitive Performance (PI: Dr. Tobias Elze)
Grant Duration: July 1, 2018 – June 30, 2019
Source: Alice Adler Fellowship
Description: This pilot grant supports a project to determine the precise and location specific association between retinal nerve fiber layer thickness and human cognitive performance. The decline of cognitive function is an important diagnostic marker for neurodegenerative impairments like Alzheimer's disease. Therefore, this project might contribute to an earlier diagnosis of neurodegenerative diseases by ocular imaging.
Computational Investigation of Glaucoma Progression (PI: Dr. Tobias Elze)
Grant Number: G2017111
Grant Duration: July 1, 2017 – June 30, 2020
Source: BrightFocus
Description: In this project, we identify defect classes of glaucomatous visual field loss progression and their relationship to retinal structure. We apply machine learning techniques to a data set of over 480,000 visual fields to identify representative patterns of vision loss progression and relate them to optical coherence tomography measurements and fundus images.