Ongoing studies

SN-IIT Madras | Clinical study to evaluate the performance of a driving simulator in Real-world driving environments

The objective of this study is to investigate the effects of visual factors on driving performance using a driving simulator in normal subjects, patients with DME and patients with Pan Retinal Photocoagulation.

RetinaRisk mathematical algorithm for STDR risk detection

The objective of this study is to deploy the RetinaRisk model among a carefully chosen group of "Champion Users" for the purpose of conducting pilot testing and acquiring pertinent insights to ensure the algorithm's readiness prior to its launch in India.

Association of OCT biomarkers and visual impairment in patients with Diabetic Macular Oedema with Vitreomacular Adhesion

This study aims to assess treatment response and predict therapy outcomes during initial visits, reducing the financial burden by optimizing resource allocation and enhancing treatment efficiency.

Artificial Intelligence for Affordable Screening and Prediction of Diabetic Retinopathy using Big data Framework

This project aims to develop an affordable AI tool for screening and predicting diabetic retinopathy (DR) using a big data framework. It is being funded by the Department of Biotechnology, Ministry of Science and Technology, and is a collaboration between five institutions. The goal is to provide a reliable and accessible tool to improve DR diagnosis and treatment outcomes.

ZEISS - DME and DKD model

A proposed DME algorithm is envisioned as a web-based standalone software that will be accessible on computers with internet connections. It is designed to utilize advanced machine learning techniques, specifically deep neural networks (DNNs), to predict the potential reduction in central subfield thickness (CST) for patients diagnosed with Diabetic Macular Edema (DME). The primary aim of this algorithm is to provide healthcare professionals with valuable insights into disease management strategies before administering Anti-VEGF injections.

AI in predicting retinal disease (WIRES- review article)

This review examines studies on the use of Artificial Intelligence (AI) or Machine Learning (ML) to detect systemic diseases or their risk factors through retinal imaging.

Real-World Outcomes of Non-Centre-Involving Diabetic Macular Edema Treated with Macular Laser Versus Observation

The aim of this study is to investigate the rate of progression to centre-involving diabetic macular oedema (CI-DME) over a two-year period in patients with non-centre involving DME (NCI-DME) who were managed either by macular laser or observation.

Natural Course of Non-Centre Involving Diabetic Macular Edema Progression in Patients Under Initial Observation

The objective of this report is to describe the natural progression of non-center involving diabetic macular edema (NCIDME) to center involving diabetic macular edema (CIDME), as well as the risk factors associated with this progression.

Gait analysis in participants with diabetic retinopathy, retinopathy and combined influence participants

This study analyzes gait in participants with diabetic neuropathy and retinopathy, aiming to assess their combined impact on mobility. It examines gait characteristics in individuals with these conditions and investigates how they affect overall mobility. By understanding the relationship between diabetic neuropathy, retinopathy, and their influence on gait, the study provides valuable insights into their collective effects on mobility.

Diopsys ERG - Normative data for Indian population

This study establishes reference values for Diopsys NOVA PERG, Fixed Luminance, and Multi-Luminance ERG parameters in the Indian population, enabling standardized evaluation and accurate interpretation of these tests in clinical settings, improving understanding and normative values.

Quantitative analysis of response to therapy on OCT images in neovascular AMD (nAMD) using machine learning

This study aims to assess treatment response and predict therapy outcomes during initial visits, reducing the financial burden by optimizing resource allocation and enhancing treatment efficiency.

Using resources from India to increase productivity to impact global health

This book chapter focuses on examining the resources needed to enhance global eye health productivity, with a specific emphasis on the influence of resources and practices in India. By exploring the various factors and strategies involved, the chapter aims to provide valuable insights into how optimizing resources and practices in India can contribute to the overall improvement of eye health on a global scale.

Appropriateness of DR recommendations obtained from a popular online Chat-based AI model

In collaboration with the Moorfields eye hospital, this research endeavors to assess the appropriateness of utilizing Chat GPT for addressing commonly asked questions related to Diabetic Retinopathy (DR) by subjecting it to evaluation by three expert judges. The objective is to determine whether Chat GPT is a suitable tool for effectively responding to patient inquiries regarding DR.

Vortex vein characteristics in pathological myopia

This research emphasizes the necessity to analyze the characteristics of vortex veins in highly myopic eyes. By investigating these characteristics, the study aims to enhance the understanding of vortex vein abnormalities and their potential implications in individuals with high myopia.

AI for affordable screening and prediction of DR in the framework of Big Data

This research aims to develop an AI-based model capable of screening and predicting diabetic retinopathy by utilizing annotated fundus and OCT images. The objective is to train the model to accurately identify signs of diabetic retinopathy, enabling early detection and intervention for improved patient outcomes.

Development and validation of AI based deep learning algorithm for the prediction of systemic and ocular abnormalities from retinal OCT and fundus images

This research aims to develop and validate a prediction model for identifying patients with intracranial hypertension. The objective is to create a robust model that can accurately identify individuals at risk of intracranial hypertension, enabling timely intervention and appropriate management strategies. The research seeks to enhance diagnostic accuracy and improve patient outcomes in relation to intracranial hypertension.

Ocular Biological senescence evaluation and science study

This collaborative research study, conducted in partnership with the University of Nebraska - USA, aims to investigate premature aging signs in individuals with HIV who are undergoing antiretroviral therapy (ART). The objective is to comprehensively assess and document the manifestations of premature aging in this specific population. By examining the effects of HIV and ART on the aging process, the study seeks to contribute to a deeper understanding of these dynamics and explore potential interventions to mitigate premature aging in HIV-infected individuals.

Artificial Intelligence for Affordable Screening and Prediction of Diabetic Retinopathy In the Framework of Big Data

Project 1, Phase 1, involved a qualitative study to identify barriers to retinal screening uptake in diabetic patients and propose strategies for minimizing these barriers. Interviews were conducted with patients, caregivers, and healthcare providers, along with a focus group discussion among providers.

In Phase 2, three interventions were implemented:

Short messaging services (SMS) to improve attendance rates in diabetic macular edema patients.
Diabetic retinopathy screening camp for individuals with long-standing diabetes to assess disease progression.
WhatsApp educational messages to enhance compliance in patients with Diabetic Macular Edema.

Project 2, named Smart India 2, consisted of a qualitative study aiming to explore the perceptions of patients with sight-threatening diabetic retinopathy (STDR) regarding their understanding of eye-related issues and the benefits and barriers to seeking care.

Project 3 focused on developing an advanced deep learning framework using artificial intelligence for affordable screening and prediction of diabetic retinopathy in fundus images, utilizing big data in the process.

Google Sites

Report abuse