International Journal of Innovative Research in Advanced Engineering (IJIRAE) ISSN: 2349-2163
August 2022, Volume 9, Issue 8 https:/ / www.ijirae.com/ archives
_____________________________________________________________________________________________________________________________________
IJIRAE:: © 2014-22, AM Publications. All rights reserved. https:/ / doi.org/ 10.26562/ ijirae Page -306
AN EXPLAI NABLE AI MODEL FOR DI ABETI C
RETINOPATHY DETECTION
Deepa Tejashwini M S
UG student, Department of CSE
Vemana Institute of Technology, Bangalore
deepatejashwini.04@gmail.com
Maitri S Gaonkar
UG student, Department of CSE
Vemana Institute of Technology, Bangalore
maitrig63@gmail.com
Lakshmi H D
UG student, Department of CSE
Vemana Institute of Technology, Bangalore
lakshmisanju6122000@gmail.com
A Rosline Mary
Assistant Professor, Department of CSE
Vemana Institute of Technology, Bangalore
roslinemary.a@vemanait.edu.in
Madhuri JM
UG student, Department of CSE
Vemana Institute of Technology, Bangalore
madhuri.jcm@gmail.com
Publication History
Manuscript Reference No: IJIRAE/ RS/ Vol.09/ Issue08/ SPAUAE10107
Research Article | Open Access | Peer-review: Double-blind Peer-reviewed
Article ID: IJIRAE/ RS/ Vol.09/ Issue08/ SPAUAE10108
Received Date: 12, July 2022 | Accepted Date: 25, July 2022 | Available Online: 12, August 2022
Volume 2022 | Article ID SPAUE10107 https:/ / www.ijirae.com/ volumes/ Vol9/ iss-08/ 28.SPAUAE10107.pdf
Article Citation: Deepa,Maitri,Lakshmi,Mary,Madhuri(2022).An Explainable AI Model for Diabetic Retionopathy
Detection. International Journal of Innovative Research in Advanced Engineering (Vol. 9, Issue 8, pp. 306–311). AM
Publications, India. doi: https:/ / doi.org/ 10.26562/ ijirae.2022.v0908.28 BibTeX key
Academic Editor-Chief: Dr.A.Arul Lawrence Selvakumar
Copyright: ©2022 This is an open access article distributed under the terms of the Creative Commons Attribution
License; Which Permits unrestricted use, distribution, and reproduction in any medium, provided the original author
and source are credited.
Abstract: Diabetes is the most common long-term condition that affects people of all ages due to inadequate insulin
production. The appearance of black spots for millennia, interpreting eye pictures, and detecting diabetic retinopathy in
its early stages has been a big challenge. The Explainable AI method is to explain the deep learning model that is
understandable by humans and trusts the result. This is especially important in safety critical domains like healthcare
or security, which replaces manual processes and understanding of the models function by non-technical domain
skilled person. Explainable AI is used to describe an AI model, its expected impact and potential biases. It helps
characterize model accuracy, fairness, transparency and outcomes in AI-powered decision making. Explainable AI is
crucial for an organization in building trust and confidence when putting AI models into production. AI explains ability
also helps an organization adopt a responsible approach to AI development. Specifically, the back propagation step is
responsible for updating the weights based on its error function. SHAP or SHAPley Additive explanations are a
visualization tool that can be used for making a machine learning model more explainable by visualizing its output. It
can be used for explaining the prediction of any model by computing the contribution of each feature to the prediction.
Keywords: Diabetic Retinopathy, CNN, Explainable AI, SHAP, Microvascular Complication.
I. INTRODUCTION
Explainable Artificial Intelligence (XAI) is a set of safety procedures and techniques that enable human users to
recognize and believe the outcomes and output generated by a machine learning algorithm. One of the most common
causes of blindness is Diabetic Retinopathy (DR). The retinal blood vessels of a diabetic patient are mutilated by DR.
There are two forms of diabetic retinopathy: non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic
retinopathy (PDR). The early tiers' DR is known as NPDR, which is also classified into Mild, Moderate, Severe, and PDR
levels. Swelling and rupture of blood vessels within the retina, as well as abnormal scratches on the retina, are all
symptoms of DR. Diabetic retinopathy is the main motive of visible impairment and keeps to developing Disability and
blindness. A premature survey is critical for reducing the progression of DR and, as a result, preventing the occurrence
of blindness.