Diabetes and heart disease identification using biomedical iris data

Abstract

The World Health Organization (WHO) report shows that Heart disease is the major
cause of death all over the world i.e. nearly 21.2 million people die every year directly or indi-
rectly from Cardiovascular (Heart) diseases estimated 32% of all deaths worldwide. Whereas,
Diabetes is at the ninth position for the death all over the world i.e. nearly 3.7 million people
die every year from diabetes estimated 6.61% of all deaths worldwide. The Heart and Pancreas
organ play a most important role in human being. The blood flows in all parts of the body
through heart. The function of pancreas is to regulate maintain the insulin levels that is respon-
sible for diabetes. The detection of heart disease and diabetes takes too much time and very
costly process. In our research, we develop a Heart Disease and Diabetes Identification System
based on Iris Healthcare Kiosk. We proposed a desktop system application that detects these
diseases through the Iris. The process starts by taking the left Eye photograph of the patient’s
through Eyeronec (company name) camera and perform intermediates operations of target
cropping, preprocessing, autocropping (through integral projection and removing sclera),
heart regions of interest (ROI) measuring, pancreatic measuring, extracting the feature and fi-
nally classify in the result. The classification result shows that 83% tests are successful, 11%
tests are scant whereas 6% tests became fail. The operation is performed on 32 different train-
ing digital data sets and final result is labelled as normal or abnormal. The result shows that ac-
curacy of our proposed system in heart disease and diabetes are 86.36% and 90.91% respec-
tively.

Conclusion


In this research, we propose a model to detect two diseases (Heart disease and Diabetes) based on iris
high definition images through our health based model. Initially, the training set of digital data is cre-
ated by taking the Iris image through EyeRonec Iris Camera. Finally, the result is classified into two
different categories namely Normal and Abnormal category based on the threshold values. The prede-
fined threshold value for the white ratio is 0.681 in case of Diabetes the black is 0.971 in case of Heart
disease. The patient is Abnormal if his/her threshold values exceeds than 0.681 and 0.971 in case of
white and black ratio respectively. The result shows that proposed system accuracy is 86.36% and
90.91% in Heart Disease and Diabetes respectively. Sometimes, final stage result is not correct or fails
due to poor lighting and camera shooting position.

Sanjeev Kumar Punia, Manoj Kumar1, Surendra Kumar Pathak, Xiaochun
Cheng
Galgotias University, Greater Noida – INDIA

Download full abstract: https://iridology-research.com/pdf/49fe3f284abc4b638a1dcab0cbbd3bb0_fKgaGpn.pdf