Abstract:

The pseudoscience known as iridology makes the unsubstantiated claim that it can identify medical disorders by examining the iris, the colored portion of the eye. Iridology does not provide a reliable means of diagnosis, and there is no scientific proof to back up its claims. To find patterns that are connected to particular medical conditions, computerized iris analysis software may need to examine thousands of iris images. A method of iridology known as Computer-Aided Iridology (CAI) uses software to study the iris. CAI still is not a medically accepted diagnostic technique and is not any more trustworthy than conventional iridology. Applying technology in medical science had a great impact on diagnosing diseases. Decision making is the most critical task in computer-aided applications. Computer vision and deep learning make this task more accurate and are widely used in many applications, mainly in diagnosing diseases. The methodologies, data acquisition source,
and volume of data used for both training and testing in the pre-diagnosis of human organs utilizing iris patterns are thoroughly studied. Understanding its limitations allows researchers to concentrate on creating and evaluating improvements in technology that could boost its accuracy and usefulness.

Iridology has been considered as having no use for years and becomes effective when combined with technology. This study includes various technical factors used in iridology for the pre-diagnosing of diseases. Recognizing the limitations of iridology allows healthcare providers to avoid errors in diagnosis and prevent individuals from undergoing redundant procedures or therapies based solely on iridology assessments.

Conclusions

The footpath of iridology began 3000 years ago in various countries like China, India, and Egypt as reported in archaeological data. It is included as a substitute for diagnosing diseases that are scientifically not proven. Even though iridology is considered harmful and useless, many researchers have proven its accuracy in predicting a disease at between 80–97%. It depends on the quality of the data captured or the pre-processing mechanism applied to it and the methodology used to classify. It is quite a challenging and interesting task to determine if any disease can be pre-diagnosed with a scan.

Authors

Suja Alphonse, Ramachandran Venkatesan and Theena Jemima Jebaseeli

Division of Computer Science and Engineering, Karunya Institute of Technology and Sciences

Presented at the International Conference on Recent Advances on Science and Engineering, Dubai, United Arab Emirates, 4–5 October 2023

Download Abstract:   https://iridology-research.com/pdf/engproc-59-00009.pdf