A promising approach with confidence level aggregation operators based on single-valued neutrosophic rough sets

Among the most prevalent and serious retinal illnesses are glaucoma, diabetic retinopathy, hypertension caused by diabetes, cataracts, and age-related macular degeneration. If these disorders are not identified at an early stage, permanent eyesight loss ensues. Numerous anomalies in the retina, including microaneurysms, neovascularization, hemorrhages, soft exudates or cotton wool patches, and macular edema, serve as illustrations. Ophthalmologists employ automated technologies that analyze ophthalmic imaging modalities to quickly screen for and diagnose these illnesses. Due to the complexity of numerous diseases that have overlapping symptoms, accurate disease diagnosis has become more difficult in modern times. When it comes to medical diagnosis, this complexity presents a huge challenge for specialists working in health departments. Many academics and researchers are actively attempting to create novel approaches and solutions to deal with the difficulties in medical diagnostics. The goal of this research initiative is to develop cutting-edge techniques that can help professionals make more accurate disease diagnoses. The present work introduces the notion of confidence level for neutrosophic average and aggregation operators, which contrasts with neutrosophic rough average and geometric aggregation operators, which do not take into account the experts' familiarity with the objects being examined during the initial assessment. A more sophisticated structure of neutrosophic rough sets is used to calculate the confidence level, allowing for a more thorough review procedure. The fundamental traits of the suggested operators are also covered in the paper.

Automated summary

Retinal diseases, such as glaucoma, diabetic retinopathy, and cataracts, can cause permanent vision loss if not diagnosed early. The complexity and overlapping symptoms of these diseases present challenges for accurate medical diagnosis. Researchers are working on developing innovative approaches to improve disease diagnostics.