Application of Machine Learning in enhancing the Scope of Optical Coherence Tomography for Glaucoma Diagnosis

An early diagnosis of glaucoma is essential to limit its unwanted progression. OCT is an important tool which provides a means of obtaining objective measurements of the optic nerve which is highly useful in the process of ascertaining the diagnosis of glaucoma. Optical coherence tomography (OCT) scan aided by machine learning (ML) algorithms can assist in this process. The purpose of this study is to review the scope of simultaneous utilization of OCT and ML in the diagnosis of glaucoma. This is a prospective study based on assessing the literature review of the subject under question. The incorporation of ML into OCT is certainly helpful in the predictive elimination of some of the patients based on the past database analysis. Nevertheless, it is important to remain prudent while comparing measurements to the normative database of OCT as the database itself may not be able to reflect the true optometric parameters of the patients being evaluated. Owing to a considerable risk of artifacts, it is always prudent to review an entire OCT scan for the purpose of isolating computational errors. Advanced ML algorithms are capable of acting upon the pre-defined criteria programmed into the system. With this assistance from artificial intelligence, OCT scans can safely diagnose the majority of people with a kind of disease.