Syndromic Management of Sexually Transmitted Diseases Using Dynamic Machine Learning and Path-Finding Algorithms

Abstract

Early detection and investigative procedures pertaining the discovery and treatment of Sexually Transmitted Diseases (STDs) requires sophisticated and expensive instruments, which ironically are unavailable to most in this country. Moreover, test results are hardly obtainable in a reasonable amount of time requiring one to return over and over again for regular checkup intervals, delaying the treatment and extending the period of infectivity developing risks of unwanted, sometimes unimaginable, complications. Syndromic approach to management of STDs is based on the identification of a consistent group of symptoms and syndromes to classify the exact disease or infection be-forehand, so that further investigations are sought for based on this initial criterion. In this paper, we will analyze results based on two different approaches: Human and Artificial Intelligence (AI). Using algorithms specifically applicable to AI, we will examine the benefits and pitfalls of using completely automated computer tasks to generate life-saving information in shortest possible time.