Predictive Analytics and Machine Learning in Disease Diagnosis: A Review of Recent Advances

Abstract

Artificial intelligence (AI) refers to the utilisation of computer information to exhibit intelligent behaviour with minimal human intervention, whereas machine learning (ML) is seen as a subset of AI methodologies. Typically, this form of intelligence is widely recognised to have originated with the advent of robotics. Given the slow progression of diseases, it is crucial to make early predictions and administer appropriate medication. Hence, it is imperative to present a decision model that may aid in the diagnosis of chronic illnesses and forecast future patient prognoses. The primary objective of this study is to investigate the application of Predictive Analytics and ML in the field of Disease Diagnosis. The study will focus on reviewing the latest advancements in this area. This work specifically emphasises the significance of ML prediction models in disease diagnosis within the AI field, amidst other approaches available.  The study utilises a qualitative research methodology. ML has been prominent in the medical field as it offers methods for analysing disease-related data, as indicated by this study. ML algorithms are crucial in attaining early disease detection. Another crucial finding in this research is that the accuracy and performance of the model can be enhanced by employing an alternative technique to generate a single ensemble model.