Study of Interpretability in ML Algorithms for Disease Prognosis

Abstract

Disease prognosis plays an important role in healthcare. Diagnosing disease at an early stage is crucial to provide treatment to the patient at the earliest in order to save his/her life or to at least reduce the severity of the disease. Application of Machine Learning algorithms is a promising area for the early and accurate diagnosis of chronic diseases. The black-box approach of Machine Learning models has been circumvented by providing different Interpretability methods. The importance of interpretability in health care field especially while taking decisions in life threatening diseases is crucial. Interpretable model increases the confidence of a medical practitioner in taking decisions. This paper gives an insight to the importance of explanations as well as the interpretability methods applied to different machine learning and deep learning models developed in recent years.