AUTHOR=M. S. Abdul Razak , C. R. Nirmala , B. R. Sreenivasa , Lahza Husam , Lahza Hassan Fareed M. 

TITLE=A survey on detecting healthcare concept drift in AI/ML models from a finance perspective

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 5 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.955314

DOI=10.3389/frai.2022.955314

ISSN=2624-8212

ABSTRACT=Today in the digital world data is very important and data represents facts and figures of our daily life transactions. Today's arrival of data is not static in nature; it is arriving in streaming fashion. The arrival of unbounded, continuous and rapid data is known as data streams. The Healthcare sector is one of the significant sources of data streams.  Processing data streams is very difficult due to their characteristics like volume, speed, and variety. Classification of data streams is challenging due to concept drift. In supervised learning, concept drift occurs when the statistical features of the target variable, which the model predicts, change surprisingly. In this paper, we focused on addressing different types of concept drift problems in healthcare data streams and summarized the existing statistical and machine learning approaches for handling concept drift. It also highlights the use of deep learning approaches for the detection of concept drift and summarizes the different healthcare datasets used for concept drift detection in the classification of data streams.