The Impact Of Healthcare Fraud And Abuse Regulations On Administration Practices

Abstract

Insurance companies or third party payers make inappropriate payments due to mistakes, misuse, and fraud. The magnitude of this problem warrants its classification as a high-priority concern for health systems. Conventional approaches to identifying instances of healthcare fraud and abuse are laborious and ineffective. The integration of automated techniques with statistical expertise has resulted in the development of a new multidisciplinary field known as Knowledge Discovery from Databases (KDD). Data mining is a fundamental component of the Knowledge Discovery in Databases (KDD) process. Data mining enables third-party payers, such as health insurance companies, to extract valuable insights from a large volume of claims and select a smaller fraction of claims or claimants that need further evaluation. We conducted a comprehensive analysis of research that used data mining techniques to identify instances of health care fraud and abuse. These studies included both supervised and unsupervised data mining methods. The majority of existing research have mostly concentrated on algorithmic data mining, neglecting the specific application of fraud detection in the field of health care supply or health insurance policy. Further research is required to establish a correlation between sound and evidence-based methods of diagnosing and treating fraudulent or abusive activities. Based on the existing research, we ultimately suggest following seven broad methods for data mining of health care claims.