Statistical Modeling for Studying the Impact of ICD-10 on Health Fraud Detection

When an individual is seen or treated by a healthcare professional, a series of alphanumeric codes are used to describe the medical diagnoses and services provided. This designated classification structure, the ninth iteration of ICD (International Classification of Diseases), implements the use of coding for healthcare management, public health and medical informatics, and insurance purposes. ICD-9 has been the coding standard in the healthcare industry for 30 years. On October 1st, 2015, the tenth revision ICD-10 was formally implemented in the United States. This paper explores the validity of predictions from domain professionals regarding fraud detection and the implementation of the ICD-10 code set. The notion that fraud detection systems using supervised learning algorithms will encounter an initial decline in performance due to ICD-10 is fairly unsupported at the moment. The authors claim that the results from their study will provide evidence that will support this notion of a preliminary negative transitional impact.