A Taxonomic Framework Based on Machine Learning for Unsupervised Anomaly Detection in Healthcare Data
Authors:
- Gelson André SchneiderGSGelson André Schneider
- Moisés Laurence de Freitas Lima JúniorMJMoisés Laurence de Freitas Lima Júnior
- Davenilcio Luiz de SouzaDSDavenilcio Luiz de Souza
- Domingos Rafael Ferla ValladaresDVDomingos Rafael Ferla Valladares
- Mikael Henrique de Jesus BatistaMBMikael Henrique de Jesus Batista
- André Luís KorzenowskiAKAndré Luís Korzenowski
Open Access
- 10 October 2026
- journal article
- research article
- Published by MDPI AG in Healthcare
- Vol. 14 (20) , 3380
Abstract
Objectives: This study presents a generic taxonomic framework as a roadmap for users who wish to implement systems for detecting fraud and waste in health data; this roadmap outlines which unsupervised machine learning techniques can be used to detect anomalies in health data, and whether these anomalies are point, contextual, or collective. Methods: The research employed the Design Science Research (DSR) methodology in five stages: awareness, ideation, development, evaluation, and conclusion. The proposed taxonomic framework was designed through the implementation of the artifact, using the “Sample 1 to Inpatient Claims CMS 2008–2010 Data Entrepreneurs’ Synthetic Public Use File (DE-SynPUF)” database, which contains 66,773 records and 81 features. The dataset was applied to the K-Means, Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms for point anomaly detection. Results: The number of anomalies detected by at least one of the algorithms was 13,966, representing (20.9%) of the dataset; K-Means alone detected 1608 (2.4%), IF alone detected 4522 (6.8%), LOF alone detected 2301 (3.4%), K-Means and IF together detected 4497 (6.7%), K-Means and LOF together detected 41 (0.1%), IF + LOF combined detected 465 (0.7%), and all three algorithms in consensus detected 532 (0.8%). Conclusions: Thus, the taxonomic framework proposed in this study can be viewed as a roadmap for researchers and developers seeking to understand which unsupervised technique to apply in detecting anomalies in health data, considering the type of anomaly.Keywords
This publication has 28 references indexed in Scilit:
- Factor analysis of mixed data for anomaly detectionStatistical Analysis and Data Mining: An ASA Data Science Journal, 2022
- Healthcare fraud detection using primitive sub peer group analysisConcurrency and Computation: Practice and Experience, 2021
- Unsupervised K-Means Clustering AlgorithmIEEE Access, 2020
- Statistical Medical Fraud Assessment: Exposition to an Emerging FieldInternational Statistical Review, 2018
- DDC-Outlier: Preventing Medication Errors Using Unsupervised LearningIEEE Journal of Biomedical and Health Informatics, 2018
- Fraud detection system: A surveyJournal of Network and Computer Applications, 2016
- A scoring model to detect abusive billing patterns in health insurance claimsExpert Systems with Applications, 2012
- Two models to investigate Medicare fraud within unsupervised databasesExpert Systems with Applications, 2010
- Anomaly detectionACM Computing Surveys, 2009
- Claims Auditing in Automobile Insurance: Fraud Detection and Deterrence ObjectivesJournal of Risk and Insurance, 2002