Explainable unsupervised anomaly detection for healthcare insurance data

Hannes De Meulemeester; Frank De Smet; Johan van Dorst; Elise Derroitte; Bart De Moor

doi:10.1186/s12911-024-02823-6

Explainable unsupervised anomaly detection for healthcare insurance data

Hannes De Meulemeester, Frank De Smet, Johan van Dorst, Elise Derroitte, Bart De Moor

Hyperspectral Unit

Onderzoeksoutput: Bijdrage aan een tijdschrift › Artikel › peer review

2 Downloads (Pure)

Samenvatting

Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior.

Originele taal-2	Engels
Pagina's (van-tot)	14
Tijdschrift	BMC Medical Informatics and Decision Making
Volume	25
Nummer van het tijdschrift	1
DOI's	https://doi.org/10.1186/s12911-024-02823-6
Status	Gepubliceerd - 2025

Toegang tot document

10.1186/s12911-024-02823-6

s12911-024-02823-6Definitieve gepubliceerde versie, 1,28 MB

Citeer dit

@article{722e45877ec646d49f5494660908c89a,

title = "Explainable unsupervised anomaly detection for healthcare insurance data",

abstract = "Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior.",

author = "{De Meulemeester}, Hannes and {De Smet}, Frank and {van Dorst}, Johan and Elise Derroitte and {De Moor}, Bart",

year = "2025",

doi = "10.1186/s12911-024-02823-6",

language = "English",

volume = "25",

pages = "14",

journal = "BMC Medical Informatics and Decision Making",

issn = "1472-6947",

number = "1",

}

TY - JOUR

T1 - Explainable unsupervised anomaly detection for healthcare insurance data

AU - De Meulemeester, Hannes

AU - De Smet, Frank

AU - van Dorst, Johan

AU - Derroitte, Elise

AU - De Moor, Bart

PY - 2025

Y1 - 2025

N2 - Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior.

AB - Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior.

U2 - 10.1186/s12911-024-02823-6

DO - 10.1186/s12911-024-02823-6

M3 - Article

SN - 1472-6947

VL - 25

SP - 14

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

IS - 1

ER -

Explainable unsupervised anomaly detection for healthcare insurance data

Samenvatting

Toegang tot document

Vingerafdruk

Citeer dit