Cargando…
Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods
BACKGROUND: Fraud, Waste, and Abuse (FWA) in medical claims have a negative impact on the quality and cost of healthcare. A major component of FWA in claims is procedure code overutilization, where one or more prescribed procedures may not be relevant to a given diagnosis and patient profile, result...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10536726/ https://www.ncbi.nlm.nih.gov/pubmed/37770866 http://dx.doi.org/10.1186/s12911-023-02268-3 |
_version_ | 1785112938872307712 |
---|---|
author | Suesserman, Michael Gorny, Samantha Lasaga, Daniel Helms, John Olson, Dan Bowen, Edward Bhattacharya, Sanmitra |
author_facet | Suesserman, Michael Gorny, Samantha Lasaga, Daniel Helms, John Olson, Dan Bowen, Edward Bhattacharya, Sanmitra |
author_sort | Suesserman, Michael |
collection | PubMed |
description | BACKGROUND: Fraud, Waste, and Abuse (FWA) in medical claims have a negative impact on the quality and cost of healthcare. A major component of FWA in claims is procedure code overutilization, where one or more prescribed procedures may not be relevant to a given diagnosis and patient profile, resulting in unnecessary and unwarranted treatments and medical payments. This study aims to identify such unwarranted procedures from millions of healthcare claims. In the absence of labeled examples of unwarranted procedures, the study focused on the application of unsupervised machine learning techniques. METHODS: Experiments were conducted with deep autoencoders to find claims containing anomalous procedure codes indicative of FWA, and were compared against a baseline density-based clustering model. Diagnoses, procedures, and demographic data associated with healthcare claims were used as features for the models. A dataset of one hundred thousand claims sampled from a larger claims database is used to initially train and tune the models, followed by experimentations on a dataset with thirty-three million claims. Experimental results show that the autoencoder model, when trained with a novel feature-weighted loss function, outperforms the density-based clustering approach in finding potential outlier procedure codes. RESULTS: Given the unsupervised nature of our experiments, model performance was evaluated using a synthetic outlier test dataset, and a manually annotated outlier test dataset. Precision, recall and F1-scores on the synthetic outlier test dataset for the autoencoder model trained on one hundred thousand claims were 0.87, 1.0 and 0.93, respectively, while the results for these metrics on the manually annotated outlier test dataset were 0.36, 0.86 and 0.51, respectively. The model performance on the manually annotated outlier test dataset improved further when trained on the larger thirty-three million claims dataset with precision, recall and F1-scores of 0.48, 0.90 and 0.63, respectively. CONCLUSIONS: This study demonstrates the feasibility of leveraging unsupervised, deep-learning methods to identify potential procedure overutilization from healthcare claims. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12911-023-02268-3. |
format | Online Article Text |
id | pubmed-10536726 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-105367262023-09-29 Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods Suesserman, Michael Gorny, Samantha Lasaga, Daniel Helms, John Olson, Dan Bowen, Edward Bhattacharya, Sanmitra BMC Med Inform Decis Mak Research BACKGROUND: Fraud, Waste, and Abuse (FWA) in medical claims have a negative impact on the quality and cost of healthcare. A major component of FWA in claims is procedure code overutilization, where one or more prescribed procedures may not be relevant to a given diagnosis and patient profile, resulting in unnecessary and unwarranted treatments and medical payments. This study aims to identify such unwarranted procedures from millions of healthcare claims. In the absence of labeled examples of unwarranted procedures, the study focused on the application of unsupervised machine learning techniques. METHODS: Experiments were conducted with deep autoencoders to find claims containing anomalous procedure codes indicative of FWA, and were compared against a baseline density-based clustering model. Diagnoses, procedures, and demographic data associated with healthcare claims were used as features for the models. A dataset of one hundred thousand claims sampled from a larger claims database is used to initially train and tune the models, followed by experimentations on a dataset with thirty-three million claims. Experimental results show that the autoencoder model, when trained with a novel feature-weighted loss function, outperforms the density-based clustering approach in finding potential outlier procedure codes. RESULTS: Given the unsupervised nature of our experiments, model performance was evaluated using a synthetic outlier test dataset, and a manually annotated outlier test dataset. Precision, recall and F1-scores on the synthetic outlier test dataset for the autoencoder model trained on one hundred thousand claims were 0.87, 1.0 and 0.93, respectively, while the results for these metrics on the manually annotated outlier test dataset were 0.36, 0.86 and 0.51, respectively. The model performance on the manually annotated outlier test dataset improved further when trained on the larger thirty-three million claims dataset with precision, recall and F1-scores of 0.48, 0.90 and 0.63, respectively. CONCLUSIONS: This study demonstrates the feasibility of leveraging unsupervised, deep-learning methods to identify potential procedure overutilization from healthcare claims. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12911-023-02268-3. BioMed Central 2023-09-28 /pmc/articles/PMC10536726/ /pubmed/37770866 http://dx.doi.org/10.1186/s12911-023-02268-3 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/ (https://creativecommons.org/publicdomain/zero/1.0/) ) applies to the data made available in this article, unless otherwise stated in a credit line to the data. |
spellingShingle | Research Suesserman, Michael Gorny, Samantha Lasaga, Daniel Helms, John Olson, Dan Bowen, Edward Bhattacharya, Sanmitra Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title | Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title_full | Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title_fullStr | Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title_full_unstemmed | Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title_short | Procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
title_sort | procedure code overutilization detection from healthcare claims using unsupervised deep learning methods |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10536726/ https://www.ncbi.nlm.nih.gov/pubmed/37770866 http://dx.doi.org/10.1186/s12911-023-02268-3 |
work_keys_str_mv | AT suessermanmichael procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT gornysamantha procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT lasagadaniel procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT helmsjohn procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT olsondan procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT bowenedward procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods AT bhattacharyasanmitra procedurecodeoverutilizationdetectionfromhealthcareclaimsusingunsuperviseddeeplearningmethods |