Cargando…

Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction

PURPOSE: To develop and internally validate a machine-learning algorithm to reliably predict cost after anterior cruciate ligament reconstruction (ACLR). METHODS: A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent el...

Descripción completa

Detalles Bibliográficos
Autores principales: Lu, Yining, Kunze, Kyle, Cohn, Matthew R., Lavoie-Gagne, Ophelie, Polce, Evan, Nwachukwu, Benedict U., Forsythe, Brian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8689347/
https://www.ncbi.nlm.nih.gov/pubmed/34977663
http://dx.doi.org/10.1016/j.asmr.2021.10.013
_version_ 1784618537637117952
author Lu, Yining
Kunze, Kyle
Cohn, Matthew R.
Lavoie-Gagne, Ophelie
Polce, Evan
Nwachukwu, Benedict U.
Forsythe, Brian
author_facet Lu, Yining
Kunze, Kyle
Cohn, Matthew R.
Lavoie-Gagne, Ophelie
Polce, Evan
Nwachukwu, Benedict U.
Forsythe, Brian
author_sort Lu, Yining
collection PubMed
description PURPOSE: To develop and internally validate a machine-learning algorithm to reliably predict cost after anterior cruciate ligament reconstruction (ACLR). METHODS: A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent elective ACLR from 2015 to 2016. Features included in initial models consisted of patient characteristics (age, sex, insurance status, income, medical comorbidities as classified by the Clinical Classifications Software diagnosis code) as well as intraoperative variables (type of anesthesia and procedure-specific factors). Models were generated to predict total charges using 4 algorithms: random forest, extreme gradient boost, elastic net penalized regression, and support vector machines with radial kernels. Training was performed with 10-fold cross-validation followed by internal validation via 0.632 bootstrapping. Model discriminative performance was assessed by area under the receiver operating characteristic curve, calibration, and the Brier score. Decision curve analysis was performed to demonstrate the net benefit of using the final model in practice. RESULTS: In total, 7,311 patients undergoing ambulatory ACLR were included. The random forest model demonstrated the best performance assessed via internal validation (area under the curve = 0.85), calibration, and the Brier score (0.208). Cost incurred was influenced by anesthesia type, operating room time, and number of chronic comorbidities. Decision curve analysis revealed a net benefit for use of the random forest model and the model was integrated into a web-based open-access application. CONCLUSIONS: The random forest model predicted cost after ambulatory ACLR using a large, statewide database with good performance. The top variables found to predict increased charges were general anesthesia, operating room time, meniscal repair, self-pay insurance, patient neighborhood characteristics, and number of chronic conditions. LEVEL OF EVIDENCE: III, retrospective cohort study.
format Online
Article
Text
id pubmed-8689347
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-86893472021-12-30 Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction Lu, Yining Kunze, Kyle Cohn, Matthew R. Lavoie-Gagne, Ophelie Polce, Evan Nwachukwu, Benedict U. Forsythe, Brian Arthrosc Sports Med Rehabil Original Article PURPOSE: To develop and internally validate a machine-learning algorithm to reliably predict cost after anterior cruciate ligament reconstruction (ACLR). METHODS: A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent elective ACLR from 2015 to 2016. Features included in initial models consisted of patient characteristics (age, sex, insurance status, income, medical comorbidities as classified by the Clinical Classifications Software diagnosis code) as well as intraoperative variables (type of anesthesia and procedure-specific factors). Models were generated to predict total charges using 4 algorithms: random forest, extreme gradient boost, elastic net penalized regression, and support vector machines with radial kernels. Training was performed with 10-fold cross-validation followed by internal validation via 0.632 bootstrapping. Model discriminative performance was assessed by area under the receiver operating characteristic curve, calibration, and the Brier score. Decision curve analysis was performed to demonstrate the net benefit of using the final model in practice. RESULTS: In total, 7,311 patients undergoing ambulatory ACLR were included. The random forest model demonstrated the best performance assessed via internal validation (area under the curve = 0.85), calibration, and the Brier score (0.208). Cost incurred was influenced by anesthesia type, operating room time, and number of chronic comorbidities. Decision curve analysis revealed a net benefit for use of the random forest model and the model was integrated into a web-based open-access application. CONCLUSIONS: The random forest model predicted cost after ambulatory ACLR using a large, statewide database with good performance. The top variables found to predict increased charges were general anesthesia, operating room time, meniscal repair, self-pay insurance, patient neighborhood characteristics, and number of chronic conditions. LEVEL OF EVIDENCE: III, retrospective cohort study. Elsevier 2021-11-27 /pmc/articles/PMC8689347/ /pubmed/34977663 http://dx.doi.org/10.1016/j.asmr.2021.10.013 Text en © 2021 Published by Elsevier on behalf of the Arthroscopy Association of North America. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Original Article
Lu, Yining
Kunze, Kyle
Cohn, Matthew R.
Lavoie-Gagne, Ophelie
Polce, Evan
Nwachukwu, Benedict U.
Forsythe, Brian
Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title_full Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title_fullStr Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title_full_unstemmed Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title_short Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
title_sort artificial intelligence predicts cost after ambulatory anterior cruciate ligament reconstruction
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8689347/
https://www.ncbi.nlm.nih.gov/pubmed/34977663
http://dx.doi.org/10.1016/j.asmr.2021.10.013
work_keys_str_mv AT luyining artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT kunzekyle artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT cohnmatthewr artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT lavoiegagneophelie artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT polceevan artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT nwachukwubenedictu artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction
AT forsythebrian artificialintelligencepredictscostafterambulatoryanteriorcruciateligamentreconstruction