Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study

Abstract Autologous reconstruction using abdominal flaps remains the most popular method for breast reconstruction worldwide. We aimed to evaluate a prediction model using machine-learning methods and to determine which factors increase abdominal flap donor site complications with logistic regressio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yujin Myung, Sungmi Jeon, Chanyeong Heo, Eun-Kyu Kim, Eunyoung Kang, Hee-Chul Shin, Eun-Joo Yang, Jae Hoon Jeong
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ff9ef3bf616d4b3dafa5d304a6a85b46
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ff9ef3bf616d4b3dafa5d304a6a85b46
record_format	dspace
spelling	oai:doaj.org-article:ff9ef3bf616d4b3dafa5d304a6a85b462021-12-02T13:34:50ZValidating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study10.1038/s41598-021-85155-z2045-2322https://doaj.org/article/ff9ef3bf616d4b3dafa5d304a6a85b462021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85155-zhttps://doaj.org/toc/2045-2322Abstract Autologous reconstruction using abdominal flaps remains the most popular method for breast reconstruction worldwide. We aimed to evaluate a prediction model using machine-learning methods and to determine which factors increase abdominal flap donor site complications with logistic regression. We evaluated the predictive ability of different machine learning packages, reviewing a cohort of breast reconstruction patients who underwent abdominal flaps. We analyzed 13 treatment variables for effects on the abdominal donor site complication rates. To overcome data imbalances, random over sampling example (ROSE) method was used. Data were divided into training and testing sets. Prediction accuracy, sensitivity, specificity, and predictive power (AUC) were measured by applying neuralnet, nnet, and RSNNS machine learning packages. A total of 568 patients were analyzed. The supervised learning package that performed the most effective prediction was neuralnet. Factors that significantly affected donor-related complication was size of the fascial defect, history of diabetes, muscle sparing type, and presence or absence of adjuvant chemotherapy. The risk cutoff value for fascial defect was 37.5 cm2. High-risk group complication rates analyzed by statistical method were significant compared to the low-risk group (26% vs 1.7%). These results may help surgeons to achieve better surgical outcomes and reduce postoperative burden.Yujin MyungSungmi JeonChanyeong HeoEun-Kyu KimEunyoung KangHee-Chul ShinEun-Joo YangJae Hoon JeongNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yujin Myung Sungmi Jeon Chanyeong Heo Eun-Kyu Kim Eunyoung Kang Hee-Chul Shin Eun-Joo Yang Jae Hoon Jeong Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
description	Abstract Autologous reconstruction using abdominal flaps remains the most popular method for breast reconstruction worldwide. We aimed to evaluate a prediction model using machine-learning methods and to determine which factors increase abdominal flap donor site complications with logistic regression. We evaluated the predictive ability of different machine learning packages, reviewing a cohort of breast reconstruction patients who underwent abdominal flaps. We analyzed 13 treatment variables for effects on the abdominal donor site complication rates. To overcome data imbalances, random over sampling example (ROSE) method was used. Data were divided into training and testing sets. Prediction accuracy, sensitivity, specificity, and predictive power (AUC) were measured by applying neuralnet, nnet, and RSNNS machine learning packages. A total of 568 patients were analyzed. The supervised learning package that performed the most effective prediction was neuralnet. Factors that significantly affected donor-related complication was size of the fascial defect, history of diabetes, muscle sparing type, and presence or absence of adjuvant chemotherapy. The risk cutoff value for fascial defect was 37.5 cm2. High-risk group complication rates analyzed by statistical method were significant compared to the low-risk group (26% vs 1.7%). These results may help surgeons to achieve better surgical outcomes and reduce postoperative burden.
format	article
author	Yujin Myung Sungmi Jeon Chanyeong Heo Eun-Kyu Kim Eunyoung Kang Hee-Chul Shin Eun-Joo Yang Jae Hoon Jeong
author_facet	Yujin Myung Sungmi Jeon Chanyeong Heo Eun-Kyu Kim Eunyoung Kang Hee-Chul Shin Eun-Joo Yang Jae Hoon Jeong
author_sort	Yujin Myung
title	Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
title_short	Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
title_full	Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
title_fullStr	Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
title_full_unstemmed	Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
title_sort	validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ff9ef3bf616d4b3dafa5d304a6a85b46
work_keys_str_mv	AT yujinmyung validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT sungmijeon validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT chanyeongheo validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT eunkyukim validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT eunyoungkang validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT heechulshin validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT eunjooyang validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy AT jaehoonjeong validatingmachinelearningapproachesforpredictionofdonorrelatedcomplicationinmicrosurgicalbreastreconstructionaretrospectivecohortstudy
_version_	1718392773801934848

Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: a retrospective cohort study

Ejemplares similares