Cargando…

Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning

BACKGROUND: This study aimed to predict the treatment outcomes in patients with diabetic macular edema (DME) after 3 monthly anti-vascular endothelial growth factor (VEGF) injections using machine learning (ML) based on pretreatment optical coherence tomography (OCT) images and clinical variables. M...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Baoyi, Zhang, Bin, Hu, Yijun, Cao, Dan, Yang, Dawei, Wu, Qiaowei, Hu, Yu, Yang, Jingwen, Peng, Qingsheng, Huang, Manqing, Zhong, Pingting, Dong, Xinran, Feng, Songfu, Li, Tao, Lin, Haotian, Cai, Hongmin, Yang, Xiaohong, Yu, Honghua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AME Publishing Company 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7859823/
https://www.ncbi.nlm.nih.gov/pubmed/33553336
http://dx.doi.org/10.21037/atm-20-1431
_version_ 1783646820299177984
author Liu, Baoyi
Zhang, Bin
Hu, Yijun
Cao, Dan
Yang, Dawei
Wu, Qiaowei
Hu, Yu
Yang, Jingwen
Peng, Qingsheng
Huang, Manqing
Zhong, Pingting
Dong, Xinran
Feng, Songfu
Li, Tao
Lin, Haotian
Cai, Hongmin
Yang, Xiaohong
Yu, Honghua
author_facet Liu, Baoyi
Zhang, Bin
Hu, Yijun
Cao, Dan
Yang, Dawei
Wu, Qiaowei
Hu, Yu
Yang, Jingwen
Peng, Qingsheng
Huang, Manqing
Zhong, Pingting
Dong, Xinran
Feng, Songfu
Li, Tao
Lin, Haotian
Cai, Hongmin
Yang, Xiaohong
Yu, Honghua
author_sort Liu, Baoyi
collection PubMed
description BACKGROUND: This study aimed to predict the treatment outcomes in patients with diabetic macular edema (DME) after 3 monthly anti-vascular endothelial growth factor (VEGF) injections using machine learning (ML) based on pretreatment optical coherence tomography (OCT) images and clinical variables. METHODS: An ensemble ML system consisting of four deep learning (DL) models and five classical machine learning (CML) models was developed to predict the posttreatment central foveal thickness (CFT) and the best-corrected visual acuity (BCVA). A total of 363 OCT images and 7,587 clinical data records from 363 eyes were included in the training set (304 eyes) and external validation set (59 eyes). The DL models were trained using the OCT images, and the CML models were trained using the OCT images features and clinical variables. The predictive posttreatment CFT and BCVA values were compared with true outcomes obtained from the medical records. RESULTS: For CFT prediction, the mean absolute error (MAE), root mean square error (RMSE), and R(2) of the best-performing model in the training set was 66.59, 93.73, and 0.71, respectively, with an area under receiver operating characteristic curve (AUC) of 0.90 for distinguishing the eyes with good anatomical response. The MAE, RMSE, and R(2) was 68.08, 97.63, and 0.74, respectively, with an AUC of 0.94 in the external validation set. For BCVA prediction, the MAE, RMSE, and R(2) of the best-performing model in the training set was 0.19, 0.29, and 0.60, respectively, with an AUC of 0.80 for distinguishing eyes with a good functional response. The external validation achieved a MAE, RMSE, and R(2) of 0.13, 0.20, and 0.68, respectively, with an AUC of 0.81. CONCLUSIONS: Our ensemble ML system accurately predicted posttreatment CFT and BCVA after anti-VEGF injections in DME patients, and can be used to prospectively assess the efficacy of anti-VEGF therapy in DME patients.
format Online
Article
Text
id pubmed-7859823
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher AME Publishing Company
record_format MEDLINE/PubMed
spelling pubmed-78598232021-02-05 Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning Liu, Baoyi Zhang, Bin Hu, Yijun Cao, Dan Yang, Dawei Wu, Qiaowei Hu, Yu Yang, Jingwen Peng, Qingsheng Huang, Manqing Zhong, Pingting Dong, Xinran Feng, Songfu Li, Tao Lin, Haotian Cai, Hongmin Yang, Xiaohong Yu, Honghua Ann Transl Med Original Article BACKGROUND: This study aimed to predict the treatment outcomes in patients with diabetic macular edema (DME) after 3 monthly anti-vascular endothelial growth factor (VEGF) injections using machine learning (ML) based on pretreatment optical coherence tomography (OCT) images and clinical variables. METHODS: An ensemble ML system consisting of four deep learning (DL) models and five classical machine learning (CML) models was developed to predict the posttreatment central foveal thickness (CFT) and the best-corrected visual acuity (BCVA). A total of 363 OCT images and 7,587 clinical data records from 363 eyes were included in the training set (304 eyes) and external validation set (59 eyes). The DL models were trained using the OCT images, and the CML models were trained using the OCT images features and clinical variables. The predictive posttreatment CFT and BCVA values were compared with true outcomes obtained from the medical records. RESULTS: For CFT prediction, the mean absolute error (MAE), root mean square error (RMSE), and R(2) of the best-performing model in the training set was 66.59, 93.73, and 0.71, respectively, with an area under receiver operating characteristic curve (AUC) of 0.90 for distinguishing the eyes with good anatomical response. The MAE, RMSE, and R(2) was 68.08, 97.63, and 0.74, respectively, with an AUC of 0.94 in the external validation set. For BCVA prediction, the MAE, RMSE, and R(2) of the best-performing model in the training set was 0.19, 0.29, and 0.60, respectively, with an AUC of 0.80 for distinguishing eyes with a good functional response. The external validation achieved a MAE, RMSE, and R(2) of 0.13, 0.20, and 0.68, respectively, with an AUC of 0.81. CONCLUSIONS: Our ensemble ML system accurately predicted posttreatment CFT and BCVA after anti-VEGF injections in DME patients, and can be used to prospectively assess the efficacy of anti-VEGF therapy in DME patients. AME Publishing Company 2021-01 /pmc/articles/PMC7859823/ /pubmed/33553336 http://dx.doi.org/10.21037/atm-20-1431 Text en 2021 Annals of Translational Medicine. All rights reserved. https://creativecommons.org/licenses/by-nc-nd/4.0/Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0 (https://creativecommons.org/licenses/by-nc-nd/4.0/) .
spellingShingle Original Article
Liu, Baoyi
Zhang, Bin
Hu, Yijun
Cao, Dan
Yang, Dawei
Wu, Qiaowei
Hu, Yu
Yang, Jingwen
Peng, Qingsheng
Huang, Manqing
Zhong, Pingting
Dong, Xinran
Feng, Songfu
Li, Tao
Lin, Haotian
Cai, Hongmin
Yang, Xiaohong
Yu, Honghua
Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title_full Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title_fullStr Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title_full_unstemmed Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title_short Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
title_sort automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7859823/
https://www.ncbi.nlm.nih.gov/pubmed/33553336
http://dx.doi.org/10.21037/atm-20-1431
work_keys_str_mv AT liubaoyi automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT zhangbin automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT huyijun automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT caodan automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT yangdawei automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT wuqiaowei automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT huyu automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT yangjingwen automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT pengqingsheng automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT huangmanqing automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT zhongpingting automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT dongxinran automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT fengsongfu automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT litao automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT linhaotian automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT caihongmin automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT yangxiaohong automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning
AT yuhonghua automaticpredictionoftreatmentoutcomesinpatientswithdiabeticmacularedemausingensemblemachinelearning