Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data
BackgroundAdrenocortical carcinoma (ACC) is a rare malignant tumor with a short life expectancy. It is important to identify patients at high risk so that doctors can adopt more aggressive regimens to treat their condition. Machine learning has the advantage of processing complicated data. To date,...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-01-01
|
Series: | Frontiers in Surgery |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fsurg.2022.966307/full |
_version_ | 1797959929301041152 |
---|---|
author | Jun Tang Yu Fang Zhe Xu |
author_facet | Jun Tang Yu Fang Zhe Xu |
author_sort | Jun Tang |
collection | DOAJ |
description | BackgroundAdrenocortical carcinoma (ACC) is a rare malignant tumor with a short life expectancy. It is important to identify patients at high risk so that doctors can adopt more aggressive regimens to treat their condition. Machine learning has the advantage of processing complicated data. To date, there is no research that tries to use machine learning algorithms and big data to construct prognostic models for ACC patients.MethodsClinical data of patients with ACC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. These records were screened according to preset inclusion and exclusion criteria. The remaining data were applied to univariate survival analysis to select meaningful outcome-related candidates. Backpropagation artificial neural network (BP-ANN), random forest (RF), support vector machine (SVM), and naive Bayes classifier (NBC) were chosen as alternative algorithms. The acquired cases were grouped into a training set and a test set at a ratio of 8:2, and a 10-fold cross-validation method repeated 10 times was performed. Area under the receiver operating characteristic (AUROC) curves were used as indices of efficiency.ResultsThe calculated 1-, 3-, 5-, and 10-year overall survival rates were 62.3%, 42.0%, 34.9%, and 26.1%, respectively. A total of 825 patients were included in the study. In the training set, the AUCs of BP-ANN, RF, SVM, and NBC for predicting 1-year survival status were 0.921, 0.885, 0.865, and 0.854; those for predicting 3-year survival status were 0.859, 0.865, 0.837, and 0.831; and those for 5-year survival status were 0.888, 0.872, 0.852, and 0.841, respectively. In the test set, AUCs of these four models for 1-year survival status were 0.899, 0.875, 0.886, and 0.862; those for 3-year survival status were 0.871, 0.858, 0.853, and 0.869; and those for 5-year survival status were 0.841, 0.783, 0.836, and 0.867, respectively. The consequences of the 10-fold cross-validation method repeated 10 times indicated that the mean values of 1-, 3-, and 5-year AUROCs of BP-ANN were 0.890, 0.847, and 0.854, respectively, which were better than those of other classifiers (P < 0.008).ConclusionThe model combined with BP-ANN and big data can precisely predict the survival status of ACC patients and has the potential for clinical application. |
first_indexed | 2024-04-11T00:39:31Z |
format | Article |
id | doaj.art-b8601decd11944dd94db5eda8d639ef4 |
institution | Directory Open Access Journal |
issn | 2296-875X |
language | English |
last_indexed | 2024-04-11T00:39:31Z |
publishDate | 2023-01-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Surgery |
spelling | doaj.art-b8601decd11944dd94db5eda8d639ef42023-01-06T13:10:44ZengFrontiers Media S.A.Frontiers in Surgery2296-875X2023-01-01910.3389/fsurg.2022.966307966307Establishment of prognostic models of adrenocortical carcinoma using machine learning and big dataJun Tang0Yu Fang1Zhe Xu2Department of Pediatric Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, ChinaDepartment of Pediatrics, China Medical University, Shenyang, ChinaDepartment of Pediatric Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, ChinaBackgroundAdrenocortical carcinoma (ACC) is a rare malignant tumor with a short life expectancy. It is important to identify patients at high risk so that doctors can adopt more aggressive regimens to treat their condition. Machine learning has the advantage of processing complicated data. To date, there is no research that tries to use machine learning algorithms and big data to construct prognostic models for ACC patients.MethodsClinical data of patients with ACC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. These records were screened according to preset inclusion and exclusion criteria. The remaining data were applied to univariate survival analysis to select meaningful outcome-related candidates. Backpropagation artificial neural network (BP-ANN), random forest (RF), support vector machine (SVM), and naive Bayes classifier (NBC) were chosen as alternative algorithms. The acquired cases were grouped into a training set and a test set at a ratio of 8:2, and a 10-fold cross-validation method repeated 10 times was performed. Area under the receiver operating characteristic (AUROC) curves were used as indices of efficiency.ResultsThe calculated 1-, 3-, 5-, and 10-year overall survival rates were 62.3%, 42.0%, 34.9%, and 26.1%, respectively. A total of 825 patients were included in the study. In the training set, the AUCs of BP-ANN, RF, SVM, and NBC for predicting 1-year survival status were 0.921, 0.885, 0.865, and 0.854; those for predicting 3-year survival status were 0.859, 0.865, 0.837, and 0.831; and those for 5-year survival status were 0.888, 0.872, 0.852, and 0.841, respectively. In the test set, AUCs of these four models for 1-year survival status were 0.899, 0.875, 0.886, and 0.862; those for 3-year survival status were 0.871, 0.858, 0.853, and 0.869; and those for 5-year survival status were 0.841, 0.783, 0.836, and 0.867, respectively. The consequences of the 10-fold cross-validation method repeated 10 times indicated that the mean values of 1-, 3-, and 5-year AUROCs of BP-ANN were 0.890, 0.847, and 0.854, respectively, which were better than those of other classifiers (P < 0.008).ConclusionThe model combined with BP-ANN and big data can precisely predict the survival status of ACC patients and has the potential for clinical application.https://www.frontiersin.org/articles/10.3389/fsurg.2022.966307/fulladrenocortical carcinomamachine learningSEERBP-ANNsurvival status |
spellingShingle | Jun Tang Yu Fang Zhe Xu Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data Frontiers in Surgery adrenocortical carcinoma machine learning SEER BP-ANN survival status |
title | Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
title_full | Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
title_fullStr | Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
title_full_unstemmed | Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
title_short | Establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
title_sort | establishment of prognostic models of adrenocortical carcinoma using machine learning and big data |
topic | adrenocortical carcinoma machine learning SEER BP-ANN survival status |
url | https://www.frontiersin.org/articles/10.3389/fsurg.2022.966307/full |
work_keys_str_mv | AT juntang establishmentofprognosticmodelsofadrenocorticalcarcinomausingmachinelearningandbigdata AT yufang establishmentofprognosticmodelsofadrenocorticalcarcinomausingmachinelearningandbigdata AT zhexu establishmentofprognosticmodelsofadrenocorticalcarcinomausingmachinelearningandbigdata |