Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer
ObjectiveTo investigate the effect of transrectal multimodal ultrasound combined with serum prostate-specific antigen (PSA)-related indicators and machine learning for the diagnosis of clinically significant prostate cancer.MethodsBased on Gleason score of postoperative pathological results, the sub...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-03-01
|
Series: | Frontiers in Endocrinology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2023.1137322/full |
_version_ | 1811158308851023872 |
---|---|
author | Maoliang Zhang Yuanzhen Liu Yuanzhen Liu Yuanzhen Liu Jincao Yao Jincao Yao Jincao Yao Kai Wang Jing Tu Zhengbiao Hu Yun Jin Yue Du Xingbo Sun Liyu Chen Liyu Chen Zhengping Wang |
author_facet | Maoliang Zhang Yuanzhen Liu Yuanzhen Liu Yuanzhen Liu Jincao Yao Jincao Yao Jincao Yao Kai Wang Jing Tu Zhengbiao Hu Yun Jin Yue Du Xingbo Sun Liyu Chen Liyu Chen Zhengping Wang |
author_sort | Maoliang Zhang |
collection | DOAJ |
description | ObjectiveTo investigate the effect of transrectal multimodal ultrasound combined with serum prostate-specific antigen (PSA)-related indicators and machine learning for the diagnosis of clinically significant prostate cancer.MethodsBased on Gleason score of postoperative pathological results, the subjects were divided into clinically significant prostate cancer groups(GS>6)and non-clinically significant prostate cancer groups(GS ≤ 6). The independent risk factors were obtained by univariate logistic analysis. Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbor (KNN) machine learning models were combined with clinically significant prostate cancer risk factors to establish the machine learning model, calculate the model evaluation indicators, construct the receiver operating characteristic curve (ROC), and calculate the area under the curve (AUC).ResultsIndependent risk factor items (P< 0.05) were entered into the machine learning model. A comparison of the evaluation indicators of the model and the area under the ROC curve showed the ANN model to be best at predicting clinically significant prostate cancer, with a sensitivity of 80%, specificity of 88.6%, F1 score of 0.897, and the AUC was 0.855.ConclusionEstablishing a machine learning model by rectal multimodal ultrasound and combining it with PSA-related indicators has definite application value in predicting clinically significant prostate cancer. |
first_indexed | 2024-04-10T05:22:18Z |
format | Article |
id | doaj.art-4c6986066af24494bed073c05a0a6cec |
institution | Directory Open Access Journal |
issn | 1664-2392 |
language | English |
last_indexed | 2024-04-10T05:22:18Z |
publishDate | 2023-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Endocrinology |
spelling | doaj.art-4c6986066af24494bed073c05a0a6cec2023-03-08T06:48:46ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922023-03-011410.3389/fendo.2023.11373221137322Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancerMaoliang Zhang0Yuanzhen Liu1Yuanzhen Liu2Yuanzhen Liu3Jincao Yao4Jincao Yao5Jincao Yao6Kai Wang7Jing Tu8Zhengbiao Hu9Yun Jin10Yue Du11Xingbo Sun12Liyu Chen13Liyu Chen14Zhengping Wang15Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, Cancer Hospital of the University of Chinese Academy of Sciences, Zhejiang Cancer Hospital, Hangzhou, ChinaInstitute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, ChinaKey Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, Hangzhou, Zhejiang, ChinaDepartment of Ultrasound, Cancer Hospital of the University of Chinese Academy of Sciences, Zhejiang Cancer Hospital, Hangzhou, ChinaInstitute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, ChinaKey Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, Hangzhou, Zhejiang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaDepartment of Ultrasound, Cancer Hospital of the University of Chinese Academy of Sciences, Zhejiang Cancer Hospital, Hangzhou, ChinaInstitute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, ChinaDepartment of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, ChinaObjectiveTo investigate the effect of transrectal multimodal ultrasound combined with serum prostate-specific antigen (PSA)-related indicators and machine learning for the diagnosis of clinically significant prostate cancer.MethodsBased on Gleason score of postoperative pathological results, the subjects were divided into clinically significant prostate cancer groups(GS>6)and non-clinically significant prostate cancer groups(GS ≤ 6). The independent risk factors were obtained by univariate logistic analysis. Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbor (KNN) machine learning models were combined with clinically significant prostate cancer risk factors to establish the machine learning model, calculate the model evaluation indicators, construct the receiver operating characteristic curve (ROC), and calculate the area under the curve (AUC).ResultsIndependent risk factor items (P< 0.05) were entered into the machine learning model. A comparison of the evaluation indicators of the model and the area under the ROC curve showed the ANN model to be best at predicting clinically significant prostate cancer, with a sensitivity of 80%, specificity of 88.6%, F1 score of 0.897, and the AUC was 0.855.ConclusionEstablishing a machine learning model by rectal multimodal ultrasound and combining it with PSA-related indicators has definite application value in predicting clinically significant prostate cancer.https://www.frontiersin.org/articles/10.3389/fendo.2023.1137322/fullclinically significant prostate cancermultimodal ultrasoundserum prostate specific antigenmachine learningartificial neural network |
spellingShingle | Maoliang Zhang Yuanzhen Liu Yuanzhen Liu Yuanzhen Liu Jincao Yao Jincao Yao Jincao Yao Kai Wang Jing Tu Zhengbiao Hu Yun Jin Yue Du Xingbo Sun Liyu Chen Liyu Chen Zhengping Wang Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer Frontiers in Endocrinology clinically significant prostate cancer multimodal ultrasound serum prostate specific antigen machine learning artificial neural network |
title | Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer |
title_full | Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer |
title_fullStr | Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer |
title_full_unstemmed | Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer |
title_short | Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer |
title_sort | value of machine learning based transrectal multimodal ultrasound combined with psa related indicators in the diagnosis of clinically significant prostate cancer |
topic | clinically significant prostate cancer multimodal ultrasound serum prostate specific antigen machine learning artificial neural network |
url | https://www.frontiersin.org/articles/10.3389/fendo.2023.1137322/full |
work_keys_str_mv | AT maoliangzhang valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT yuanzhenliu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT yuanzhenliu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT yuanzhenliu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT jincaoyao valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT jincaoyao valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT jincaoyao valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT kaiwang valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT jingtu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT zhengbiaohu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT yunjin valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT yuedu valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT xingbosun valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT liyuchen valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT liyuchen valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer AT zhengpingwang valueofmachinelearningbasedtransrectalmultimodalultrasoundcombinedwithpsarelatedindicatorsinthediagnosisofclinicallysignificantprostatecancer |