Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics

Chang Song,1,* Jingsong Chen,2,* Chunyan Zhao,1,* Shulin Song,3,* Tong Yang,4 Aichun Huang,1 Renhao Liu,1 Yanxi Pan,3 Chaoyan Xu,1 Canling Chen,1 Qingdong Zhu1 1Tuberculosis Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of C...

Full description

Saved in:
Bibliographic Details
Main Authors: Song C, Chen J, Zhao C, Song S, Yang T, Huang A, Liu R, Pan Y, Xu C, Chen C, Zhu Q
Format: Article
Language:English
Published: Dove Medical Press 2025-04-01
Series:Cancer Management and Research
Subjects:
Online Access:https://www.dovepress.com/prediction-of-ki-67-expression-in-hiv-associated-lung-adenocarcinoma-p-peer-reviewed-fulltext-article-CMAR
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850170769389125632
author Song C
Chen J
Zhao C
Song S
Yang T
Huang A
Liu R
Pan Y
Xu C
Chen C
Zhu Q
author_facet Song C
Chen J
Zhao C
Song S
Yang T
Huang A
Liu R
Pan Y
Xu C
Chen C
Zhu Q
author_sort Song C
collection DOAJ
description Chang Song,1,* Jingsong Chen,2,* Chunyan Zhao,1,* Shulin Song,3,* Tong Yang,4 Aichun Huang,1 Renhao Liu,1 Yanxi Pan,3 Chaoyan Xu,1 Canling Chen,1 Qingdong Zhu1 1Tuberculosis Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China; 2Gastroenterology Department, Hepu County People’s Hospital, Beihai, Guangxi, 536100, People’s Republic of China; 3Radiology Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China; 4Rehabilitation Department, Hepu County People’s Hospital, Beihai, Guangxi, 536100, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qingdong Zhu, Tuberculosis Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China, Email zhuqingdong2003@163.comPurpose: The incidence of lung adenocarcinoma (LUAD) in HIV-infected individuals is significantly increased. However, invasive procedures for Ki-67 assessment may increase the risk of complications. Therefore, developing a non-invasive and accurate method for Ki-67 prediction holds significant clinical importance. This study aims to explore the feasibility and value of a radiomics model based on preoperative CT images in predicting Ki-67 expression levels in HIV-associated LUAD.Patients and Methods: A total of 237 patients with HIV-associated LUAD were included. Of these, 102 were classified into the high Ki-67 expression group, and 135 into the low Ki-67 expression group. The patients were randomly divided into a training group (n=189) and a validation group (n=48) in a 4:1 ratio. Feature selection was based on intra-class correlation coefficient (ICC), Spearman correlation coefficient, and Least Absolute Shrinkage and Selection Operator (LASSO) regression, yielding 16 optimal radiomic features for building a logistic regression model. Model performance was evaluated by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the receiver operating characteristic curve (AUC).Results: 1834 CT image features were extracted, with 16 retained for further analysis. The Support Vector Machine (SVM) model demonstrated the most balanced and optimal performance among the seven developed models. It achieved robust sensitivity (training set: 0.89; testing set: 0.86), specificity (training set: 0.92; testing set: 0.89), PPV (training set: 0.89; testing set: 0.86), NPV (training set: 0.92; testing set: 0.89), F1 score (training set: 0.89; testing set: 0.86), and AUC (training set: 0.975; testing set: 0.905), indicating excellent predictive accuracy.Conclusion: This study first demonstrates that a preoperative CT-based radiomics model can non-invasively predict Ki-67 expression levels in HIV-associated LUAD patients. This finding not only provides a precise assessment tool for the HIV-infected population to avoid the risks of invasive examinations but also paves new interdisciplinary research avenues for exploring tumor heterogeneity under immunodeficiency conditions.Keywords: HIV, lung adenocarcinoma, Ki-67, radiomics, machine learning, SVM
format Article
id doaj-art-e58751151bee4b02a022814fb8da6708
institution OA Journals
issn 1179-1322
language English
publishDate 2025-04-01
publisher Dove Medical Press
record_format Article
series Cancer Management and Research
spelling doaj-art-e58751151bee4b02a022814fb8da67082025-08-20T02:20:25ZengDove Medical PressCancer Management and Research1179-13222025-04-01Volume 17881892102420Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging RadiomicsSong CChen JZhao CSong SYang THuang ALiu RPan YXu CChen CZhu QChang Song,1,* Jingsong Chen,2,* Chunyan Zhao,1,* Shulin Song,3,* Tong Yang,4 Aichun Huang,1 Renhao Liu,1 Yanxi Pan,3 Chaoyan Xu,1 Canling Chen,1 Qingdong Zhu1 1Tuberculosis Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China; 2Gastroenterology Department, Hepu County People’s Hospital, Beihai, Guangxi, 536100, People’s Republic of China; 3Radiology Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China; 4Rehabilitation Department, Hepu County People’s Hospital, Beihai, Guangxi, 536100, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qingdong Zhu, Tuberculosis Department, Nanning Fourth People’s Hospital, Nanning, Guangxi, 530023, People’s Republic of China, Email zhuqingdong2003@163.comPurpose: The incidence of lung adenocarcinoma (LUAD) in HIV-infected individuals is significantly increased. However, invasive procedures for Ki-67 assessment may increase the risk of complications. Therefore, developing a non-invasive and accurate method for Ki-67 prediction holds significant clinical importance. This study aims to explore the feasibility and value of a radiomics model based on preoperative CT images in predicting Ki-67 expression levels in HIV-associated LUAD.Patients and Methods: A total of 237 patients with HIV-associated LUAD were included. Of these, 102 were classified into the high Ki-67 expression group, and 135 into the low Ki-67 expression group. The patients were randomly divided into a training group (n=189) and a validation group (n=48) in a 4:1 ratio. Feature selection was based on intra-class correlation coefficient (ICC), Spearman correlation coefficient, and Least Absolute Shrinkage and Selection Operator (LASSO) regression, yielding 16 optimal radiomic features for building a logistic regression model. Model performance was evaluated by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the receiver operating characteristic curve (AUC).Results: 1834 CT image features were extracted, with 16 retained for further analysis. The Support Vector Machine (SVM) model demonstrated the most balanced and optimal performance among the seven developed models. It achieved robust sensitivity (training set: 0.89; testing set: 0.86), specificity (training set: 0.92; testing set: 0.89), PPV (training set: 0.89; testing set: 0.86), NPV (training set: 0.92; testing set: 0.89), F1 score (training set: 0.89; testing set: 0.86), and AUC (training set: 0.975; testing set: 0.905), indicating excellent predictive accuracy.Conclusion: This study first demonstrates that a preoperative CT-based radiomics model can non-invasively predict Ki-67 expression levels in HIV-associated LUAD patients. This finding not only provides a precise assessment tool for the HIV-infected population to avoid the risks of invasive examinations but also paves new interdisciplinary research avenues for exploring tumor heterogeneity under immunodeficiency conditions.Keywords: HIV, lung adenocarcinoma, Ki-67, radiomics, machine learning, SVMhttps://www.dovepress.com/prediction-of-ki-67-expression-in-hiv-associated-lung-adenocarcinoma-p-peer-reviewed-fulltext-article-CMARhivlung adenocarcinomaki-67radiomicsmachine learningsvm
spellingShingle Song C
Chen J
Zhao C
Song S
Yang T
Huang A
Liu R
Pan Y
Xu C
Chen C
Zhu Q
Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
Cancer Management and Research
hiv
lung adenocarcinoma
ki-67
radiomics
machine learning
svm
title Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
title_full Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
title_fullStr Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
title_full_unstemmed Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
title_short Prediction of Ki-67 Expression in HIV-Associated Lung Adenocarcinoma Patients Using Multiple Machine Learning Models Based on CT Imaging Radiomics
title_sort prediction of ki 67 expression in hiv associated lung adenocarcinoma patients using multiple machine learning models based on ct imaging radiomics
topic hiv
lung adenocarcinoma
ki-67
radiomics
machine learning
svm
url https://www.dovepress.com/prediction-of-ki-67-expression-in-hiv-associated-lung-adenocarcinoma-p-peer-reviewed-fulltext-article-CMAR
work_keys_str_mv AT songc predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT chenj predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT zhaoc predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT songs predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT yangt predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT huanga predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT liur predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT pany predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT xuc predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT chenc predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics
AT zhuq predictionofki67expressioninhivassociatedlungadenocarcinomapatientsusingmultiplemachinelearningmodelsbasedonctimagingradiomics