Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study
Wanling Wang,1 Bingqing Yang,2 Huan Wu,1 Hebin Che,1 Yue Tong,1 Bozun Zhang,1 Hongwu Liu,3,* Yuanyuan Chen1,* 1Medical Innovation Research Department of PLA General Hospital, Beijing, People’s Republic of China; 2Goodwill Hessian Health Technology Co. Ltd, Beijing, People’s R...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-06-01
|
| Series: | Journal of Multidisciplinary Healthcare |
| Subjects: | |
| Online Access: | https://www.dovepress.com/auxiliary-diagnosis-of-pulmonary-nodules-benignancy-and-malignancy-bas-peer-reviewed-fulltext-article-JMDH |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850109814097575936 |
|---|---|
| author | Wang W Yang B Wu H Che H Tong Y Zhang B Liu H Chen Y |
| author_facet | Wang W Yang B Wu H Che H Tong Y Zhang B Liu H Chen Y |
| author_sort | Wang W |
| collection | DOAJ |
| description | Wanling Wang,1 Bingqing Yang,2 Huan Wu,1 Hebin Che,1 Yue Tong,1 Bozun Zhang,1 Hongwu Liu,3,* Yuanyuan Chen1,* 1Medical Innovation Research Department of PLA General Hospital, Beijing, People’s Republic of China; 2Goodwill Hessian Health Technology Co. Ltd, Beijing, People’s Republic of China; 3Department of Pulmonary and Critical Care Medicine, the Seventh Medical Center of Chinese PLA General Hospital, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yuanyuan Chen, Email charry135@163.com Hongwu Liu, Email liuhw1005@163.comBackground: Lung cancer, one of the most lethal malignancies globally, often presents insidiously as pulmonary nodules. Its nonspecific clinical presentation and heterogeneous imaging characteristics hinder accurate differentiation between benign and malignant lesions, while biopsy’s invasiveness and procedural constraints underscore the critical need for non-invasive early diagnostic approaches.Methods: In this retrospective study, we analyzed outpatient and inpatient records from the First Medical Center of Chinese PLA General Hospital between 2011 and 2021, focusing on pulmonary nodules measuring 5– 30mm on CT scans without overt signs of malignancy. Pathological examination served as the reference standard. Comparative experiments evaluated SVM, RF, XGBoost, FNN, and Atten_FNN using five-fold cross-validation to assess AUC, sensitivity, and specificity. The dataset was split 70%/30%, and stratified five-fold cross-validation was applied to the training set. The optimal model was interpreted with SHAP to identify the most influential predictive features.Results: This study enrolled 3355 patients, including 1156 with benign and 2199 with malignant pulmonary nodules. The Atten_FNN model demonstrated superior performance in five-fold cross-validation, achieving an AUC of 0.82, accuracy of 0.75, sensitivity of 0.77, and F1 score of 0.80. SHAP analysis revealed key predictive factors: demographic variables (age, sex, BMI), CT-derived features (maximum nodule diameter, morphology, density, calcification, ground-glass opacity), and laboratory biomarkers (neuroendocrine markers, carcinoembryonic antigen).Conclusion: This study integrates electronic medical records and pathology data to predict pulmonary nodule malignancy using machine/deep learning models. SHAP-based interpretability analysis uncovered key clinical determinants. Acknowledging limitations in cross-center generalizability, we propose the development of a multimodal diagnostic systems that combines CT imaging and radiomics, to be validated in multi-center prospective cohorts to facilitate clinical translation. This framework establishes a novel paradigm for early precision diagnosis of lung cancer.Keywords: pulmonary nodules, benignancy, malignancy, machine learning, risk factors |
| format | Article |
| id | doaj-art-3a91763c792f447d965b80acfc4826a2 |
| institution | OA Journals |
| issn | 1178-2390 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Journal of Multidisciplinary Healthcare |
| spelling | doaj-art-3a91763c792f447d965b80acfc4826a22025-08-20T02:37:58ZengDove Medical PressJournal of Multidisciplinary Healthcare1178-23902025-06-01Volume 18Issue 137353748104295Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective StudyWang W0Yang BWu H1Che H2Tong Y3Zhang B4Liu H5Chen Y6Medical Innovation Research DivisionMedical Innovation Research DivisionDepartment of Pulmonary and Critical Care MedicineMedical Innovation Research DivisionDepartment of Pulmonary and Critical Care MedicineDepartment of Pulmonary and Critical Care MedicineMedical Innovation Research DivisionWanling Wang,1 Bingqing Yang,2 Huan Wu,1 Hebin Che,1 Yue Tong,1 Bozun Zhang,1 Hongwu Liu,3,* Yuanyuan Chen1,* 1Medical Innovation Research Department of PLA General Hospital, Beijing, People’s Republic of China; 2Goodwill Hessian Health Technology Co. Ltd, Beijing, People’s Republic of China; 3Department of Pulmonary and Critical Care Medicine, the Seventh Medical Center of Chinese PLA General Hospital, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yuanyuan Chen, Email charry135@163.com Hongwu Liu, Email liuhw1005@163.comBackground: Lung cancer, one of the most lethal malignancies globally, often presents insidiously as pulmonary nodules. Its nonspecific clinical presentation and heterogeneous imaging characteristics hinder accurate differentiation between benign and malignant lesions, while biopsy’s invasiveness and procedural constraints underscore the critical need for non-invasive early diagnostic approaches.Methods: In this retrospective study, we analyzed outpatient and inpatient records from the First Medical Center of Chinese PLA General Hospital between 2011 and 2021, focusing on pulmonary nodules measuring 5– 30mm on CT scans without overt signs of malignancy. Pathological examination served as the reference standard. Comparative experiments evaluated SVM, RF, XGBoost, FNN, and Atten_FNN using five-fold cross-validation to assess AUC, sensitivity, and specificity. The dataset was split 70%/30%, and stratified five-fold cross-validation was applied to the training set. The optimal model was interpreted with SHAP to identify the most influential predictive features.Results: This study enrolled 3355 patients, including 1156 with benign and 2199 with malignant pulmonary nodules. The Atten_FNN model demonstrated superior performance in five-fold cross-validation, achieving an AUC of 0.82, accuracy of 0.75, sensitivity of 0.77, and F1 score of 0.80. SHAP analysis revealed key predictive factors: demographic variables (age, sex, BMI), CT-derived features (maximum nodule diameter, morphology, density, calcification, ground-glass opacity), and laboratory biomarkers (neuroendocrine markers, carcinoembryonic antigen).Conclusion: This study integrates electronic medical records and pathology data to predict pulmonary nodule malignancy using machine/deep learning models. SHAP-based interpretability analysis uncovered key clinical determinants. Acknowledging limitations in cross-center generalizability, we propose the development of a multimodal diagnostic systems that combines CT imaging and radiomics, to be validated in multi-center prospective cohorts to facilitate clinical translation. This framework establishes a novel paradigm for early precision diagnosis of lung cancer.Keywords: pulmonary nodules, benignancy, malignancy, machine learning, risk factorshttps://www.dovepress.com/auxiliary-diagnosis-of-pulmonary-nodules-benignancy-and-malignancy-bas-peer-reviewed-fulltext-article-JMDHonary nodulesbenignancymalignancymachine learningrisk factors |
| spellingShingle | Wang W Yang B Wu H Che H Tong Y Zhang B Liu H Chen Y Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study Journal of Multidisciplinary Healthcare onary nodules benignancy malignancy machine learning risk factors |
| title | Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study |
| title_full | Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study |
| title_fullStr | Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study |
| title_full_unstemmed | Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study |
| title_short | Auxiliary Diagnosis of Pulmonary Nodules’ Benignancy and Malignancy Based on Machine Learning: A Retrospective Study |
| title_sort | auxiliary diagnosis of pulmonary nodules amp rsquo benignancy and malignancy based on machine learning a retrospective study |
| topic | onary nodules benignancy malignancy machine learning risk factors |
| url | https://www.dovepress.com/auxiliary-diagnosis-of-pulmonary-nodules-benignancy-and-malignancy-bas-peer-reviewed-fulltext-article-JMDH |
| work_keys_str_mv | AT wangw auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT yangb auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT wuh auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT cheh auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT tongy auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT zhangb auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT liuh auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy AT cheny auxiliarydiagnosisofpulmonarynodulesamprsquobenignancyandmalignancybasedonmachinelearningaretrospectivestudy |