Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy
Background: When obtaining specimens from pulmonary nodules in TBLB, distinguishing between benign samples and mis-sampling from a tumor presents a challenge. Our objective is to develop a machine-learning-based classifier for TBLB specimens. Methods: Three pathologists assessed six pathological fin...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/16/4/731 |
| _version_ | 1797298703681191936 |
|---|---|
| author | Hisao Sano Ethan N. Okoshi Yuri Tachibana Tomonori Tanaka Kris Lami Wataru Uegami Yoshio Ohta Luka Brcic Andrey Bychkov Junya Fukuoka |
| author_facet | Hisao Sano Ethan N. Okoshi Yuri Tachibana Tomonori Tanaka Kris Lami Wataru Uegami Yoshio Ohta Luka Brcic Andrey Bychkov Junya Fukuoka |
| author_sort | Hisao Sano |
| collection | DOAJ |
| description | Background: When obtaining specimens from pulmonary nodules in TBLB, distinguishing between benign samples and mis-sampling from a tumor presents a challenge. Our objective is to develop a machine-learning-based classifier for TBLB specimens. Methods: Three pathologists assessed six pathological findings, including interface bronchitis/bronchiolitis (IB/B), plasma cell infiltration (PLC), eosinophil infiltration (Eo), lymphoid aggregation (Ly), fibroelastosis (FE), and organizing pneumonia (OP), as potential histologic markers to distinguish between benign and malignant conditions. A total of 251 TBLB cases with defined benign and malignant outcomes based on clinical follow-up were collected and a gradient-boosted decision-tree-based machine learning model (XGBoost) was trained and tested on randomly split training and test sets. Results: Five pathological changes showed independent, mild-to-moderate associations (AUC ranging from 0.58 to 0.75) with benign conditions, with IB/B being the strongest predictor. On the other hand, FE emerged to be the sole indicator of malignant conditions with a mild association (AUC = 0.66). Our model was trained on 200 cases and tested on 51 cases, achieving an AUC of 0.78 for the binary classification of benign vs. malignant on the test set. Conclusion: The machine-learning model developed has the potential to distinguish between benign and malignant conditions in TBLB samples excluding the presence or absence of tumor cells, thereby improving diagnostic accuracy and reducing the burden of repeated sampling procedures for patients. |
| first_indexed | 2024-03-07T22:38:48Z |
| format | Article |
| id | doaj.art-91950c92eb05432ba2cd184a156a9679 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-07T22:38:48Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-91950c92eb05432ba2cd184a156a96792024-02-23T15:10:43ZengMDPI AGCancers2072-66942024-02-0116473110.3390/cancers16040731Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung BiopsyHisao Sano0Ethan N. Okoshi1Yuri Tachibana2Tomonori Tanaka3Kris Lami4Wataru Uegami5Yoshio Ohta6Luka Brcic7Andrey Bychkov8Junya Fukuoka9Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki 852-8588, Nagasaki, JapanDepartment of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki 852-8588, Nagasaki, JapanDepartment of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki 852-8588, Nagasaki, JapanDepartment of Diagnostic Pathology, Izumi City General Hospital, Izumi 594-0073, Osaka, JapanDepartment of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki 852-8588, Nagasaki, JapanDepartment of Pathology, Kameda Medical Center, Kamogawa 296-8602, Chiba, JapanDepartment of Diagnostic Pathology, Izumi City General Hospital, Izumi 594-0073, Osaka, JapanDiagnostic and Research Institute of Pathology, Medical University of Graz, 8010 Graz, AustriaDepartment of Pathology, Kameda Medical Center, Kamogawa 296-8602, Chiba, JapanDepartment of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki 852-8588, Nagasaki, JapanBackground: When obtaining specimens from pulmonary nodules in TBLB, distinguishing between benign samples and mis-sampling from a tumor presents a challenge. Our objective is to develop a machine-learning-based classifier for TBLB specimens. Methods: Three pathologists assessed six pathological findings, including interface bronchitis/bronchiolitis (IB/B), plasma cell infiltration (PLC), eosinophil infiltration (Eo), lymphoid aggregation (Ly), fibroelastosis (FE), and organizing pneumonia (OP), as potential histologic markers to distinguish between benign and malignant conditions. A total of 251 TBLB cases with defined benign and malignant outcomes based on clinical follow-up were collected and a gradient-boosted decision-tree-based machine learning model (XGBoost) was trained and tested on randomly split training and test sets. Results: Five pathological changes showed independent, mild-to-moderate associations (AUC ranging from 0.58 to 0.75) with benign conditions, with IB/B being the strongest predictor. On the other hand, FE emerged to be the sole indicator of malignant conditions with a mild association (AUC = 0.66). Our model was trained on 200 cases and tested on 51 cases, achieving an AUC of 0.78 for the binary classification of benign vs. malignant on the test set. Conclusion: The machine-learning model developed has the potential to distinguish between benign and malignant conditions in TBLB samples excluding the presence or absence of tumor cells, thereby improving diagnostic accuracy and reducing the burden of repeated sampling procedures for patients.https://www.mdpi.com/2072-6694/16/4/731transbronchial lung biopsy (TBLB)non-diagnostic samplesDelphi methodinterface bronchitis/bronchiolitis (IB/B)decision-tree based classifiers |
| spellingShingle | Hisao Sano Ethan N. Okoshi Yuri Tachibana Tomonori Tanaka Kris Lami Wataru Uegami Yoshio Ohta Luka Brcic Andrey Bychkov Junya Fukuoka Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy Cancers transbronchial lung biopsy (TBLB) non-diagnostic samples Delphi method interface bronchitis/bronchiolitis (IB/B) decision-tree based classifiers |
| title | Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy |
| title_full | Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy |
| title_fullStr | Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy |
| title_full_unstemmed | Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy |
| title_short | Machine-Learning-Based Classification Model to Address Diagnostic Challenges in Transbronchial Lung Biopsy |
| title_sort | machine learning based classification model to address diagnostic challenges in transbronchial lung biopsy |
| topic | transbronchial lung biopsy (TBLB) non-diagnostic samples Delphi method interface bronchitis/bronchiolitis (IB/B) decision-tree based classifiers |
| url | https://www.mdpi.com/2072-6694/16/4/731 |
| work_keys_str_mv | AT hisaosano machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT ethannokoshi machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT yuritachibana machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT tomonoritanaka machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT krislami machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT wataruuegami machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT yoshioohta machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT lukabrcic machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT andreybychkov machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy AT junyafukuoka machinelearningbasedclassificationmodeltoaddressdiagnosticchallengesintransbronchiallungbiopsy |