Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma
Аутори
Popović Krneta, MarinaKrajčinović, Nemanja
Bukumirić, Zoran
Tanić, Miljana
Остала ауторства
Morić, IvanaĐorđević, Valentina
Конференцијски прилог (Објављена верзија)
,
© 2023 Institute of Molecular Genetics and Genetic Engineering, University of Belgrade
Метаподаци
Приказ свих података о документуАпстракт
This study aimed to assess and compare four machine learning (ML) based classifiers in
predicting occult cervical lymph node metastasis (LNM) in clinically node-negative (cN0),
T1-T2 papillary thyroid carcinoma (PTC) patients.
The study cohort included 288 PTC patients who underwent total thyroidectomy and
prophylactic central neck dissection with sentinel lymph node biopsy performed for
lateral LNM identification. The classifiers, namely k-Nearest Neighbor (k-NN), Support
Vector Machines, Decision Tree, and Logistic Regression were developed using patients’
demographic and clinicopathological variables. Evaluation metrics such as area under the
receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative
predictive values (PPV and NPV), accuracy, and F1 and F2 scores were utilized for model
comparison.
The final ML classifier was selected based on achieving the highest specificity and the
lowest degree of overfitting while maintaining a se...nsitivity of 95%. Among the evaluated
models, the k-NN emerged as the best-performing, demonstrating an AUC of 0.72. The
sensitivity, specificity, PPV, NPV, F1, and F2 scores were 98%, 27%, 56%, 93%, 72%, and
85%, respectively Furthermore, a web application was developed allowing users to predict
the potential of cervical LNM and explore possibilities for further model development.
The k-NN classifier incorporating patients’ clinicopathological information shows potential
in predicting LNM. Improved prediction models are necessary to identify patients at higher
risk of LNM, guiding appropriate postsurgical treatment for high-risk individuals while
minimizing unnecessary interventions for low-risk patients.
Кључне речи:
machine learning / papillary thyroid carcinoma / lymph node metastasisИзвор:
4th Belgrade Bioinformatics Conference, 2023, 4, 87-87Издавач:
- Belgrade : Institute of molecular genetics and genetic engineering
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200043 (Институт за онкологију и радиологију Србије, Београд) (RS-MESTD-inst-2020-200043)
Напомена:
- Book of abstract: 4th Belgrade Bioinformatics Conference, June 19-23, 2023
Колекције
Институција/група
Institut za molekularnu genetiku i genetičko inženjerstvoTY - CONF AU - Popović Krneta, Marina AU - Krajčinović, Nemanja AU - Bukumirić, Zoran AU - Tanić, Miljana PY - 2023 UR - https://belbi.bg.ac.rs/ UR - https://imagine.imgge.bg.ac.rs/handle/123456789/2032 AB - This study aimed to assess and compare four machine learning (ML) based classifiers in predicting occult cervical lymph node metastasis (LNM) in clinically node-negative (cN0), T1-T2 papillary thyroid carcinoma (PTC) patients. The study cohort included 288 PTC patients who underwent total thyroidectomy and prophylactic central neck dissection with sentinel lymph node biopsy performed for lateral LNM identification. The classifiers, namely k-Nearest Neighbor (k-NN), Support Vector Machines, Decision Tree, and Logistic Regression were developed using patients’ demographic and clinicopathological variables. Evaluation metrics such as area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive values (PPV and NPV), accuracy, and F1 and F2 scores were utilized for model comparison. The final ML classifier was selected based on achieving the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the evaluated models, the k-NN emerged as the best-performing, demonstrating an AUC of 0.72. The sensitivity, specificity, PPV, NPV, F1, and F2 scores were 98%, 27%, 56%, 93%, 72%, and 85%, respectively Furthermore, a web application was developed allowing users to predict the potential of cervical LNM and explore possibilities for further model development. The k-NN classifier incorporating patients’ clinicopathological information shows potential in predicting LNM. Improved prediction models are necessary to identify patients at higher risk of LNM, guiding appropriate postsurgical treatment for high-risk individuals while minimizing unnecessary interventions for low-risk patients. PB - Belgrade : Institute of molecular genetics and genetic engineering C3 - 4th Belgrade Bioinformatics Conference T1 - Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma EP - 87 SP - 87 VL - 4 UR - https://hdl.handle.net/21.15107/rcub_imagine_2032 ER -
@conference{ author = "Popović Krneta, Marina and Krajčinović, Nemanja and Bukumirić, Zoran and Tanić, Miljana", year = "2023", abstract = "This study aimed to assess and compare four machine learning (ML) based classifiers in predicting occult cervical lymph node metastasis (LNM) in clinically node-negative (cN0), T1-T2 papillary thyroid carcinoma (PTC) patients. The study cohort included 288 PTC patients who underwent total thyroidectomy and prophylactic central neck dissection with sentinel lymph node biopsy performed for lateral LNM identification. The classifiers, namely k-Nearest Neighbor (k-NN), Support Vector Machines, Decision Tree, and Logistic Regression were developed using patients’ demographic and clinicopathological variables. Evaluation metrics such as area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive values (PPV and NPV), accuracy, and F1 and F2 scores were utilized for model comparison. The final ML classifier was selected based on achieving the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the evaluated models, the k-NN emerged as the best-performing, demonstrating an AUC of 0.72. The sensitivity, specificity, PPV, NPV, F1, and F2 scores were 98%, 27%, 56%, 93%, 72%, and 85%, respectively Furthermore, a web application was developed allowing users to predict the potential of cervical LNM and explore possibilities for further model development. The k-NN classifier incorporating patients’ clinicopathological information shows potential in predicting LNM. Improved prediction models are necessary to identify patients at higher risk of LNM, guiding appropriate postsurgical treatment for high-risk individuals while minimizing unnecessary interventions for low-risk patients.", publisher = "Belgrade : Institute of molecular genetics and genetic engineering", journal = "4th Belgrade Bioinformatics Conference", title = "Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma", pages = "87-87", volume = "4", url = "https://hdl.handle.net/21.15107/rcub_imagine_2032" }
Popović Krneta, M., Krajčinović, N., Bukumirić, Z.,& Tanić, M.. (2023). Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma. in 4th Belgrade Bioinformatics Conference Belgrade : Institute of molecular genetics and genetic engineering., 4, 87-87. https://hdl.handle.net/21.15107/rcub_imagine_2032
Popović Krneta M, Krajčinović N, Bukumirić Z, Tanić M. Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma. in 4th Belgrade Bioinformatics Conference. 2023;4:87-87. https://hdl.handle.net/21.15107/rcub_imagine_2032 .
Popović Krneta, Marina, Krajčinović, Nemanja, Bukumirić, Zoran, Tanić, Miljana, "Supervised Machine Learning Approach for Prediction of Occult Lymph Node Metastasis in T1-T2 Papillary Thyroid Carcinoma" in 4th Belgrade Bioinformatics Conference, 4 (2023):87-87, https://hdl.handle.net/21.15107/rcub_imagine_2032 .