prikaz prve stranice dokumenta Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment
  Download
PDF 3.26 MB
Scientific paper - Original scientific paper
Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment
Cancers, 15 (2023), 3; 634. https://doi.org/10.3390/cancers15030634
Vrdoljak, Josip; Boban, Zvonimir; Barić, Domjan; Šegvić, Darko; Kumrić, Marko; Avirović, Manuela; Perić Balja, Melita; Periša, Marija Milković; Tomasović, Čedna; Tomić, Snježana; Vrdoljak, Eduard; Božić, Joško

Institutional repository: Repository of the University of Rijeka, Faculty of Medicine

Cite this document

Vrdoljak, J., Boban, Z., Barić, D., Šegvić, D., Kumrić, M., Avirović, M. ... Božić, J. (2023). Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment. Cancers, 15. (3). doi: 10.3390/cancers15030634

Vrdoljak, Josip, et al. "Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment." Cancers, vol. 15, no. 3, 2023. https://doi.org/10.3390/cancers15030634

Vrdoljak, Josip, Zvonimir Boban, Domjan Barić, Darko Šegvić, Marko Kumrić, Manuela Avirović, Melita Perić Balja, et al. "Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment." Cancers 15, no. 3 (2023). https://doi.org/10.3390/cancers15030634

Vrdoljak, J., et al. (2023) 'Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment', Cancers, 15(3). doi: 10.3390/cancers15030634

Vrdoljak J, Boban Z, Barić D, Šegvić D, Kumrić M, Avirović M, and sur.. Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment. Cancers [Internet]. 2023 January 19 [cited 2024 December 28];15(3). doi: 10.3390/cancers15030634

J. Vrdoljak, et al., "Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment", Cancers, vol. 15, no. 3, January 2023. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:184:670813. [Accessed: 28 December 2024]

Metadata
Title (english)Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment
AuthorJosip Vrdoljak
AuthorZvonimir Boban
AuthorDomjan Barić
AuthorDarko Šegvić
AuthorMarko Kumrić
AuthorManuela Avirović
AuthorMelita Perić Balja
AuthorMarija Milković Periša
AuthorČedna Tomasović
AuthorSnježana Tomić
AuthorEduard Vrdoljak
AuthorJoško Božić
Author's institutionUniversity of Rijeka
Faculty of Medicine
(Department of General Pathology and Pathological Anatomy)
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Pathology
Scientific / art field,
discipline and subdiscipline		INTERDISCIPLINARY AREAS OF KNOWLEDGE
Biotechnology in Biomedicine (natural science, biomedicine and healthcare, bioethics area
Abstract (english)
Background: Due to recent changes in breast cancer treatment strategy, significantly more patients are treated with neoadjuvant systemic therapy (NST). Radiological methods do not precisely determine axillary lymph node status, with up to 30% of patients being misdiagnosed. Hence, supplementary methods for lymph node status assessment are needed. This study aimed to apply and evaluate machine learning models on clinicopathological data, with a focus on patients meeting NST criteria, for lymph node metastasis prediction. Methods: From the total breast cancer patient data (n = 8381), 719 patients were identified as eligible for NST. Machine learning models were applied for the NST-criteria group and the total study population. Model explainability was obtained by calculating Shapley values. Results: In the NST-criteria group, random forest achieved the highest performance (AUC: 0.793 [0.713, 0.865]), while in the total study population, XGBoost performed the best (AUC: 0.762 [0.726, 0.795]). Shapley values identified tumor size, Ki-67, and patient age as the most important predictors. Conclusion: Tree-based models achieve a good performance in assessing lymph node status. Such models can lead to more accurate disease stage prediction and consecutively better treatment selection, especially for NST patients where radiological and clinical findings are often the only way of lymph node assessment.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleCancers
Numberingvol. 15, no. 3, 634
e-ISSN2072-6694
DOIhttps://doi.org/10.3390/cancers15030634
URN:NBNurn:nbn:hr:184:670813
Publication2023-01-19
Document URLhttps://www.mdpi.com/2072-6694/15/3/634
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2023-01-25 14:15:12