A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence
Frontiers in Medicine · مج 11 · 1461372-1461372 · 2024
الملخّص
Background: Differentiated thyroid cancer (DTC) is the most prevalent endocrine malignancy with a recurrence rate of about 20%, necessitating better predictive methods for patient management. This study aims to create a relational classification model to predict DTC recurrence by integrating clinical, pathological, and follow-up data. Methods: The balanced dataset comprises 550 DTC samples collected over 15 years, featuring 13 clinicopathological variables. To address the class imbalance in recurrence status, the Synthetic Minority Over-sampling Technique for Nominal and Continuous (SMOTE-NC) was utilized. A hybrid model combining classification algorithms with association rule mining was developed. Two relational classification approaches, regularized class association rules (RCAR) and classification based on association rules (CBAR), were implemented. Binomial logistic regression analyzed independent predictors of recurrence. Model performance was assessed through accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. Results: The RCAR model demonstrated superior performance over the CBAR model, achieving accuracy, sensitivity, and F1 score of 96.7%, 93.1%, and 96.7%, respectively. Association rules highlighted that papillary pathology with an incomplete response strongly predicted recurrence. The combination of incomplete response and lymphadenopathy was also a significant predictor. Conversely, the absence of adenopathy and complete response to treatment were linked to freedom from recurrence. Incomplete structural response was identified as a critical predictor of recurrence risk, even with other low-recurrence conditions. Conclusion: This study introduces a robust and interpretable predictive model that enhances personalized medicine in thyroid cancer care. The model effectively identifies high-risk individuals, allowing for tailored follow-up strategies that could improve patient outcomes and optimize resource allocation in DTC management.
التفاصيل
- المجلة
- Frontiers in Medicine
- الناشر
- Frontiers Media
- المجلد
- 11
- العدد
- —
- الصفحات
- 1461372-1461372
- الترقيم الدولي ISSN
- 2296-858X
- السنة
- 2024
- اللغة
- en
- الترخيص
- cc-by
- الوصول المفتوح
- gold
- الاستشهادات
- 24
- المصدر
- scopus
الكلمات المفتاحية
الموضوعات
Thyroid Cancer Diagnosis and Treatment (Medicine) · Artificial Intelligence in Healthcare (Health Professions) · Data Mining and Machine Learning Applications (Computer Science)
استشهد بهذا
Atay, F. F., Yağın, F. H., Çolak, C., Elkıran, E. T., Mansuri, N., Ahmad, F., Ardigò, L. P. (2024). A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence. Frontiers in Medicine, 11, 1461372-1461372. https://doi.org/10.3389/fmed.2024.1461372
Atay, F. F., Yağın, F. H., Çolak, C., Elkıran, E. T., Mansuri, N., Ahmad, F., Ardigò, L. P. 2024, 'A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence', Frontiers in Medicine, vol. 11, 1461372-1461372. Available at: https://doi.org/10.3389/fmed.2024.1461372
Atay FF, Yağın FH, Çolak C, Elkıran ET, Mansuri N, Ahmad F, Ardigò LP. A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence. Frontiers in Medicine. 2024;11, 1461372-1461372.
@article{atay20241137,
title = {A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence},
author = {Feyza Firat Atay and Fatma Hilal Yağın and Cemil Çolak and Emin Tamer Elkıran and Nasrin Mansuri and Fuzail Ahmad and Luca Paolo Ardigò},
year = {2024},
journal = {Frontiers in Medicine},
volume = {11},
pages = {1461372-1461372},
publisher = {Frontiers Media},
doi = {10.3389/fmed.2024.1461372},
url = {https://doi.org/10.3389/fmed.2024.1461372}
}TY - JOUR AU - Feyza Firat Atay AU - Fatma Hilal Yağın AU - Cemil Çolak AU - Emin Tamer Elkıran AU - Nasrin Mansuri AU - Fuzail Ahmad AU - Luca Paolo Ardigò TI - A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence PY - 2024 JO - Frontiers in Medicine VL - 11 SP - 1461372-1461372 DO - 10.3389/fmed.2024.1461372 UR - https://doi.org/10.3389/fmed.2024.1461372 ER -
