A Comparative Analysis of Six Machine Learning Models Based on Ultrasound to Distinguish the Possibility of Central Cervical Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma
| Autor: | Fang Sun, Zhi Yang, Guanghe Cui, Ying Zou, Yan Shi, Jihua Liu, Meiling Liu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Cancer Research
030209 endocrinology & metabolism Machine learning computer.software_genre Thyroid carcinoma 03 medical and health sciences 0302 clinical medicine Medicine lymphatic metastasis RC254-282 Original Research business.industry ultrasound Ultrasound Area under the curve Neoplasms. Tumors. Oncology. Including cancer and carcinogens Retrospective cohort study Confidence interval Random forest machine learning Oncology 030220 oncology & carcinogenesis Cohort papillary thyroid carcinoma T-stage Artificial intelligence business computer random forest |
| Zdroj: | Frontiers in Oncology, Vol 11 (2021) Frontiers in Oncology |
| DOI: | 10.3389/fonc.2021.656127/full |
| Popis: | Current approaches to predict central cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) have failed to identify patients who would benefit from preventive treatment. Machine learning has offered the opportunity to improve accuracy by comparing the different algorithms. We assessed which machine learning algorithm can best improve CLNM prediction. This retrospective study used routine ultrasound data of 1,364 PTC patients. Six machine learning algorithms were compared to predict the possibility of CLNM. Predictive accuracy was assessed by sensitivity, specificity, positive predictive value, negative predictive value, and the area under the curve (AUC). The patients were randomly split into the training (70%), validation (15%), and test (15%) data sets. Random forest (RF) led to the best diagnostic model in the test cohort (AUC 0.731 ± 0.036, 95% confidence interval: 0.664–0.791). The diagnostic performance of the RF algorithm was most dependent on the following five top-rank features: extrathyroidal extension (27.597), age (17.275), T stage (15.058), shape (13.474), and multifocality (12.929). In conclusion, this study demonstrated promise for integrating machine learning methods into clinical decision-making processes, though these would need to be tested prospectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|