Application of machine learning methods to guide patient management by predicting the risk of malignancy of Bethesda III-V thyroid nodules

Abstract

Objective Indeterminate thyroid nodules (ITN) are common and often lead to (sometimes unnecessary) diagnostic surgery. We aimed to evaluate the performance of two machine learning methods (ML), based on routinely available features to predict the risk of malignancy (RM) of ITN. Design Multicentric diagnostic retrospective cohort study conducted between 2010 and 2020. Methods Adult patients who underwent surgery for at least one Bethesda III-V thyroid nodule (TN) with fully available medical records were included. Of the 7,917 records reviewed, eligibility criteria were met in 1,288 patients with 1,335 TN. Patients were divided in a training (940 TN) and validation cohort (395 TN). The diagnostic performance of a multivariate logistic regression model (LR) and its nomogram, and a random forest model (RF) in predicting the nature and RM of a TN were evaluated. All available clinical, biological, ultrasound, and cytological data of the patients were collected and used to construct the two algorithms. Results There were 253 (19%), 693 (52%) and 389 (29%) TN classified as Bethesda III, IV and V respectively, with an overall RM of 35%. Both cohorts were well balanced for baseline characteristics. Both models were validated on the validation cohort, with performances in terms of specificity, sensitivity, positive predictive value, negative predictive value and area under the receiver operating characteristic curve of 90%, 57.3%, 73.4%, 81.4%, 84% (CI95%: 78.5–89.5%) for the LR model, and 87.6%, 54.7%, 68.1%, 80%, 82.6% (CI95%: 77.4–87.9%) for the RF model, respectively. Conclusions Our ML models performed well in predicting the nature of Bethesda III-V TN. In addition, our freely available online nomogram helped to refine the RM, identifying low-risk TN that may benefit from surveillance in up to a third of ITN, and thus may reduce the number of unnecessary surgeries.

Diagnostic models for predicting malignancy in thyroid nodules classified as Bethesda Category III in an endemic region

“…26 Our study appears to have a broader scope than many previous studies on AUS. While prior research has primarily focused on clinical and ultrasound (USG) variables or demographic and pathological variables, [27][28][29][30][31] in this study includes a comprehensive examination of clinical, USG, and cytopathological (not routinely examined, all presented in Tables 1 and 2) variables. This comprehensive approach could potentially provide a more detailed understanding of AUS.…”

Recent Advances in the Surgical Management of Thyroid Cancer

“…Promising new biomarkers have been identified in the tumor microenvironment and, in particular, in the tumor immune infiltrate and could lead to significant improvements in the diagnostic performance of thyroid molecular tests in the near future [22]. Machine learning methods combining both clinical, US, and cytological data could help to better predict the risk of malignancy specific to each patient [23]. They could also integrate, in the near future, the results of the molecular tests mentioned above.…”