Search Results
Search for other papers by Roberto Negro in
Google Scholar
PubMed
Search for other papers by Matteo Rucco in
Google Scholar
PubMed
Search for other papers by Annalisa Creanza in
Google Scholar
PubMed
Search for other papers by Alberto Mormile in
Google Scholar
PubMed
Search for other papers by Paolo Piero Limone in
Google Scholar
PubMed
Search for other papers by Roberto Garberoglio in
Google Scholar
PubMed
Search for other papers by Stefano Spiezia in
Google Scholar
PubMed
Search for other papers by Salvatore Monti in
Google Scholar
PubMed
Search for other papers by Christian Cugini in
Google Scholar
PubMed
Search for other papers by Ghassan El Dalati in
Google Scholar
PubMed
Search for other papers by Maurilio Deandrea in
Google Scholar
PubMed
Background: Radiofrequency (RF) is a therapeutic modality for reducing the volume of large benign thyroid nodules. If thermal therapies are interpreted as an alternative strategy to surgery, critical issues in their use are represented by the extent of nodule reduction and by the durability of nodule reduction over a long period of time. Objective: To assess the ability of machine learning to discriminate nodules with volume reduction rate (VRR) < or ≥50% at 12 months following RF treatment. Methods: A machine learning model was trained with a dataset of 402 cytologically benign thyroid nodules subjected to RF at six Italian Institutions. The model was trained with the following variables: baseline nodule volume, echostructure, macrocalcalcifications, vascularity, and 12-month VRR. Results: After training, the model could distinguish between nodules having VRR <50% from those having VRR ≥50% in 85% of cases (accuracy: 0.85; 95% confidence interval [CI]: 0.80–0.90; sensitivity: 0.70; 95% CI: 0.62–0.75; specificity: 0.99; 95% CI: 0.98–1.0; positive predictive value: 0.95; 95% CI: 0.92–0.98; negative predictive value: 0.95; 95% CI: 0.92–0.98). Conclusions: This study demonstrates that a machine learning model can reliably identify those nodules that will have VRR < or ≥50% at 12 months after one RF treatment session. Predicting which nodules will be poor or good responders represents valuable data that may help physicians and patients decide on the best treatment option between thermal ablation and surgery or in predicting if more than one session might be necessary to obtain a significant volume reduction.
Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy
Search for other papers by Laura Fugazzola in
Google Scholar
PubMed
Search for other papers by Maurilio Deandrea in
Google Scholar
PubMed
Search for other papers by Stefano Borgato in
Google Scholar
PubMed
Search for other papers by Marco Dell’Acqua in
Google Scholar
PubMed
Search for other papers by Francesca Retta in
Google Scholar
PubMed
Search for other papers by Alberto Mormile in
Google Scholar
PubMed
Search for other papers by Chiara Carzaniga in
Google Scholar
PubMed
Search for other papers by Giacomo Gazzano in
Google Scholar
PubMed
Search for other papers by Gabriele Pogliaghi in
Google Scholar
PubMed
Search for other papers by Marina Muzza in
Google Scholar
PubMed
Department of Medical Biotechnology and Translational Medicine, University of Milan, Milan, Italy
Search for other papers by Luca Persani in
Google Scholar
PubMed
Background
Radiofrequency ablation (RFA) is effective in the treatment of thyroid nodules, leading to a 50–90% reduction with respect to baseline. Current guidelines indicate the need for a benign cytology prior to RFA, though, on the other side, this procedure is also successfully used for the treatment of papillary microcarcinomas. No specific indications are available for nodules with an indeterminate cytology (Bethesda III/IV).
Aim
To evaluate the efficacy of RFA in Bethesda III nodules without genetic alterations as verified by means of a custom panel.
Methods
We have treated 33 patients (mean delivered energy 1069 ± 1201 J/mL of basal volume) with Bethesda III cytology, EU-TIRADS 3-4, and negative genetic panel. The mean basal nodular volume was 17.3 ± 10.7 mL.
Results
Considering the whole series, the mean volume reduction rate (VRR) was 36.8 ± 16.5% at 1 month, 59.9 ± 15.5% at 6 months, and 62 ± 15.7% at 1-year follow-up. The sub-analysis done in patients with 1 and 2 years follow-up data available (n = 20 and n = 5, respectively) confirmed a progressive nodular volume decrease. At all-time points, the rate of reduction was statistically significant (P < 0.0001), without significant correlation between the VRR and the basal volume. Neither cytological changes nor complications were observed after the procedure.
Conclusion
RFA is effective in Bethesda III, oncogene-negative nodules, with reduction rates similar to those obtained in confirmed benign lesions. This procedure represents a good alternative to surgery or active surveillance in this particular class of nodules, regardless of their initial volume. A longer follow-up will allow to evaluate further reduction or possible regrowth.
