Liu J, et al. - In order to establish a practical model for thyroid nodule discrimination, this study was undertaken. Researchers proposed that a predictive model of malignancy that combines clinical, laboratory and sonographic characteristics would aid clinicians in avoiding unnecessary procedures and making better clinical decisions.

• Researchers analyzed records for 2984 patients who underwent thyroidectomy.
• They retrospectively evaluated Clinical, laboratory, and US variables.
• They carried out multivariate logistic regression analysis and established a mathematical model for malignancy prediction.

• It was noted that the malignant group was younger and had smaller nodules than the benign group (43.5 ± 11.6 vs 48.5 ± 11.5 y, p < 0.001; 1.96 ± 1.16 vs 2.75 ± 1.70 cm, p < 0.001, respectively).
• In the malignant group vs in the benign group, higher serum thyrotropin (TSH) level (median = 1.63 mIU/L, IQR (0.89–2.66) vs 1.19 (0.59–2.10), p < 0.001) was reported.
• Researchers noted that patients with malignancies tested positive for anti-thyroglobulin antibody (TGAb) and anti-thyroid peroxidase antibody (TPOAb) more frequently than those with benign nodules (TGAb, 30.3% vs 15.0%, p < 0.001; TPOAb, 25.6% vs 18.0%, p=0.028).
• In the malignant group, significantly higher prevalence of ultrasound (US) features (irregular shape, ill-defined margin, solid structure, hypoechogenicity, microcalcifications, macrocalcifications and central intranodular flow) was noted.
• It was confirmed in multivariate logistic regression analysis that thyroid malignancy was independently predicted by age (OR = 0.963, 95% CI = 0.934–0.993, p=0.017), TGAb (OR = 4.435, 95% CI = 1.902–10.345, p=0.001), hypoechogenicity (OR = 2.830, 95% CI = 1.113–7.195, p=0.029), microcalcifications (OR = 4.624, 95% CI = 2.008–10.646, p < 0.001), and central intranodular flow (OR = 2.155, 95% CI = 1.011–4.594, p < 0.05).
• Notably, an optimal discriminatory accuracy (area under the curve, AUC) of 0.808 (95% CI = 0.761–0.855) was demonstrated by a predictive model including 4 variables (age, TGAb, hypoechogenicity and microcalcification).
• The best cut-off value for prediction was 0.52, achieving sensitivity and specificity of 84.6% and 76.3%, respectively.