Background <p>This study aimed to develop a nomogram based on Ultrasound features for predicting the probability of central lymph node metastases (CLNM) in patients diagnosed with papillary thyroid microcarcinoma (PTMC).</p> Methods <p>A total of 670 patients with histologically confirmed PTMC between 2021 and 2024 were included in this retrospective study and divided into the training (<i>n</i> = 469) and validation (<i>n</i> = 201) cohorts. Through least absolute shrinkage and selection operator (LASSO) regression analysis on the training cohort, we identified the most effective predictors. These predictors were then used to construct a nomogram. We evaluated the nomogram’s discrimination, calibration, and clinical usefulness in the validation cohort using receiver operating characteristic (ROC) analysis, calibration plots, and decision curve analysis.</p> Results <p>After applying LASSO and logistic regression screening with criteria for retaining non-zero coefficients, several factors were found to be independently linked to CLNM in PTMC patients. A nomogram model was subsequently developed to predict the risk of CLNM in PTMC patients based on the predictors. The AUC (C-statistic) of the nomogram was 0.73 (95% CI: 0.68–0.77) for the training cohort and 0.77 (95% CI: 0.70–0.83) for the validation cohort. Decision curve analysis (DCA) demonstrated that the model achieved a higher net benefit than the baseline strategy within the threshold probability ranges of 17%–88% in the training cohort and 10%–76% in the validation cohort.</p> Conclusions <p>This ultrasound-based nomogram, incorporating relevant clinical characteristics, holds promise as a valuable clinical instrument capable of furnishing essential information to guide treatment decisions.</p> Trial registration <p>Not applicable.</p>