Work

Development and Validation of a Routine Clinical Indicator-Based Predictive Model for Malignancy Risk Stratification in Thyroid Nodules

Year: 2026
Type: preprint
Study design: Observational Study
Abstract: Objective To develop and validate a predictive model based on routine clinical indicators for assessing the risk of malignancy in thyroid nodules, thereby providing a reference for the preoperative differentiation of papillary thyroid carcinoma. Methods A total of 1,754 patients with thyroid nodules who underwent thyroidectomy at Longyan First Hospital from January 2021 to December 2023 were retrospectively enrolled, including 754 patients with benign nodules and 1,000 patients with papillary thyroid carcinoma(PTC). Data on thyroid function, thyroid autoantibodies, inflammatory markers, biochemical parameters, and nodule volume were collected. Variables were selected using LASSO regression and the Boruta algorithm, followed by bidirectional stepwise selection based on the Akaike Information Criterion to construct the final multivariable logistic regression model. Results The final model included six predictors: nodule volume, FT3, FT4, TSH, serum total protein, and total bilirubin. The model demonstrated good discrimination, with AUC values of approximately 0.87 in the training cohort and 0.86 in the validation cohort, as well as favorable calibration and clinical net benefit. Conclusion This study developed a prediction model for differentiating papillary thyroid carcinoma from benign thyroid nodules based on nodule volume, FT3, FT4, TSH, total bilirubin, and serum total protein. Trial registration Clinical trial number not applicable
Language: English
Field: Medicine
Open Access status: green
OpenAlex ID: W7225876364
Cites: 24
Cited by:
Related to: 10