Objective To investigate the risk factors for postoperative cognitive dysfunction in elderly patients with thyroid carcinoma (TC) and to establish a Nomogram prediction model. Methods A total of 315 elderly patients with TC who underwent surgical treatment at Zhengzhou Central Hospital Affiliated to Zhengzhou University from March 2023 to March 2025 were enrolled. Based on the Montreal cognitive assessment (MoCA) scores, patients were divided into cognitive dysfunction group (n＝233) and noncognitive dysfunction group (n＝82). Logistic regression analysis was used to identify factors influencing postoperative cognitive dysfunction in elderly TC patients, and a Nomogram model was constructed based on these independent risk factors. The receiver operator characteristic (ROC) curve was plotted, and the area under the curve (AUC) was calculated to evaluate the discrimination performance of the model; the calibration curve was plotted to assess the calibration degree of the model. Results The age and the proportion of those with a high school education or above in the non-cognitive dysfunction group were higher than those in the cognitive dysfunction group, and the score of the perceived social support scale (PSSS) were higher in the non-cognitive dysfunction group (all P＜0.05). Additionally, the non-cognitive dysfunction group group had lower postoperative numerical rating scale (NRS) scores, Pittsburgh sleep quality index (PSQI) scores, Hamilton anxiety scale (HAMA) scores, and Hamilton depression scale (HAMD) scores than the cognitive dysfunction group (all P＜0.05). Logistic regression analysis revealed that age (OR＝1.087), education level of junior high school or below (OR＝ 1.732), elevated postoperative NRS score (OR＝1.609), elevated PSQI score (OR＝2.081), elevated HAMA score (OR＝1.302), and elevated HAMD score (OR＝1.414) were independent risk factors for postoperative cognitive dysfunction in elderly TC patients (all P＜ 0.05). Conversely, an increased PSSS score (OR＝0.830) served as a protective factor (P＜0.05). The Nomogram model demonstrated good predictive performance with a C-index of 0.955 (95%CI: 0.899-0.989). The AUC for prediction model was 0.950 (95%CI: 0.923- 0.977). Conclusion Age, education level, postoperative NRS score, PSQI score, HAMA score, HAMD score, and PSSS score are significant influencing factors for postoperative cognitive dysfunction in elderly patients with TC. The established Nomogram model based on the above influencing factors possesses a high predictive value.