A predictive model using platelets and neutrophil-to-lymphocyte ratio for the number of lymph node metastases in papillary thyroid carcinoma: a retrospective analysis.

BACKGROUND

Large number lymph node metastases (LNLNMs) in papillary thyroid carcinoma (PTC) significantly increase recurrence risk, yet preoperative prediction remains challenging. This study aimed to develop a predictive model integrating blood inflammatory markers and clinical features to identify patients with high-risk LNLNM.

METHODS

A retrospective cohort of 731 patients with PTC who underwent thyroid surgery at Hangzhou First People's Hospital between September 2021 and October 2022 was included. These patients were divided into a model group (n=513) and a validation group (n=218) at a 7:3 ratio. Analyzed variables included age, gender, absolute values of neutrophils (N), monocytes (M), platelets (Plt), and lymphocytes (L), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), lymphocyte-to-monocyte ratio (LMR), systemic immune-inflammatory index (SII), and tumor diameter and multifocality. Independent risk factors for LNLNM were identified through univariate and multivariate logistic regression analyses, and a risk prediction model was subsequently constructed. Model performance was assessed via receiver operating characteristic (ROC) curves, the Hosmer-Lemeshow (HL) test, calibration curves, and decision curve analysis (DCA).

RESULTS

Age, tumor diameter, Plt, and NLR were identified as independent risk factors for LNLNM in patients with PTC. A predictive model was developed to evaluate the risk of LNLNM, with an area under the curve (AUC) of 0.827 (95% CI: 0.784-0.870; P<0.001) and the specificity and sensitivity were both 75.8%. The AUC of the validation group was 0.824 (95% CI: 0.757-0.890; P<0.001), with a specificity of 79.5% and a sensitivity of 76.9%. Furthermore, the model demonstrated good calibration in the HL test and favorable diagnostic value in calibration curve analysis and DCA.

CONCLUSIONS

Age, tumor diameter, Plt count, and NLR count are high-risk factors for LNLNM in patients with PTC, and the predictive model established in combination with the above factors could effectively predict the occurrence of LNLNMs in PTC. This study provides support for surgeons in accurately predicting the possibility of LNLNMs and developing personalized treatment plans before surgery.