Postoperative pulmonary complications (PPCs) risk prediction models can help healthcare professionals identify the probability of PPCs occurring in patients after surgery and provide a foundation for rapid decision-making by clinical healthcare professionals. This study evaluated PPCs of lung cancer models' merits, limitations, and challenges, covering construction methods, model performance, and clinical applications. The current risk prediction models for PPCs after lung cancer surgery have a certain predictive effect on the occurrence of PPCs. However, deficiencies persist in study design, clinical implementation, and reporting transparency. Future research should prioritize large-sample, prospective, multi-center studies for multiomics models, ensuring robust data for precise predictions, thereby facilitating clinical translation, adoption, and promotion.
ObjectiveTo explore the papillary thyroid carcinoma (PTC) occurs on the lymph nodes posterior to the right recurrent laryngeal nerve (LN-prRLN) factors that influence the transfer of clinical nomogram prediction model, and build as a reference of LN-prRLN cleaning the decision. MethodsThe clinical data of PTC patients admitted to the General Surgery Department of Baoding No.1 Central Hospital from January 2021 to December 2023 were retrospectively analyzed. Among them, 325 patients underwent LN-prRLN dissection, and they were divided into non-metastatic group (269 cases) and metastasis group (56 cases) according to the presence or absence of LN-prRLN metastasis. By comparing the differences of clinical and pathological characteristics between the two groups, the independent risk factors of LN-prRLN metastasis were analyzed and discussed, and then the nomogram prediction model of LN-prRLN metastasis was constructed with the independent risk factors, and the effectiveness of the model was verified and evaluated. ResultsIn 325 patients, 56 cases (17.23%) occurred LN-prRLN metastasis. The results of univariate analysis showed that gender, extrathyroidal extension, lymph nodes anterior to right recurrent laryngeal nerve (LN-arRLN) metastasis, location of cancer focus, and lateral lymph node metastasis (LLNM) were related to LN-prRLN metastasis of PTC (P<0.05). Multivariate binary logistic regression analysis showed that male [OR=3.878, 95%CI (1.192, 12.615)], with extrathyroidal extension [OR=2.836, 95%CI (1.036, 7.759)], with LN-arRLN metastasis [OR=10.406, 95%CI (3.225, 33.926)], right cancer focus [OR= 5.632, 95%CI (1.812, 17.504)] and with LLNM [OR=3.426, 95%CI (1.147, 10.231)] were independent risk factors of LN-prRLN metastasis. Receiver operating characteristic curves of nomogram prediction model based on the above independent risk factors showed that the area under the curve was 0.865, 95%CI was (0.795, 0.934), Jordan index was 0.729, sensitivity was 0.873, and specificity was 0.856, which had higher prediction value. The C-index of Bootstrap test was 0.84 [95%CI (0.755, 0.954) ]. Calibration curves showed that predictive value close to the ideal curve, had good consistency. The analysis of clinical decision curve showed that the model had good clinical prediction effect on LN-prRLN metastasis of PTC. ConclusionsMale, extrathyroidal extension, LN-arRLN metastasis, right cancer focus and LLNM are independent risk factors for LN-prRLN metastasis of PTC. The nomogram prediction model based on the above independent risk factors has high discrimination and calibration, which is helpful for surgeons to make clinical decisions.