Background Few highly accurate tests can diagnose central lymph node metastasis (CLNM) of papillary thyroid cancer (PTC). Genetic sequencing of tumor tissue has allowed the targeting of certain genetic variants for personalized cancer therapy development. Methods This study included 488 patients diagnosed with PTC by ultrasound-guided fine-needle aspiration biopsy, collected clinicopathological data, analyzed the correlation between CLNM and clinicopathological features using univariate analysis and binary logistic regression, and constructed prediction models. Results Binary logistic regression analysis showed that age, maximum diameter of thyroid nodules, capsular invasion, and BRAF V600E gene mutation were independent risk factors for CLNM, and statistically significant indicators were included to construct a nomogram prediction model, which had an area under the curve (AUC) of 0.778. A convolutional neural network (CNN) prediction model built with an artificial intelligence (AI) deep learning algorithm achieved AUCs of 0.89 in the training set and 0.78 in the test set, which indicated a high prediction efficacy for CLNM. In addition, the prediction models were validated in the subclinical metastasis and clinical metastasis groups with high sensitivity and specificity, suggesting the broad applicability of the models. Furthermore, CNN prediction models were constructed for patients with nodule diameters less than 1 cm. The AUCs in the training set and test set were 0.87 and 0.76, respectively, indicating high prediction efficacy. Conclusions The deep learning-based multifeature integration prediction model provides a reference for the clinical diagnosis and treatment of PTC.
Background: Whether tumor mutation burden (TMB) correlated with improved survival outcomes or promotion of immunotherapies remained controversy in various malignancies. We aimed to explore the prognostic value of TMB and the relationship between TMB and immune infiltration in human epidermal growth factor receptor 2-positive (HER2+) breast cancer (BC).Methods: We downloaded somatic mutation data and clinical information for 216 HER2+ BC patients from the The Cancer Genome Atlas (TCGA) and cBioPortal databases. Patients were divided into highand low-TMB groups through TMB calculation. Cox regression analysis was used to establish an immuneand mutant-related risk model based on 5-hub genes. The relationship between 5-hub genes mutants and the level of immune infiltration, as well as the relationship between the risk model and the immune microenvironment were analyzed by "TIMER" database.Results: TMB was negatively correlated with overall survival (OS) and disease-free survival (DFS), and high TMB may inhibit immune infiltration in HER2+ BC. Furthermore, risk score classified effectively patients into low-and high-risk groups in training and validation cohorts. The infiltration of CD4+ T cells and NK cells and the levels of immune checkpoint pathway genes were lower in the high-risk group, which indicated a poor prognosis.Conclusions: Higher TMB correlated with poor survival outcomes and might inhibit the immune infiltrates in HER2+ BC. The 5-hub TMB-related signature conferred lower immune cells infiltration which deserved further validation.
The current diagnostic technologies for assessing the axillary lymph node metastasis (ALNM) status accurately in breast cancer (BC) remain unsatisfactory. Here, we developed a diagnostic model for evaluating the ALNM status using a combination of mRNAs and the T stage of the primary tumor as a novel biomarker. We collected relevant information on T1–2 BC from public databases. An ALNM prediction model was developed by logistic regression based on the screened signatures and then internally and externally validated. Calibration curves and the area under the curve (AUC) were employed as performance metrics. The prognostic value and tumor immune infiltration of the model were also determined. An optimal diagnostic model was created using a combination of 11 mRNAs and T stage of the primary tumor and showed high discrimination, with AUCs of 0.828 and 0.746 in the training sets. AUCs of 0.671 and 0.783 were achieved in the internal validation cohorts. The mean external AUC value was 0.686 and ranged between 0.644 and 0.742. Moreover, the new model has good specificity in T1 and hormone receptor-negative/human epidermal growth factor receptor 2- negative (HR−/HER2−) BC and good sensitivity in T2 BC. In addition, the risk of ALNM and 11 mRNAs were correlated with the infiltration of M2 macrophages, as well as the prognosis of BC. This novel prediction model is a useful tool to identify the risk of ALNM in T1–2 BC patients, particularly given that it can be used to adjust surgical options in the future.
The current diagnostic technologies for assessing the axillary lymph node metastasis (ALNM) status accurately in breast cancer (BC) remain unsatisfactory. Here, we developed a diagnostic model for evaluating the ALNM status using a combination of mRNAs and the T stage of the primary tumor as a novel biomarker. We collected relevant information on T1-2 BC from public databases. An ALNM prediction model was developed by logistic regression based on the screened signatures and then internally and externally validated. Calibration curves and the area under the curve (AUC) were employed as performance metrics. The prognostic value and tumor immune infiltration of the model were also determined. An optimal diagnostic model was created using a combination of 11 mRNAs and T stage of the primary tumor and showed high discrimination, with AUCs of 0.828 and 0.746 in the training sets. AUCs of 0.671 and 0.783 were achieved in the internal validation cohorts. The mean external AUC value was 0.686 and ranged between 0.644 and 0.742. Moreover, the new model has good specificity in T1 and hormone receptor-negative/human epidermal growth factor receptor 2- negative (HR-/HER2-) BC and good sensitivity in T2 BC. In addition, the risk of ALNM and 11 mRNAs were correlated with the infiltration of M2 macrophages, as well as the prognosis of BC. This novel prediction model is a useful tool to identify the risk of ALNM in T1-2 BC patients, particularly given that it can be used to adjust surgical options in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.