Real-life utility of five-gene panel test in preoperative thyroid fine-needle aspiration biopsy: a large cohort of 740 patients study.

PURPOSE: Fine-needle aspiration (FNA) biopsy is an effective method to discriminate malignant thyroid nodules but reaches indeterminate results in approximately 30% of cases. Molecular testing can improve the diagnostic accuracy of FNA. This study aimed to investigate the real-life utility of the five-gene panel testing in thyroid FNAs. METHODS: 759 thyroid nodules from 740 patients under FNAs were retrospectively enrolled. Gene mutation information and clinical parameters, including age, gender, tumor size, and lymph node metastasis, were respectively recorded. Cytological results were classified based on The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). We analyzed mutational hotspots in BRAF, KRAS, NRAS, HRAS, and TERT genes from FNA specimens. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated to assess diagnostic performance. RESULTS: We identified 549 five-gene mutations in 759 nodules (72.3%), and the mutation frequency increased from the lower TBSRTC category to the upper category. BRAF.p.V600E showed the highest mutation incidence (71.3%) in the five-gene panel, correlated with the small to medium diameter (p = 0.008, p = 0.012) and high cytological categories (p < 0.001). The sensitivity, specificity, PPV, NPV, and accuracy of the combination of FNA cytology and five-gene detection were 96.83%, 100%, 100%, 42.86%, and 96.90%, respectively. CONCLUSIONS: The mutation frequency of the five-gene panel is 72.3% in thyroid FNAs. BRAF.p.V600E has the highest alteration rate, which is closely associated with tumor size and cytological results. The five-gene panel can improve the sensitivity and accuracy of FNA cytology, which may represent a valid adjunct technique in distinguishing thyroid nodules.

Environmental and social determinants of thyroid cancer: A spatial analysis based on the Geographical Detector.

Introduction: Thyroid cancer has increased sharply in China in recent years. This change may be attributable to multiple factors. The current study aimed to explore the environmental and social determinants of thyroid cancer. Methods: Incidence data from 487 cancer registries in 2016 were collected. Eight factors were considered, namely, air pollution, green space, ambient temperature, ultraviolet radiation, altitude, economic status, healthcare, and education level. A geographical detector (measured by q statistic) was used to evaluate the independent and interactive impact of the eight factors on thyroid cancer. Results: Social factors, especially economic status and healthcare level (q > 0.2), were most influential on thyroid cancer.Ultraviolet radiation, air pollution, and temperature had more impact on women, while green space and altitude had more influence on men. Enhanced effects were observed when two factors interacted. Spatially, economic status, healthcare, and air pollution were positively associated with thyroid cancer, while education level, green space, and altitude were negatively related to thyroid cancer. Conclusion: The socio-environmental determinants and spatial heterogeneity of thyroid cancer were observed in this study. These findings may improve our understanding of thyroid cancer epidemiology and help guide public health interventions.

Constructing tongue coating recognition model using deep transfer learning to assist syndrome diagnosis and its potential in noninvasive ethnopharmacological evaluation.

ETHNOPHARMACOLOGICAL RELEVANCE: Tongue coating has been used as an effective signature of health in traditional Chinese medicine (TCM). The level of greasy coating closely relates to the strength of dampness or pathogenic qi in TCM theory. Previous empirical studies and our systematic review have shown the relation between greasy coating and various diseases, including gastroenteropathy, coronary heart disease, and coronavirus disease 2019 (COVID-19). However, the objective and intelligent greasy coating and related diseases recognition methods are still lacking. The construction of the artificial intelligent tongue recognition models may provide important syndrome diagnosis and efficacy evaluation methods, and contribute to the understanding of ethnopharmacological mechanisms based on TCM theory. AIM OF THE STUDY: The present study aimed to develop an artificial intelligent model for greasy tongue coating recognition and explore its application in COVID-19. MATERIALS AND METHODS: Herein, we developed greasy tongue coating recognition networks (GreasyCoatNet) using convolutional neural network technique and a relatively large (N = 1486) set of tongue images from standard devices. Tests were performed using both cross-validation procedures and a new dataset (N = 50) captured by common cameras. Besides, the accuracy and time efficiency comparisons between the GreasyCoatNet and doctors were also conducted. Finally, the model was transferred to recognize the greasy coating level of COVID-19. RESULTS: The overall accuracy in 3-level greasy coating classification with cross-validation was 88.8% and accuracy on new dataset was 82.0%, indicating that GreasyCoatNet can obtain robust greasy coating estimates from diverse datasets. In addition, we conducted user study to confirm that our GreasyCoatNet outperforms TCM practitioners, yet only consuming roughly 1% of doctors' examination time. Critically, we demonstrated that GreasyCoatNet, along with transfer learning, can construct more proper classifier of COVID-19, compared to directly training classifier on patient versus control datasets. We, therefore, derived a disease-specific deep learning network by finetuning the generic GreasyCoatNet. CONCLUSIONS: Our framework may provide an important research paradigm for differentiating tongue characteristics, diagnosing TCM syndrome, tracking disease progression, and evaluating intervention efficacy, exhibiting its unique potential in clinical applications.