BackgroundCurrently, the high morbidity of individuals with thyroid cancer (TC) is an increasing health care burden worldwide. The aim of our study was to investigate the relationship among the gut microbiota community, metabolites, and the development of differentiated thyroid cancer.Methods16S rRNA gene sequencing and an integrated LC–MS-based metabolomics approach were performed to obtain the components and characteristics of fecal microbiota and metabolites from 50 patients with TC and 58 healthy controls (HCs).ResultsThe diversity and richness of the gut microbiota in the TC patients were markedly decreased. The composition of the gut microbiota was significantly altered, and the Bacteroides enterotype was the dominant enterotype in TC patients. Additionally, the diagnostic validity of the combined model (three genera and eight metabolites) and the metabolite model (six metabolites) were markedly higher than that of the microbial model (seven genera) for distinguishing TC patients from HCs. LEfSe analysis demonstrated that genera (g_Christensenellaceae_R-7_group, g_Eubacterium_coprostanoligenes_group) and metabolites [27-hydroxycholesterol (27HC), cholesterol] closely related to lipid metabolism were greatly reduced in the TC group. In addition, a clinical serum indicator (total cholesterol) and metabolites (27HC and cholesterol) had the strongest influence on the sample distribution. Furthermore, functional pathways related to steroid biosynthesis and lipid digestion were inhibited in the TC group. In the microbiota-metabolite network, 27HC was significantly related to metabolism-related microorganisms (g_Christensenellaceae_R-7_group).ConclusionsOur research explored the characteristics of the gut microecology of patients with TC. The findings of this study will help to discover risk factors that affect the occurrence and development of TC in the intestinal microecology.
Objective To explore the differential diagnostic efficiency of the residual network (ResNet)50, random forest (RF), and DS ensemble models for papillary thyroid carcinoma (PTC) and other pathological types of thyroid nodules. Methods This study retrospectively analyzed 559 patients with thyroid nodules and collected thyroid pathological images and auxiliary examination results (laboratory and ultrasound results) to construct datasets. The pathological image dataset was used to train a ResNet50 model, the text dataset was used to train a random forest (RF) model, and a DS ensemble model was constructed from the results of the two models. The differential diagnostic values of the three models for PTC and other types of thyroid nodules were then compared. Results The DS ensemble model had the highest sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (85.87%, 97.18%, 93.77%, and 0.982, respectively). Conclusions Compared with Resnet50 and the RF models trained only on imaging data or text information, respectively, the DS ensemble model showed better diagnostic value for PTC.
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.