RESUMEN
BACKGROUND: This study is to propose a clinically applicable 2-echelon (2e) diagnostic criteria for the analysis of thyroid nodules such that low-risk nodules are screened off while only suspicious or indeterminate ones are further examined by histopathology, and to explore whether artificial intelligence (AI) can provide precise assistance for clinical decision-making in the real-world prospective scenario. METHODS: In this prospective study, we enrolled 1036 patients with a total of 2296 thyroid nodules from three medical centers. The diagnostic performance of the AI system, radiologists with different levels of experience, and AI-assisted radiologists with different levels of experience in diagnosing thyroid nodules were evaluated against our proposed 2e diagnostic criteria, with the first being an arbitration committee consisting of 3 senior specialists and the second being cyto- or histopathology. RESULTS: According to the 2e diagnostic criteria, 1543 nodules were classified by the arbitration committee, and the benign and malignant nature of 753 nodules was determined by pathological examinations. Taking pathological results as the evaluation standard, the sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) of the AI systems were 0.826, 0.815, 0.821, and 0.821. For those cases where diagnosis by the Arbitration Committee were taken as the evaluation standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.946, 0.966, 0.964, and 0.956. Taking the global 2e diagnostic criteria as the gold standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.868, 0.934, 0.917, and 0.901, respectively. Under different criteria, AI was comparable to the diagnostic performance of senior radiologists and outperformed junior radiologists (all P < 0.05). Furthermore, AI assistance significantly improved the performance of junior radiologists in the diagnosis of thyroid nodules, and their diagnostic performance was comparable to that of senior radiologists when pathological results were taken as the gold standard (all p > 0.05). CONCLUSIONS: The proposed 2e diagnostic criteria are consistent with real-world clinical evaluations and affirm the applicability of the AI system. Under the 2e criteria, the diagnostic performance of the AI system is comparable to that of senior radiologists and significantly improves the diagnostic capabilities of junior radiologists. This has the potential to reduce unnecessary invasive diagnostic procedures in real-world clinical practice.
Asunto(s)
Inteligencia Artificial , Nódulo Tiroideo , Ultrasonografía , Humanos , Estudios Prospectivos , Nódulo Tiroideo/diagnóstico por imagen , Nódulo Tiroideo/patología , Femenino , Masculino , Persona de Mediana Edad , Adulto , Ultrasonografía/métodos , Radiólogos , Anciano , Glándula Tiroides/diagnóstico por imagen , Sensibilidad y Especificidad , Adulto Joven , AdolescenteRESUMEN
ETHNOPHARMACOLOGICAL RELEVANCE: Epimedium sagittatum (Sieb. et Zucc.) Maxim. has been used traditionally in Asia. It can dispel wind and cold, tonify the kidney, and strengthen bones and tendons. However, adverse effects of E. sagittatum have been reported, and the underlying mechanisms remain unclear. AIM OF THE STUDY: This study aimed to investigate liver injury caused by an aqueous extract of E. sagittatum in Institute of Cancer Research (ICR) mice and explore its potential mechanisms. MATERIALS AND METHODS: Dried E. sagittatum leaves were decocted in water to prepare aqueous extracts for ultra-high performance liquid chromatography analysis. Mice were administered an aqueous extract of E. sagittatum equivalent to either 3 g raw E. sagittatum/kg or 10 g raw E. sagittatum/kg once daily via intragastric injection for three months. The liver weights and levels of the serum biochemical parameters including alanine transaminase (ALT), aspartate aminotransferase (AST), lactate dehydrogenase (LDH), total bilirubin (TBIL), and alkaline phosphatase were measured. Hematoxylin-eosin staining was performed for histopathology. Apoptosis was detected using the TUNEL apoptosis assay kit. IL-1ß was detected using ELISA kits. Proteomics was used to identify the differentially expressed proteins. Western blot analysis was performed to determine the levels of proteins significantly affected by the aqueous extract of E. sagittatum. RESULTS: E. sagittatum treatment increased the liver weights and liver coefficients, and ALT and AST levels significantly increased (p < 0.05). A high dose of E. sagittatum significantly increased LDH and TBIL levels (p < 0.05). Ruptured cell membranes and multiple sites of inflammatory cell infiltration were also observed. No evidence of apoptosis was observed. IL-1ß levels were significantly increased (p < 0.05). The expressions of PIK3R1, p-MAP2K4, p-Jun N-terminal kinase (JNK)/JNK, p-c-Jun, VDAC2, Bax, and CYC were upregulated, whereas that of Bcl-2 was inhibited by E. sagittatum. The expression of cleaved caspase-1 was significantly increased; however, its effects on GSDMD and GSDMD-N were significantly decreased. The expression levels of cleaved caspase-3 and its effector proteins GSDME and GSDME-N significantly increased. CONCLUSIONS: Our results suggest that the aqueous extract of E. sagittatum induces liver injury in ICR mice after three months of intragastric injection via inflammatory pyroptosis.