Search

Abstract Background Prediction of lymph node metastasis (LNM) is critical for individualized management of papillary thyroid carcinoma (PTC) patients to avoid unnecessary overtreatment as well as undesired under-treatment. Artificial intelligence (AI) trained by thyroid ultrasound (US) may improve prediction performance. Methods From September 2017 to December 2018, patients with suspicious PTC from the first medical center of the Chinese PLA general hospital were retrospectively enrolled to pre-train the multi-scale, multi-frame, and dual-direction deep learning (MMD-DL) model. From January 2019 to July 2021, PTC patients from four different centers were prospectively enrolled to fine-tune and independently validate MMD-DL. Its diagnostic performance and auxiliary effect on radiologists were analyzed in terms of receiver operating characteristic (ROC) curves, areas under the ROC curve (AUC), accuracy, sensitivity, and specificity. Results In total, 488 PTC patients were enrolled in the pre-training cohort, and 218 PTC patients were included for model fine-tuning (n = 109), internal test (n = 39), and external validation (n = 70). Diagnostic performances of MMD-DL achieved AUCs of 0.85 (95% CI: 0.73, 0.97) and 0.81 (95% CI: 0.73, 0.89) in the test and validation cohorts, respectively, and US radiologists significantly improved their average diagnostic accuracy (57% vs. 60%, P = 0.001) and sensitivity (62% vs. 65%, P

Objective: the Controlling Nutritional Status (CONUT) score is an objective tool widely used to assess nutritional status of patients. We aimed to investigate the value of CONUT score on predicting length of hospital stay (LOS) and the risk of long COVID in patients with COVID-19. Methods: a total of 151 patients with COVID-19 were enrolled for analysis. Patients were followed up for two years from three months after the onset of SARS-CoV-2 infection. CONUT score was calculated on admission. The correlation between CONUT score and LOS were assessed by Spearman's rank correlation coefficient and multivariate linear analysis. The association between different CONUT grade and long COVID was evaluated by Kaplan-Meier survival curves with log-rank test and Cox proportional hazard models. Results: Spearman's rank correlation coefficient showed that CONUT scores were positively correlated with LOS (r = 0.469, p < 0.001). Multivariate linear analysis showed that CONUT score is the only independent determinant of LOS (B 2.055, 95 % CI: 1.067-3.043, p < 0.001). A total of 53 (35.10 %) patients with long COVID were identified. Kaplan-Meier cumulative survival curves and Cox proportional hazards analyses showed that the incidence of long COVID in patients with a higher CONUT score was significantly higher than in patients with lower CONUT score (p < 0.001). Conclusions: higher CONUT score predicts longer LOS and the risk of long COVID in patients with COVID-19. The CONUT score might be useful for risk stratification in COVID-19 patients and help to develop new nutritional treatment strategies for long COVID. [ABSTRACT FROM AUTHOR]