Surgical Methods and Social Factors Are Associated With Long-Term Survival in Follicular Thyroid Carcinoma: Construction and Validation of a Prognostic Model Based on Machine Learning Algorithms.

Background: This study aimed to establish and verify an effective machine learning (ML) model to predict the prognosis of follicular thyroid cancer (FTC), and compare it with the eighth edition of the American Joint Committee on Cancer (AJCC) model. Methods: Kaplan-Meier method and Cox regression model were used to analyze the risk factors of cancer-specific survival (CSS). Propensity-score matching (PSM) was used to adjust the confounding factors of different surgeries. Nine different ML algorithms,including eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Random Forests (RF), Logistic Regression (LR), Adaptive Boosting (AdaBoost), Gaussian Naive Bayes (GaussianNB), K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP),were used to build prognostic models of FTC.10-fold cross-validation and SHapley Additive exPlanations were used to train and visualize the optimal ML model.The AJCC model was built by multivariate Cox regression and visualized through nomogram. The performance of the XGBoost model and AJCC model was mainly assessed using the area under the receiver operating characteristic (AUROC). Results: Multivariate Cox regression showed that age, surgical methods, marital status, T classification, N classification and M classification were independent risk factors of CSS. Among different surgeries, the prognosis of one-sided thyroid lobectomy plus isthmectomy (LO plus IO) was the best, followed by total thyroidectomy (hazard ratios: One-sided thyroid LO plus IO, 0.086[95% confidence interval (CI),0.025-0.290], P<0.001; total thyroidectomy (TT), 0.490[95%CI,0.295-0.814], P=0.006). PSM analysis proved that one-sided thyroid LO plus IO, TT, and partial thyroidectomy had no significant differences in long-term prognosis. Our study also revealed that married patients had better prognosis than single, widowed and separated patients (hazard ratios: single, 1.686[95%CI,1.146-2.479], P=0.008; widowed, 1.671[95%CI,1.163-2.402], P=0.006; separated, 4.306[95%CI,2.039-9.093], P<0.001). Among different ML algorithms, the XGBoost model had the best performance, followed by Gaussian NB, RF, LR, MLP, LightGBM, AdaBoost, KNN and SVM. In predicting FTC prognosis, the predictive performance of the XGBoost model was relatively better than the AJCC model (AUROC: 0.886 vs. 0.814). Conclusion: For high-risk groups, effective surgical methods and well marital status can improve the prognosis of FTC. Compared with the traditional AJCC model, the XGBoost model has relatively better prediction accuracy and clinical usage.

Assessment of atherosclerotic plaques in the rabbit abdominal aorta with interleukin-8 monoclonal antibody-targeted ultrasound microbubbles.

In this study, we aimed to prepare a neovascularization-relevant inflammatory cytokine-targeted ultrasound contrast agent and apply it in the ultrasound imaging of atherosclerotic plaque. An interleukin-8 (IL-8) monoclonal antibody was conjugated to SonoVue microbubbles using the N-succinimidyl-3-(2-pyridyldithio)propionate cross-linking method. Then, a prepared IL-8-targeted contrast agent was used for contrast-enhanced ultrasound (CEU) to detect rabbit abdominal aorta atherosclerotic plaque and to investigate the imaging characteristics of atherosclerotic plaque with the contrast agent. We found that an IL-8 monoclonal antibody can be successfully coupled to SonoVue microbubbles with stable biological characteristics. CEU with this IL-8-targeted contrast agent can increase the atherosclerotic plaque detection sensitivity, with stronger echo, so that three more plaques were detected compared with using non-targeted SonoVue microbubbles. Thus, an inflammatory cytokine-targeting ultrasound contrast agent carrying IL-8 monoclonal antibody can provide unique advantages for researching the characteristics of atherosclerotic plaque.

Assessment of ascending aortic elasticity in hypertension patients by quantitative tissue velocity imaging.

The elasticity of the ascending aorta in healthy volunteers and hypertension patients were examined by using quantitative tissue velocity imaging (QTVI), and the age-related change in the ascending aortic elasticity was investigated. The anterior and posterior walls of the ascending aorta were imaged with tissue Doppler method in all the subjects and QTVI was performed. Stable curves were obtained from 173 hypertension patients and 185 healthy adults. The peak early diastolic velocity (V(e)), peak late diastolic velocity (V(a)) and peak systolic velocity (V(s)) were measured. The relation of age with these measures was assessed. The results showed that the elasticity of the ascending aorta was much lower in the hypertension patients than in normal controls (P<0.05), and the elasticity was decreased with age in both groups (P<0.05). Our results suggested that QTVI, a new non-invasive ultrasonic technique, is helpful for the assessment of the aortic elasticity in hypertension patients.