Ultrasound-based prediction of preoperative core biopsy categories in solid breast tumor using machine learning.

Background: The American College of Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) used with ultrasonography cannot guide the individual management of solid breast tumors, but preoperative core biopsy categories (CBCs) can. We aimed to use machine learning to analyze clinical and ultrasonic features for predicting CBCs and to aid in the development of a new ultrasound (US) imaging reporting system for solid tumors of the breast. Methods: This retrospective study included women with solid breast tumors who underwent US-guided core needle biopsy from March 1, 2019, to December 31, 2019. All patients were randomly assigned to a training or validation cohort (7:3 ratio). CBC was predicted using 5 machine learning models: random forest (RF), support vector machine (SVM), k-nearest-neighbor (KNN), multilayer perceptron (MLP), and ridge regression (RR). In the validation cohort, the area under the curve (AUC) and accuracy were ascertained for every algorithm. Based on AUC values, the optimal algorithm was determined, and the features' importance was depicted. Results: A total of 1,082 female patients were included (age range, 12-96 years; mean age ± standard deviation, 42.22±13.37 years). The proportion of the 4 CBCs was 4% (44/1,185) for the B1 group, 60% (714/1,185) for the B2 group, 5% (57/1,185) for the B3 group, and 31% (370/1,185) for the B5 group. In the validation cohort, AUCs of the optimal algorithm constructed RF were 0.78, 0.88, 0.64, and 0.92 for B1, B2, B3, and B5, respectively, with an accuracy of 0.82. Conclusions: Machine learning could strongly predict CBC, particularly in B2 and B5 categories of solid breast tumors, with RF being the optimal machine learning model.

B lymphocytes subpopulations are associated with cardiac remodeling in elderly patients with advanced chronic kidney disease.

AIM: Chronic Kidney Disease (CKD) is independently associated with increased cardiovascular disease (CVD) risk. The aim of this study was to investigate the potential roles of B lymphocyte populations with cardiac remodeling in elderly patients with advanced CKD. METHODS: We designed a retrospective study in a cohort of 167 patients (84 advanced CKD patients with stage 4-5 and 83 non-CKD controls). B cell subsets: CD19(+)CD5(+) and CD19(+)CD5(-) B cells were identified by flow cytometry. Correlation of B cells subsets with cardiac remodeling and clinical data in elderly CKD patients were analyzed. RESULTS: In this study, we found that the prevalence of hypertension was more common in CKD patients than in the control subjects (P < 0.05). Spearman's analysis showed that CD19(+)CD5(+) B cells were negatively correlated with high sensitivity C-reactive protein (hsCRP), ß2-microglobulin (ß2-MG), serum creatinine (SCr), pro-brain natriuretic peptide (pro-BNP), high-sensitivity troponin T (TNT-hs), left ventricle end-diastolic dimension (LVDD), left ventricle end-systolic dimension (LVSD) and left ventricular mass (LVM), and CD19(+)CD5(-) B cells were negatively correlated with ß2-MG, SCr, pro-BNP and TNT-hs (P < 0.05). In contrary, left ventricular ejection fractions (LVEF) was positively correlated with CD19(+)CD5(+) and CD19(+)CD5(-) B cells (P < 0.05). In addition, patients with higher levels of CD19(+)CD5(+) B cells exhibited lower level of pro-BNP, TNT-hs, interventricular septum (IVS), LVSD and LVM (P < 0.05). Higher levels of CD19(+)CD5(-) B cells also presented lower levels of pro-BNP, TNT-hs and LVSD, but higher levels of LVEF (P < 0.05). Cox regression analysis showed that patients with higher levels of LVSD, lower CD19(+)CD5(+)and CD19(+)CD5(-) B cells counts have a higher risk of all-cause mortality (P < 0.05). CONCLUSIONS: Our results showed that CD19(+)CD5(+) and CD19(+)CD5(-) B lymphocytes were negatively correlated with ventricular hypertrophy-related echocardiographic parameters in advanced CKD patients, which indicated that B lymphocytes might be involved in pathogenesis and improve cardiac remodeling in CKD patients.

Decreased B lymphocytes subpopulations are associated with higher atherosclerotic risk in elderly patients with moderate-to-severe chronic kidney diseases.

AIM: Cardiovascular diseases (CVD) are the leading cause of death in patients with chronic kidney disease (CKD), and the risk of CVD increases with reductions in renal function. This study aims to investigate the potential roles of B lymphocyte populations in subclinical atherosclerosis (measured by intima-media thickness, IMT) and prognosis in elderly patients with moderate-to-severe CKD. METHODS: In this study, a total of 219 patients (143 moderate-to-severe CKD patients with stage 3-4 and 76 non-CKD controls) were recruited. B cell subsets: CD19(+)CD5(+) and CD19(+)CD5(-) B cells were analyzed by flow cytometry. Intima-media thickness (IMT) was measured by ultrasound. Correlations between the B cell subsets with IMT and clinical outcome was analyzed. RESULTS: CKD patients showed increased IMT (P = 0.006). The level of CD19(+)CD5(+) and CD19(+)CD5(-) B cells were decreased in CKD patients. Correlation analysis showed that IMT was positively correlated with systolic blood pressure, protein/creatinine ratio and diabetes (P < 0.05), and were negatively correlated with CD19(+)CD5(+) and CD19(+)CD5(-) B lymphocytes (P < 0.05). Stepwise multiple regression analysis showed that CD19(+)CD5(-) B cells had a significant independent association with IMT (P < 0.05). IMT was increased in lower level of total CD19(+) B cells (≤ 0.06 × 109 /L) and CD19(+)CD5(-) B cells (≤ 0.05 × 109 /L) (P < 0.05). Kaplan-Meier analysis showed that patients with lower levels of CD19(+)CD5(+) and CD19(+)CD5(-) B cells exhibited worse survival (P < 0.05). Cox regression analysis showed that patients with lower CD19(+)CD5(+) and CD19(+)CD5(-) B cells counts have a higher risk of all-cause mortality (P < 0.05). CONCLUSIONS: Our results showed that decreased CD19(+)CD5(+) and CD19(+)CD5(-) B lymphocytes were correlated with atherosclerosis and worse survival, which indicates that B lymphocytes might involve in atherosclerosis and associated the prognosis of elderly patients with moderate-to-severe CKD.

Development and validation of an ultrasound-based nomogram for preoperative prediction of cervical central lymph node metastasis in papillary thyroid carcinoma.

BACKGROUND: Preoperative prediction of central lymph node metastasis (CLNM) holds significant value in determining a patient's suitability for surgical resection and the need for adjuvant treatment, thereby contributing to better therapeutic strategies. This study aimed to build and confirm a nomogram that integrates ultrasound (US) characteristics with clinical features to predict CLNM in patients with papillary thyroid carcinoma (PTC) preoperatively. METHODS: The prediction model was set up with a training dataset that included 512 patients with histopathologically confirmed PTC. The least absolute shrinkage and selection operator (LASSO) regression method was applied to select US features in the development cohort. The patients' US characteristics and clinical features were incorporated into a multivariate logistic regression analysis to develop the nomogram. The clinical feasibility, calibration, and discriminatory ability of the nomogram were evaluated in an independent validation cohort of 306 patients. RESULTS: Age, sex, tumor size, multiple tumors, and US-based CLNM status were included as independent predictors in the personalized nomogram. The nomogram showed good calibration and discrimination in the training and validation datasets. The addition of the BRAF V600E mutation status did not improve the performance of the nomogram. The decision curve analysis showed the nomogram to have clinical feasibility. CONCLUSIONS: A nomogram that integrates US characteristics with patients' clinical features was built. This US-based nomogram can be expediently applied to promote the personalized preoperative prediction of CLNM and to develop surgical strategies, such as tailored central compartment neck dissection, in patients with PTC.