A comparison of logistic regression analysis and an artificial neural network using the BI-RADS lexicon for ultrasonography in conjunction with introbserver variability.

To determine which Breast Imaging Reporting and Data System (BI-RADS) descriptors for ultrasound are predictors for breast cancer using logistic regression (LR) analysis in conjunction with interobserver variability between breast radiologists, and to compare the performance of artificial neural network (ANN) and LR models in differentiation of benign and malignant breast masses. Five breast radiologists retrospectively reviewed 140 breast masses and described each lesion using BI-RADS lexicon and categorized final assessments. Interobserver agreements between the observers were measured by kappa statistics. The radiologists' responses for BI-RADS were pooled. The data were divided randomly into train (n = 70) and test sets (n = 70). Using train set, optimal independent variables were determined by using LR analysis with forward stepwise selection. The LR and ANN models were constructed with the optimal independent variables and the biopsy results as dependent variable. Performances of the models and radiologists were evaluated on the test set using receiver-operating characteristic (ROC) analysis. Among BI-RADS descriptors, margin and boundary were determined as the predictors according to stepwise LR showing moderate interobserver agreement. Area under the ROC curves (AUC) for both of LR and ANN were 0.87 (95% CI, 0.77-0.94). AUCs for the five radiologists ranged 0.79-0.91. There was no significant difference in AUC values among the LR, ANN, and radiologists (p > 0.05). Margin and boundary were found as statistically significant predictors with good interobserver agreement. Use of the LR and ANN showed similar performance to that of the radiologists for differentiation of benign and malignant breast masses.

Comparison of the risk-taking behaviours of children and the practices adopted by their caregivers for improving home safety.

OBJECTIVES: The objectives of this study were: (1) to describe the efforts of caregivers to provide a safe home environment for their children and the risk-taking behaviours of children; (2) to determine the efficacy of caregivers' practices for providing a safe environment on the risk-taking behaviours of children; (3) to identify factors influencing the home-safety practices adopted by caregivers for their children; and (4) to determine the information sources that caregivers use for preventing in-home injuries in their children. STUDY DESIGN: Cross-sectional study METHODS: The sample consisted of 563 pairs of elementary students and their caregivers, who were administered home-safety questionnaires at school and home, respectively. Five hundred and one matched pairs were included in the analysis. RESULTS: Caregivers' provision of a safe environment resulted in a reduced level of risk-taking behaviours in children, with this improving with sociodemographic status, higher paternal educational level, higher income level, living in an apartment, and for male children. Television and radio were the primary sources of information about preventing childhood in-home injuries, with only 38.0% of the caregivers listing doctors or hospitals as an information source. CONCLUSION: The data from this study indicate the vital roles played by caregivers in managing the risk of injury to young children and preventing injuries in the home.