RESUMO
Automated machine learning (AutoML) has been recognized as a powerful tool to build a system that automates the design and optimizes the model selection machine learning (ML) pipelines. In this study, we present a tree-based pipeline optimization tool (TPOT) as a method for determining ML models with significant performance and less complex breast cancer diagnostic pipelines. Some features of pre-processors and ML models are defined as expression trees and optimal gene programming (GP) pipelines, a stochastic search system. Features of radiomics have been presented as a guide for the ML pipeline selection from the breast cancer data set based on TPOT. Breast cancer data were used in a comparative analysis of the TPOT-generated ML pipelines with the selected ML classifiers, optimized by a grid search approach. The principal component analysis (PCA) random forest (RF) classification was proven to be the most reliable pipeline with the lowest complexity. The TPOT model selection technique exceeded the performance of grid search (GS) optimization. The RF classifier showed an outstanding outcome amongst the models in combination with only two pre-processors, with a precision of 0.83. The grid search optimized for support vector machine (SVM) classifiers generated a difference of 12% in comparison, while the other two classifiers, naïve Bayes (NB) and artificial neural network-multilayer perceptron (ANN-MLP), generated a difference of almost 39%. The method's performance was based on sensitivity, specificity, accuracy, precision, and receiver operating curve (ROC) analysis.
RESUMO
Elevated temperatures can induce changes in red blood cell (RBC), white blood cell (WBC) and platelet (PLT) counts. Ultrasound heating during obstetric scans has the potential to increase body temperature owing to the phenomenon of absorption. We conducted a study to determine the thermal effects of prenatal ultrasound on RBCs, hemoglobin concentration (Hb), WBCs and PLTs in young rabbits. We selected 69 rabbits that were 1 month of age and 73 that were 5 months of age, and allocated them to four groups. The control group consisted of four pregnant does that were allowed to have a full term delivery without any ultrasound exposure. The experimental groups were subjected to one-time ultrasound exposure for 30, 60 and 90 min in the middle of each gestational stage accordingly. RBCs and Hb showed significant reductions in the experimental groups of 1- and 5-month-old rabbits (P<0.05). In addition, WBCs and PLTs yielded significant differences in the 1-month group that were not observed in the 5-month group (P>0.05). The highest values recorded were those of the WBCs of 1-month-old subjects that received 90 min of exposure at the second stage of gestation. The PLTs were the lowest values recorded in 1-month-old subjects following 90 min of ultrasound exposure at the third stage of gestation. These findings suggest that hematological fluctuations during the early stages of postnatal life persisted until 1 month of age and recovered thereafter, as the subjects progressed into adulthood. Therefore, ultrasound heating can cause significant, yet reversible effects on the hematological parameters of rabbits.
