China
Africa
Explore chapters and articles related to this topic
§
Published in Raouf N.G. Naguib, Gajanan V. Sherbet, Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management, 2001
The outcomes of the data analysis by the ANN and the clinicians were expressed in terms of mean accuracy (sum of correct predictions divided by total number of predictions), sensitivity, specificity, and positive/negative predictive values. The McNemar test [30] was used to analyse the relative accuracy of the predictions from clinicians and the ANN in relation to actual patient outcomes; whereas to compare their predictions with each other, Fisher’s exact test was used [31]. p-values of < 0.05 were considered statistically significant. All statistical analyses were performed using UNISTAT® Statistical Package Version 4.5.01.
The effects of subchronic exposure to NeemAzal T/S on zebrafish (Danio rerio)
Published in Chemistry and Ecology, 2018
Lucie Plhalova, Jana Blahova, Lenka Divisova, Vladimira Enevova, Francesca Casuscelli di Tocco, Caterina Faggio, Frantisek Tichy, Vladimir Vecerek, Zdenka Svobodova
Statistical assessment was carried out using Unistat 5.6 (Unistat Ltd., GB). All data (body weight, total length, and specific growth rate, as well as data on oxidative stress biomarkers) were tested for normal distribution using the Shapiro-Wilk test. After testing for homogeneity of variance across groups (Levene test), an analysis of variance (one-way ANOVA) was used. For more detailed analysis of the differences between control and experimental groups in different concentrations, a post-hoc analysis was computed using Dunnett`s test. Since a non-normal distribution of data was identified, a non-parametric test was used. The Kruskal-Wallis test, followed by multiple comparison (Dunn test), was used to determine differences between control and experimental groups. Significance was accepted at p < 0.05. All data are expressed as a mean ± standard error of the mean.