Predictions of random forests (RF), gradient boosting machines (GBM), and neural networks (NN) trained on 12 covariates chosen using subjective feature selection. by Dennis Ochola (11626912)

Predictions of random forests (RF), gradient boosting machines (GBM), and neural networks (NN) trained on 17 covariates selected after recursive feature selection. by Dennis Ochola (11626912)

Fig 5 - by Dennis Ochola (11626912)

Fig 9 - by Dennis Ochola (11626912)

Fig 7 - by Dennis Ochola (11626912)

Fig 4 - by Dennis Ochola (11626912)

Family History of Hypertension Impairs the Autonomic Balance, but not the Endothelial Function, in Young Soccer Players by Walter Vargas (6798635)

“…The significance level adopted in the statistical analysis was 5%. Results The standard deviation of normal RR intervals (SDNN; FM-N=314±185; FM-H=182.4± 57.8), the square root of the mean squared differences in successive RR intervals (RMSSD; FM-N=248±134; FM-H=87±51), the number of interval differences of successive NN intervals greater than 50ms (NN50; FM-N=367±83.4; FM-H=229±55), the ratio derived by dividing NN50 by the total number of NN intervals (pNN50; FM-N=32.4±6.2; FM-H=21.1±5.3) and the high (HF; FM-N=49±8.9; FM-H=35.3±12) and low-frequency (LF; FM-N=50.9±8.9; FM-H=64.6±12) components, in normalized units (%), were significantly lower in the FM-H group than in the FM-N group (p<0.05). …”