Skip to main content

Table 1 Results using data of subjects in all ages, under 50 and over 50

From: How can gender be identified from heart rate data? Evaluation using ALLSTAR heart rate variability big data analysis

Method

Age

Acc

Prec

Recall

F1

k-means

Under 50

0.512753

0.512799

0.999424

0.677815

Over 50

0.540683

0.540742

0.999333

0.701759

Logistic regression

Under 50

0.513727

0.512773

0.998169

0.677501

Over 50

0.540853

0.540859

0.999917

0.702002

Random forest

Under 50

0.681927

0.675664

0.727825

0.700766

Over 50

0.655528

0.657664

0.757349

0.703986

SVM

Under 50

0.511716

0.511716

1.000000

0.676999

Over 50

0.540859

0.540859

1.000000

0.702022

  1. Number of all subjects: 428,302, Average age 65.16, Number of subjects Age < 50: 73,349, Average age 33.03 (± 13.12), Number of subjects Age ≥ 50: 347,555, Average age 71.94 (± 10.14). Statistical analysis using Fisher's exact test for < 50 and ≥ 50 showed that the probability of an event not related to age was low, and the results were considered to be related to age (p < 0.0001 for each method)