Skip to main content

Table 2 Comparison between the predictions of the two machine learning models for the values of the five parameters associated with blood-supply capability

From: Pulse wave-based evaluation of the blood-supply capability of patients with heart failure via machine learning

ML networks

Error function

Predicted values

SpO2 (%)

LVDd (%)

LVDs (%)

LVEF (%)

LAD (%)

Fully connected network

MAPE

6.6

14.7

17.3

21.2

14.9

DenseNet

5.6

12.9

14.6

18.2

12.0

  1. SpO2 peripheral oxygen saturation, LVDd left ventricular end-diastolic diameter, LVDs left ventricular end-systolic diameter, LVEF left ventricular ejection fraction, LAD left atrial dimension, MAPE mean absolute percentage error
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us