Skip to main content

Table 11 Blood pressure inference error

From: Computer vision digitization of smartphone images of anesthesia paper health records from low-middle income countries

Measure

Deshadowing and homography

Deshadowing only

Homography only

No preprocessing

Systolic MAE

1.000

2.153

1.038

2.227

Diastolic MAE

1.356

2.520

1.340

2.589

  1. The effect of preprocessing on blood pressure inference. Removing the deshadowing component has very little effect on error, but the removal of the homography correction had a negative effect on error
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us