Preliminary study on detection of atrial fibrillation during oscillometric blood pressure measurement

Abstract

The paper presents a prototype method for detection of cardiac arrhythmia from pneumatic cuff pressure course, obtained during oscillometric blood pressure measurement. Oscillometric blood pressure measurement is an indirect method for blood pressure measure where pneumatic cuff is placed on patient's extremity, usually upper arm, inflated and then gradually deflated. During deflation phase the pressure oscillations in the cuff caused by squeezed blood vessels are analyzed to determine patient's blood pressure. Since presence of arrhythmia can be detected through observation of heart rhythm, it is possible to detect arrhythmia during blood pressure measurement. We have captured cuff pressure courses -samples from 34 patients of which 6 had arrhythmia present. From captured pressure courses we determined a set of features which we used to train a classifier for discrimination of samples with present arrhythmia from samples where arrhythmia is not present.

Development of a Photoplethysmogram Based Heart Abnormality Detection Technique

“…Meza [12] presented a prototype method for detection of cardiac arrhythmia from pneumatic cuff pressure course, obtained during oscillometric blood pressure measurement. In this study, pressure course samples were collected from 34 patients and used to develop an algorithm for detection of atrial fibrillation.…”

Classificação de segmentos de eletrocardiograma normais e com fibrilação atrial: estudo metodológico.

“…Há técnicas de software que podem ser aplicadas a diversos sinais cardíacos, com o objetivo de detectar a FA. Os algoritmos têm sido aplicados aos sinais de sismografia (Humanen et al, 2017), fotopletismografia (Shan et al, 2016), PA (Wiesel et al, 2014;Verberk et al, 2016;Meža, 2015) além do eletrocardiograma (Shan et al, 2016).…”

“…• desvio padrão (Maji;Mitra;Pal, 2014;Meža, 2015;Nuryani et al, 2015;Kalsi;Prakash, 2016;Shan et al, 2016);…”

“…Por sua vez, os classificadores é que realizam a detecção de FA. Os classificadores podem ser do tipo lineares, por distância de Mahalanobis (Ladavich;Ghoraani, 2014), K-vizinhos mais próximos (Kennedy et al, 2016), máquinas de vetor de suporte (Nuryani et al, 2015;Meža, 2015;Shan et al, 2016), redes neurais artificiais (Meža, 2015), árvores…”

“…Dentre os artigos mencionados na revisão da literatura, as acurácias obtidas estavam na faixa de 85,92% (Meža, 2015) a 99,77% (Trardi et al, 2018b). Alguns outros artigos mencionam também as sensibilidades e especificidades.…”