NONINVASIVE BLOOD-PRESSURE MONITORING FROM THE SUPRAORBITAL ARTERY USING AN ARTIFICIAL NEURAL-NETWORK OSCILLOMETRIC ALGORITHM

Objective, Our objective was to overcome the limitations of linear mod els of oscillometric blood pressure determination by using a nonlinear technique to model the relationship between the oscillometric envelop e and systolic and diastolic blood pressures, and then to use that tec hnique for near-continuous arterial pressure monitoring at the supraor bital artery. Methods. An adhesive pressure pad and transducer were us ed to collect oscillometric data from the supraorbital artery of 85 su bjects. These data were then used to train an artificial neural networ k (ANN) to report diastolic or systolic pressure. Arterial pressure me asurements defined by brachial artery auscultation were used as a refe rence. ANN results were compared with those obtained using a standard oscillometric algorithm that determined pressures based on fixed perce ntages of the maximum oscillometric amplitude. Results. The ANN produc ed better estimates of reference blood pressures than the standard osc illometric algorithm. Mean difference between target and actual output for the ANN was 0.50 +/- 5.73 mm Hg for systolic pressures, compared to the mean difference of the standard algorithm of 2.78 +/- 19.38 mm Hg. For diastolic pressures, the ANN had a mean difference of 0.04 +/- 4.70 mm Hg, while the mean difference of the standard algorithm was - 0.34 +/- 9.75 mm Hg. Conclusions. The ANN produced a better model of t he relationship between the oscillometric envelope and reference systo lic and diastolic pressures than did the standard oscillometric algori thm. Noninvasive blood pressure measured from the supraorbital artery agreed with pressure measured by auscultation in the brachial artery, and may sometimes be more clinically useful than an arm cuff device.