Intelligent Medicine (Nov 2022)
Non-invasive cuffless blood pressure and heart rate monitoring using impedance cardiography
Abstract
Background: Continuous blood pressure (BP) monitoring provides additional information about how changes in BP may correlate with daily activities and sleep patterns. Recommendations from the American Heart Association and American College of Cardiology strongly suggest confirming a diagnosis of hypertension with continuous BP monitoring. Non-invasive and non-intrusive detection of haemodynamic parameters is emerging as a norm, based on self-monitoring wearable medical devices. Researchers have carried out several studies using non-invasive and continuous BP measurements as an alternative to conventional cuff-based measurements. In this work, we proposed a novel method for cuffless estimation of BP using impedance cardiography (ICG). Methods: We conducted a single-centre, cross-sectional study of 104 subjects (of whom 30 were categorized as controls and the remaining 74 as the disease group) at the Medical College and Hospital, Kolkata. The disease group consisted of patients with confirmed coronary artery disease, while the individuals in the control group were deemed to be healthy. All subjects underwent electrocardiogram recording by on-duty doctors in order to determine their health status. A custom-made device based on the principle of impedance plethysmography was designed to record impedance changes due to subjects’ peripheral blood flow. The device was used to record ICG signals. In this study, we developed a novel auto-adaptive algorithm based on ICG signals for non-invasive, cuffless, continuous monitoring of BP and heart rate. Separate mathematical models were developed for all the estimated parameters (BP and heart rate) for both the study groups (control and disease). The developed models were auto-adaptive and did not require subject-specific calibration. Performance indicators including, r2, error percentage, standard deviation, and mean difference were used to quantify the performance of the models. Results: The ICG signal recorded by the device was used to extract features and compute the augmentation index. The calculated augmentation index values showed strong correlations with systolic BP (r=0.99, P<0.05), diastolic BP (r=0.95, P<0.05), and heart rate (r=0.78, P<0.05). The models were also shown to have a high degree of accuracy for systolic and diastolic BP. Error margins were in the range ±2.33 and ±1.79 mmHg for systolic BP in disease and control subjects, respectively, and ±3.60 and ±1.82 mmHg for diastolic BP. However, the accuracy was lower in the prediction of heart rate in disease subjects, with a reported r2 value of 0.72 and an error margin of ±2.88 beats per min; for healthy subjects, the results were marginally better, with an error margin of ±1.82 beats per min. All statistical analyses were performed using MATLAB (R2017a, MathWorksⓇ, USA). Conclusion: In this study, we developed a non-invasive cuffless approach for estimation of systemic peripheral BP and heart rate using ICG. The proposed methodology eliminated any discomfort to patients caused by inflation of the cuff (in the case of cuff-based BP monitoring) or the need to constantly wear a fingertip photoplethysmography device (in the case of cuffless BP monitoring). The results obtained appeared promising and increased the potential scope of ICG for monitoring other haemodynamic parameters related to heart function.
