Unobtrusive Detection of Simulated Orthostatic Hypotension and Supine Hypertension Using Ballistocardiogram and Electrocardiogram of Healthy Adults

Abstract

Effective management of neurogenic orthostatic hypotension and supine hypertension (SH-OH) due autonomic failure requires a frequent and timely adjustment of medication throughout the day to maintain the blood pressure (BP) within the normal range, i.e., an accurate depiction of BP is a key prerequisite of effective management. One of the emerging technologies that provide one’s circadian and long-term physiological status with increased usability is unobtrusive zero-effort monitoring. In this paper, a zero-effort device, a floor tile, was used to develop an unobtrusive BP monitoring technique. Namely, RJ-interval, the time between the J-peak of a ballistocardiogram and the R-peak of an electrocardiogram, was used to develop a classifier that can detect changes in systolic BP (SBP) induced by the Valsalva maneuver on healthy adults (i.e., a simulated SH-OH). A t-test was used to show statistical differences between the mean RJ-intervals of decreased SBP, baseline, and increased SBP. Following the t-test, a classifier that detected a change in SBP was developed based on a naïve Bayes classifier (NBC). The t-test showed a clear statistical difference between the mean RJ-intervals of the increased SBP, baseline, and decreased SBP. The NBC-based classifier was able to detect increased SBP with 89.3% true positive rate (TPR), 100% true negative rate (TNR), and 94% accuracy and detect decreased SBP with 92.3% TPR, 100% TNR, and 95% accuracy. The analysis showed strong potential in using the developed classifier to assist monitoring of people with SH-OH; the algorithm may be used clinically to detect a long-term trend of symptoms of SH-OH.

Quantification of Resting-State Ballistocardiogram Difference Between Clinical and Non-Clinical Populations for Ambient Monitoring of Heart Failure

“…The use of similar window size has precedence in other works, including the authors’ previous works where the window size of 7-second for ensemble average was used. The effect of different window sizes has been elaborated in the article [21] .…”

“…As such, the beat-to-beat measurements of the Portapres were corrected to match the BP measured by the BpTRU. As the offset correction and synchronization processes were elaborated in previous work [21] , the algorithms were briefly summarized here. The offset correction aimed to shift the entire sequence of BP samples to best match the BP measured by the BpTRU.…”

“…Summaries of the studies are presented below for brevity. The correlated physiological parameters and the corresponding BCG features include heart rate (HR) using the J-waves of the BCG, pre-ejection rate (PEP) using RJ- and RI-intervals (i.e., the time interval between the R-wave of the ECG and the J- or I-wave of the BCG), cardiac output (CO) using the root mean square (RMS) power of the BCG, stroke volume (SV) using the combination of the I- and J-waves of the BCG with the ICG, systolic blood pressure (SBP) using the RJ-interval, and diastolic blood pressure (DBP) using the pulse transit time (i.e., time interval involving the I-wave of the BCG and PPG; PTT) [9] – [13] , [21] .…”

Personal Identification Using a Ballistocardiogram During Urination Obtained from a Toilet Seat

“…Peaks H, I, J, K, and L were detected from the BCG using the following procedure. The maximum value of the BCG wave within 0.3 s after the ECG R-peak was identi ed as the J-peak [17]. The minimum value of the BCG wave between the ECG R-peak and the J-peak was identi ed as the I-negative-peak.…”