Search

US-20260123887-A1 - BED-BASED BALLISTOCARDIOGRAM APPARATUS AND METHOD

US20260123887A1US 20260123887 A1US20260123887 A1US 20260123887A1US-20260123887-A1

Abstract

A bed-based ballistocardiogram (BCG) enables non-invasive cardiovascular monitoring of a patient on a patient bed. A method for bed-based BCG recordings includes (1) creating templates for standing BCG signals obtained from subjects in a prior study, and (2) quantifying the distance between these templates and BCG waveforms obtained in different body positions on the patient bed for a new set of subjects. The different body positions on the patient bed include supine, left lying, right lying, prone, and seated.

Inventors

  • Hewon Jung
  • Jacob P. Kimball
  • Omer T. Inan
  • Timothy J. Receveur
  • Eric D. Agdeppa

Assignees

  • HILL-ROM SERVICES, INC.
  • GEORGIA TECH RESEARCH CORPORATION

Dates

Publication Date
20260507
Application Date
20260106

Claims (20)

  1. 1 . A patient bed comprising a weigh scale to weigh a patient on the bed, the weigh scale having a plurality of load cells that each produce a signal, and circuitry including a processor and a memory device, the memory device including instructions that, when executed by the processor, determine the heart rate of the individual from the load cell signals by probabilistically estimating an inter-beat-interval.
  2. 2 . The patient bed of claim 1 , wherein the circuitry further includes instructions in memory, that, when executed by the processor applies a Bayesian approach to fusion to selectively fuse the signals from the plurality of load cells.
  3. 3 . The patient bed of claim 2 , wherein the circuitry further includes instructions in memory, that, when executed by the processor cause the selective fusion of the signals by applying an assessment of a probability density function obtained from each signal.
  4. 4 . The patient bed of claim 3 , wherein the circuitry further includes instructions in memory, that, when executed by the processor, performs an assessment of the reliability of the probability density function for each signal.
  5. 5 . The patient bed of claim 1 , wherein the circuitry further includes instructions in memory, that, when executed by the processor, applies Gaussian weights to each of the respective signals from each of the load cells to produce a weighted joint probability density function.
  6. 6 . The patient bed ( 10 ) of claim 1 , wherein the circuitry further includes instructions in memory, that, when executed by the processor, combines three time-domain local estimators to obtain a joint probability density function for each respective load cell signal.
  7. 7 . The patient bed of claim 1 , wherein the circuitry includes instructions in memory, that, when executed by the processor, apply a finite impulse response band-pass filter with a Kaiser window to the respective load cell signals.
  8. 8 . A patient bed comprising: a frame having a first frame portion and a second frame portion; circuitry; and a weigh scale to weigh a patient supported on the patient bed, the weigh scale having four load cells that support the first frame portion of the patient bed relative to the second frame portion of the patient bed, the four load cells being configured to produce signals from which a patient weight is determined by the circuitry of the patient bed, wherein the circuitry is configured to process signals from only two of the load cells to implement a ballistocardiogram to determine a heart rate of the patient through a probabilistic approach.
  9. 9 . The patient bed of claim 8 , wherein the signals from the only two load cells also are used to determine a respiration rate of the patient.
  10. 10 . The patient bed of claim 8 , wherein the frame has a head end and a foot end, and the only two load cells are situated closer to the foot end than to the head end.
  11. 11 . The patient bed of claim 1 , wherein the probabilistic approach involves the circuitry using a signal quality index (SQI) that is determined as a function of an inverse of a distance between the signals from the only two load cells and at least one template waveform.
  12. 12 . The patient bed of claim 1 , wherein the probabilistic approach involves the circuitry calculating a Pearson correlation coefficient.
  13. 13 . The patient bed of claim 1 , wherein the circuitry includes a controller and at least one finite impulse response (FIR) band-pass filter with a Kaiser window through which the signals from the only two load cells are fed prior to reaching the controller.
  14. 14 . A patient bed comprising: a frame configured to support a patient, a weigh scale coupled to the frame and configured to weigh a patient supported by the frame of the patient bed, the weigh scale having a plurality of load cells that produce signals from which a patient weight is determined, a ballistocardiogram carried by the frame, wherein the ballistocardiogram includes ballistocardiogram circuitry in electrical communication with the plurality of load cells, wherein the signals from at least some, but not all, of the plurality of load cells being processed by the ballistocardiogram circuitry to determine a heart rate of the patient, and a graphical user interface (GUI) carried by the frame and coupled electrically to the ballistocardiogram circuitry, the GUI being usable to provide inputs to a pneumatic system that controls inflation of bladders of a mattress of the patient bed, wherein the bladders overlie the plurality of load cells.
  15. 15 . The patient bed of claim 14 , wherein the ballistocardiogram circuitry is configured to account for a posture of the patient relative to the frame in connection with determining the heart rate of the patient and wherein the posture accounted for includes one or more of the following: supine, left lying, right lying, prone, or seated.
  16. 16 . The patient bed of claim 15 , wherein a transformation function is used by the ballistocardiogram circuitry to map the signals corresponding to left lying, right lying, prone or seated postures to the supine posture.
  17. 17 . The patient bed of claim 14 , wherein the ballistocardiogram circuitry is configured to determine the heart rate of the patient by using a signal quality index (SQI) that is determined as a function of an inverse of a distance between the signals and a respective at least one template waveform.
  18. 18 . The patient bed of claim 17 , wherein the distance is determined by using a dynamic-time feature matching (DTFM) technique.
  19. 19 . The patient bed of claim 14 , wherein the ballistocardiogram circuitry is configured to determine the heart rate of the patient by comparing signals in a manner that involves calculating a Pearson correlation coefficient.
  20. 20 . The patient bed of claim 14 , wherein the ballistocardiogram circuitry is configured to determine the heart rate by feeding the signals through at least one finite impulse response (FIR) band-pass filter with a Kaiser window prior to compare the signals to a respective at least one template waveform.

Description

The present application is a continuation of U.S. application Ser. No. 17/189,935, filed Mar. 2, 2021, now U.S. Pat. No. ______, which claims the benefit, under 35 U.S.C. § 119 (e), of U.S. Provisional Application No. 63/001,585, filed Mar. 30, 2020 and U.S. Provisional Application No. 63/086,724, filed Oct. 2, 2020, each of which is hereby incorporated by reference herein in its entirety. BACKGROUND The present disclosure relates to patient beds used in healthcare facilities and particularly, to patient beds having sensors integrated therein for detecting patient physiological conditions. More particularly, the present disclosure relates to patient beds using load cell signals to provide a bed-based ballistocardiogram. Continuous and unobtrusive vitals monitoring has gained attention for the treatment and prevention of diseases as the number of patients with chronic cardiorespiratory conditions grows. In home settings, such monitoring may allow longitudinal tracking of the patient's physiological conditions. See, P. D. Ziegler, J. L. Koehler, and R. Mehra, “Comparison of continuous versus intermittent monitoring of atrial arrhythmias,” Heart Rhythm, 2006, and M. A. Konstam, “Home monitoring should be the central element in an effective program of heart failure disease management,” Circulation, 2012. Furthermore, it serves a key role in hospitals for patient safety and earlier detection of patient deterioration without increasing the burden on caregivers. See, B. H. Cuthbertson, M. Boroujerdi, L. McKie, L. Aucott, and G. Prescott, “Can physiological variables and early warning scoring systems allow early recognition of the deteriorating surgical patient?,” Critical Care Medicine, 2007. Advances in sensing cardiogenic vibration signals have paved the way for such unobtrusive vitals monitoring. One of the most commonly investigated sensing modalities for unobtrusive monitoring is the ballistocardiogram (BCG). See, O. T. Inan, P. F. Migeotte, K. S. Park, M. Etemadi, K. Tavakolian, R. Casanella, J. Zanetti, J. Tank, I. Funtova, G. K. Prisk, and M. Di Rienzo, “Ballistocardiography and Seismocardiography: A Review of Recent Advances,” IEEE Journal of Biomedical and Health Informatics, 2015 (hereinafter “Inan and Migeotte”). The BCG measures the microdisplacement of the whole body in response to the movement of blood caused by cardiac ejection. See, C. S. Kim, S. L. Ober, M. S. McMurtry, B. A. Finegan, O. T. Inan, R. Mukkamala, and J. O. Hahn, “Ballistocardiogram: Mechanism and Potential for Unobtrusive Cardiovascular Health Monitoring,” Scientific Reports, 2016 (hereinafter “Kim and Ober”). Recent literature has reported promising results for BCG use on monitoring patients with heart failure (see, O. T. Inan, M. Baran Pouyan, A. Q. Javaid, S. Dowling, M. Etemadi, A. Dorier, J. A. Heller, A. O. Bicen, S. Roy, T. De Marco, and L. Klein, “Novel Wearable Seismocardiography and Machine Learning Algorithms Can Assess Clinical Status of Heart Failure Patients,” (′Circulation. Heart failure, 2018), and the assessment of physiological indicators in home settings. See, C. Brüser, K. Stadlthanner, S. De Waele, and S. Leonhardt, “Adaptive beat-to-beat heart rate estimation in ballistocardiograms,” IEEE Transactions on Information Technology in Biomedicine, 2011 (hereinafter “Bruser”), and A. M. Carek and O. T. Inan, “Robust Sensing of Distal Pulse Waveforms on a Modified Weighing Scale for Ubiquitous Pulse Transit Time Measurement,” IEEE Transactions on Biomedical Circuits and Systems, 2017 (hereinafter “Carek”). Modern forms of ballistocardiographic measurement include beds (see, Brüser), chairs (see, S. Junnila, A. Akhbardeh, and A. Värri, “An electromechanical film sensor based wireless ballistocardiographic chair: Implementation and performance,” Journal of Signal Processing Systems, 2009), and weighing scales (see, O. T. Inan, M. Etemadi, A. Paloma, L. Giovangrandi, and G. T. Kovacs, “Non-invasive cardiac output trending during exercise recovery on a bathroom-scale-based ballistocardiograph,” Physiological Measurement, 2009 (hereinafter, “Inan and Paloma”) and Carek), all of which are everyday objects without any interference to normal daily activities. However, BCG measurement systems are sensitive to the posture of the subject during the recording period, in that the signal shape may be distorted when the subject's posture changes. For BCG signals measured with a weighing scale or force plate, subjects are required to stand upright and still to obtain high-quality signals. Any modification in the position or posture of the subject such as slouching will distort signal morphology, making the physiological interpretation of the BCG challenging. Additionally, for bed-based BCG recordings, commonly used for long-term monitoring such as overnight sleep studies (see, B. H. Choi, G. S. Chung, J. S. Lee, D. U. Jeong, and K. S. Park, “Slow-wave sleep estimation on a load-cell-installed bed: A non-constrained method,” Physiolog