Computerized systems and methods for stability—theoretic prediction and prevention of falls

• US 8,529,448 B2
• Filed: 12/30/2010
• Issued: 09/10/2013
• Est. Priority Date: 12/31/2009
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Primary Examiner(s): Thomson, Bill
• Assistant Examiner(s): SORIANO, BOBBY GILES
• Application Number:
  US12/982,631
• Publication Number:
  US 20110190593A1
• Time in Patent Office: 985 Days
• Field of Search: 600300-301
• US Class Current: 600/301
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/0004 characterised by the type of physiological signal transmitted
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• CPC Class Codes: A61B 5/6891 Furniture
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/7405 using sound
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: A61B 5/747 in case of emergency, i.e. alerting emergency services
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A system, methods and computer-readable media are provided for the automatic identification of patients according to near-term risk of sudden kinematic injury (falling). Embodiments of the invention are directed to event prediction, risk stratification, and optimization of the assessment, communication, and decision-making to prevent falling in humans, and in one embodiment take the form of a platform for wearable, mobile, unteathered monitoring devices with embedded decision support. Thus the aim of embodiments of the present invention relates to automatically identifying persons who are at risk for falls through the use of an inexpensive, noninvasive, portable, wearable electronic device and sensors equipped with signal-processing software and statistical predictive algorithms that calculate stability-theoretic measures derived from the digital accelerometer and gyroscope timeseries acquired by the device. The measurements and predictive algorithms embedded within the device provide for unsupervised use in the home or in general acute-care and chronic-care venues and afford a degree of robustness against variations in individual anatomy and sensor placement. In some embodiments, the present invention provides a leading indicator of near-term future abnormalities, proactively alerting the user, for example, 2 hours or more in advance, and providing the wearer and/or care providers with sufficient advance notice to enable effective preventive maneuvers to be undertaken. In one exemplary embodiment, the device is equipped with radiofrequency telecommunication capabilities that enable integration with case-management software, electronic health record decision-support systems, and consumer personal health record systems.

Claims

1. Computer-readable media having computer-executable instructions embodied thereon that when executed, facilitate a method for automatically predicting life-threatening ventricular arrhythmias that are likely to result in sudden kinematic death (falling) in humans, the method comprising:

obtaining motion signals representative of motion of an individual;

detecting the presence of instability (chaos or trajectory-divergence) of motion dispersion or other measurements in said signals;

determining, utilizing an objective function, a motion dispersion stability index (MdSI) from said signals based on one or a plurality of previous time intervals; and

determining a difference between the index and a reference value to classify the likelihood of events leading to falling within a future time interval,

wherein a significant difference is indicative of an increased risk for falling.

2. The computer-readable media of claim 1, wherein the objective function evaluates digitized kinematic waveforms from the one or a plurality of previous time intervals to classify the likelihood of a cascade of events leading to falling within a future time interval.

3. The computer-readable media of claim 1, wherein the objective function comprises a timeseries calculated from serially-acquired waveform data embodying the Lyapunov exponent.

4. The computer-readable media of claim 3, wherein the results of the objective function are used by a decision-support algorithm to determine a quantitative risk for falling.

5. The computer-readable media of claim 4, wherein the decision-support algorithm comprises at least one of a decision-tree, a suite of ‘

if-then’

production rules and an inference engine, a support vector machine (SVM), a logistic regression equation, an automated neural network, or a statistical predictive algorithm.

20. The computer-readable media of claim 1, wherein the reference value is determined based on parameters associated with the individual including at least one of age, mobility, and falling history;

wherein the determined difference is determined as significant when the difference exceeds a threshold; and

wherein the threshold is based on a value indicative of minor fluctuations in activity level of the individual.

6. Computer-readable media having computer-executable instructions embodied thereon that when executed, facilitate a method for determining a motion dispersion stability index for an individual, the method comprising:

identifying translational or rotational kinematics from accelerometer or gyroscopic signals representative of movements of an individual; and

determining a motion dispersion stability index based on the kinematics from one or a plurality of previous time intervals, for determining a likelihood of falling within a future time interval.

7. The computer-readable media of claim 6, wherein said determining a motion dispersion stability index based on the kinematics further comprises eliminating anomalous kinematic values following fall occurrences.

8. The computer-readable media of claim 7, wherein said fall occurrences comprise a predominantly translational motion or a predominantly rotational motion.

9. The computer-readable media of claim 7, wherein the method further comprises filtering the signal prior to determining the motion dispersion stability index.

10. The computer-readable media of claim 7, wherein said determining a motion dispersion stability index based on the kinematics further comprises removing baseline fluctuation from said signal prior to determining the motion dispersion stability index.

11. The computer-readable media of claim 7, wherein said determining a motion dispersion stability index based on the kinematics further comprises:

calculating the maximal value of root-mean-square differences; and

normalizing the maximal value of root-mean-square differences to an absolute magnitude of signal-averaged motions.

12. The computer-readable media of claim 7, wherein said determining a motion dispersion stability index based on the kinematics further comprises calculating and storing Lyapunov exponents.

13. A method for automatically predicting sudden kinematic injury (falling) in humans the method comprising:

obtaining motion signals representative of motion of an individual;

determining, utilizing an objective function, a motion dispersion stability index (MdSI) from said signals based on one or a plurality of previous time intervals, to classify a likelihood of events leading to falling within a future time interval; and

determining a difference between the index and a reference value,

wherein a significant difference is indicative of an increased risk for falling.

14. The method of claim 13, wherein the objective function evaluates digitized kinematic waveforms from the one or a plurality of previous time intervals to classify the likelihood of a cascade of events leading to falling within a future time interval.

15. The method of claim 13, wherein the objective function comprises a timeseries calculated from serially-acquired waveform data embodying a Lyapunov exponent of one or a plurality of kinematic or other physiologic variables as functions of time.

16. The method of claim 13, wherein the results of the objective function are used by a decision-support algorithm to determine a quantitative risk for falling.

17. The method of claim 16, wherein the decision-support algorithm comprises at least one of a decision-tree, a suite of ‘

if-then’

production rules and an inference engine, a support vector machine (SVM), a logistic regression equation, an automated neural network, or a statistical predictive algorithm.

18. The method of claim 13, wherein the method further comprises providing a notification to a health care provider when said increased risk for falling is indicated.

19. The method of claim 13, wherein the reference value is determined based on parameters associated with the individual including at least one of age, mobility, and falling history;

wherein the determined difference is determined as significant when the difference exceeds a threshold; and

wherein the threshold is based on a value indicative of minor fluctuations in activity level of the individual.