Computerized Systems and Methods for Stability-Theoretic Prediction and Prevention of Falls

Abstract

A system, methods, 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.

1 . Computer-readable media having computer-executable instructions embodied thereon that when executed, facilitate a method for predicting a sudden kinematic event (falling) in humans, the method comprising:
 receiving motion information representative of motion of an individual;   determining a level of instability of motion dispersion or other measurements based on the motion information; and   determining that the individual has an increased risk for falling based on the determined level of instability of motion dispersion or other measurements;   wherein the motion information comprises information about the individual's motion over one or a plurality of previous time intervals.   
     
     
         2 . The computer-readable media of  claim 1 , wherein determining the level of instability involves detecting the presence of chaos or trajectory divergence instability. 
     
     
         3 . The computer-readable media of  claim 1 , wherein determining a level of instability of motion dispersion or other measurements comprises determining a motion dispersion stability index (MdSI) based on the received motion information. 
     
     
         4 . The computer-readable media of  claim 3 , wherein the motion dispersion stability index (MdSI) is determined utilizing an objective function. 
     
     
         5 . The computer-readable media of  claim 4 , 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. 
     
     
         6 . The computer-readable media of  claim 4 , wherein the objective function comprises a timeseries calculated from serially-acquired waveform data embodying the Lyapunov exponent. 
     
     
         7 . The computer-readable media of  claim 4 , wherein the results of the objective function are used by a decision-support algorithm to determine a quantitative risk for falling. 
     
     
         8 . The computer-readable media of  claim 1 , wherein the motion information is received at a mobile communication device carried by the individual. 
     
     
         9 . A method to prevent injury from a sudden kinematic event (falling) in a population of humans, the method comprising providing an electronic notification to a caregiver of a member of the population, or a member of the population, who exhibits an above-reference value of a predicted risk for falling calculated from a timeseries of motion information acquired from the member over one or a plurality of previous time intervals. 
     
     
         10 . The method of  claim 9  wherein the motion information comprises translational or rotational kinematics from accelerometer or gyroscopic signals representative of movements of an individual. 
     
     
         11 . The method of  claim 9  wherein the electronic notification comprises a visual display, audible alarm, call, email, http, SMS text-message, or other form of radiofrequency communication, that the user has an increased likelihood of a near-term future abnormality or fall occurrence. 
     
     
         12 . The method of  claim 9  wherein the reference value is determined based on parameters associated with the individual including at least one or age, mobility, and falling history. 
     
     
         13 . The method of  claim 9  wherein the predicted risk for falling calculation involves utilizing an objective function for evaluating 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. 
     
     
         14 . The method of  claim 9  wherein the predicted risk for falling calculation involves utilizing an objective function comprising a timeseries calculated from serially-acquired waveform data embodying a Lyapunov exponent. 
     
     
         15 . The method of  claim 14 , wherein the results of the objective function are used by a decision-support algorithm to determine a quantitative risk for falling. 
     
     
         16 . 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 level of motion dispersion instability based on the kinematics from one or a plurality of previous time intervals, for determining a likelihood of falling within a future time interval.   
     
     
         17 . The computer-readable media of  claim 16 , wherein the accelerometer or gyroscopic signals are derived from a mobile communication device carried by the individual. 
     
     
         18 . The computer-readable media of  claim 16 , wherein determining the level of motion dispersion instability involves calculating and storing Lyapunov exponents. 
     
     
         19 . The computer-readable media of  claim 16 , further comprising determining that the level of motion dispersion instability exceeds a reference value, and based on the determination, providing an electronic notification that the individual has an increased risk for falling. 
     
     
         20 . The computer-readable media of  claim 19  wherein the reference value is determined based on parameters associated with the individual including at least one or age, mobility, and falling history, and wherein the electronic notification comprises a call, email, http, or SMS text-message, visual display, or audible alarm.