Abnormal motion detector and monitor

Abstract

In an embodiment, a seizure monitor provides intelligent epileptic seizure detection, monitoring, and alerting for epilepsy patients or people with seizures. In an embodiment, the seizure monitor may be a wearable, non-intrusive, passive monitoring device that does not require any insertion or ingestion into the human body. In an embodiment, the seizure monitor may include several output options for outputting the accelerometer/gyro or other motion sensor data and video data, so that the data may be immediately validated and/or remotely viewed. The device alerts and communicates to the outside care givers via wirelessly or wired medium. The device may also support recording of accelerometer or other motion sensor data and video data, which can be reviewed later for further analysis and/or diagnosis. The device and invention is also used and applicable for other body motion disorders or detection and diagnostics.

1 . A method comprising:
 collecting data, at a machine having a processor system including at least one processor and a memory unit, related to motions associated with a person;   analyzing, by the processor system, the data collected to determine one or more values characterizing the motion; and   comparing, by the machine, the one or more values characterizing the motion to one or more values characterizing motion of a medically abnormal condition;   determining, by the machine, whether the one or more values characterizing the motion match the one or more values characterizing a medically abnormal condition based on the comparing; and   activating, by the machine, an alert if as a result of the determining it is determined that the one or more values characterizing the motion matches the one or more values characterizing the medically abnormal condition.   
     
     
         2 . The method of  claim 1 , the one or more values characterizing the motion of a medically abnormal condition including at least a threshold value for a frequency of oscillation of a body part;
 the comparing including at least comparing the one or more values characterizing the motion, collected during the collecting, to the threshold; and   the determining including at least determining whether the value crossed the threshold based on the comparing.   
     
     
         3 . The method of  claim 1 , the one or more values characterizing motion of the medically abnormal condition including one or more motion patterns characterizing a medically abnormal condition;
 the comparing including at least comparing a motion pattern derived from the data collected during the collecting to the one or more motion patterns characterizing the medically abnormal condition; and   the determining including at least determining whether the motion pattern derived matches within a predetermined tolerance one of the one or more motion patterns characterizing the medically abnormal condition.   
     
     
         4 . The method of  claim 1 , further comprising storing the data in long term memory for later analysis. 
     
     
         5 . The method of  claim 1 , the analyzing including at least
 identifying distinguishable points or features, and   determining locations of the distinguishable points or features across multiple picture frames to determine a path for each of a set of the distinguishable points or features;   the comparing including at least comparing the path for each of the set of the distinguishable points or features to paths characterizing the medically abnormal condition; and   the determining including at least determining whether the path for each of the set of the distinguishable points or features matches paths characterizing the medically abnormal condition within a predetermined tolerance.   
     
     
         6 . The method of  claim 1 , the analyzing including at least
 determining oscillatory motion; and   determining one or more parameters characterizing the oscillatory motion.   
     
     
         7 . The method of  claim 6 , the one or more parameters including at least a frequency of oscillation;
 the comparing including at least comparing the frequency of oscillation to a predetermined threshold; and   the determining including at least determining whether the frequency of oscillation is higher than the predetermined threshold   the activating of the alert including activating the alert if the frequency of oscillation is higher than the predetermined threshold.   
     
     
         8 . The method of  claim 7 , the one or more parameters being output of an accelerometer. 
     
     
         9 . The method of  claim 7 , the one or more parameters being output of a gyro sensor. 
     
     
         10 . The method of  claim 7 , the one or more parameters being output a a combination of one or more accelerometers and gyro sensors. 
     
     
         11 . The method of  claim 7 , the one or more parameters being derived from an optical flow or feature point analysis. 
     
     
         12 . The method of  claim 7 , the one or more parameters being derived from motion vectors. 
     
     
         13 . The method of  claim 1 , the activating of the alert including at least sending a message to a device associated with a concerned party. 
     
     
         14 . The method of  claim 13 , the message including data from a current episode of abnormal motion. 
     
     
         15 . The method of  claim 13 , the message including a current location of the person. 
     
     
         16 . The method of  claim 1 , the analyzing including at least
 identifying distinguishable points or features, and   determining locations of the distinguishable points or features across multiple-data sampling to determine a path for each of a set of the distinguishable points or features;   the determining whether the motion data indicates that the medically abonormal motion has occurred including at least comparing the path for each of the set of the distinguishable points or features to paths characterizing the medically abnormal motion; and   the determining of locations including at least determining whether the path for each of the set of the distinguishable points or features matches paths characterizing a the medically abnormal motion within a predetermined tolerance.   
     
     
         17 . The method of  claim 1 , the medically abnormal motion being a seizure 
     
     
         18 . The system of  claim 1 , the analyzing including at least
 identifying distinguishable points or features, and   determining locations of the distinguishable points or features across multiple-data sampling to determine a path for each of a set of the distinguishable points or features;   the determining whether the motion data indicates that a specific type of motion has occurred including at least comparing the path for each of the set of the distinguishable points or features to paths characterizing a specific type of motion; and   the determining of locations including at least determining whether the path for each of the set of the distinguishable points or features matches paths characterizing a specific type of motion within a predetermined tolerance.   
     
     
         19 . The system of  claim 18 , the algorithm also including
 windowing the data being collected;   the analyzing including at least determining a difference between a minimum accelerations and maximum accelerations during a window of time;   the determining whether the motion data indicates that a specific type of motion has occurred including at least determining whether the difference is greater than a threshold value that is indicative of a specific type of motion.   
     
     
         20 . The system of  claim 1 , the analyzing including at least determining how many jerks occur during a period of time;
 the determining of whether the motion indicates a specific type of motion includes at least determining whether the number of jerks is greater than a threshold.   
     
     
         21 . The system of  claim 20 , each jerk of the jerks being an absolute value of a numerical estimate of a first derivative of a magnitude of acceleration. 
     
     
         22 . The system of  claim 1 , the analyzing including at least computing a second derivative of acceleration of the one or more parts of the body during a specified window;
 the determining of whether the motion indicates a specific type of motion includes at least determining how many second derivative within the specified window have crossed a threshold indicative of a specific type of motion.   
     
     
         23 . A system comprising:
 a body-worn portable device including at least
 a strap for strapping the portable device onto a person; 
 an input system for inputting seizure detections parameters; 
 an accelerometer or gyro sensor for measuring motion data; 
 a housing for enclosing the accelerometer or gyro sensor, 
 the display being attached to the housing for displaying setting for a specific type of motion and status information, and 
 the input system being attached to the housing in a manner in which the setting for the specific type of motion may be entered by the person; and 
 the remote unit, which is a unit remote from the body-worn portable device, including at least 
 a receiver for receiving motion data from the wrist-worn portable device; 
 a memory having stored thereon characteristics of a specific type of motion, and 
 an algorithm for
 analyzing the motion data measured, 
 comparing tile seizure the characteristics of the specific type of motion to the motion data measured, and 
 determining whether to send an alert based on the comparing; and 
 a processor that implements the algorithm and generates an indication that abnormal motion has occurred based on the algorithm.