Non-invasive method and apparatus for determining onset of physiological conditions

• US 7,450,986 B2
• Filed: 02/28/2002
• Issued: 11/11/2008
• Est. Priority Date: 02/28/2001
• Status: Expired due to Fees

• Current Assignee: University of Technology at Sydney
• Original Assignee: AiMedics Pty., Ltd.
• Inventors: Nguyen, Hung, Ghevondian, Nejhdeh
• Primary Examiner(s): Bockelman; Mark
• Assistant Examiner(s): Bertram; Eric D
• Application Number:
  US10/469,814
• Publication Number:
  US 20040167418A1
• Time in Patent Office: 2,448 Days
• Field of Search: 600/300, 600/513, 600/515
• US Class Current: 600/513
• 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 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0531 Measuring skin impedance
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

The invention relates to the modelling and design of early warning systems for detecting medical conditions using physiological responses. The device comprises sensors for monitoring physiological parameters such as skin impedance, heart rate, and QT interval of a patient, means for establishing when those parameters change, the rate of change of the parameters, and a neural network processor for processing the information obtained by the sensors. The neural network processor is programmed with a fast learning algorithm. When the neural network establishes that a physiological condition is present in the patient an alarm signal will be generated. The invention extends to a method of non-invasive monitoring of a person using a neural network programmed with a fast learning algorithm. A non-invasive hypoglycaemia monitor is specifically described.

Claims

1. A non-invasive method of determining the value, presence or onset of a hypoglycemia condition in a patient known to be susceptible to hypoglycemia comprising the steps of:

determining base parameters of a patient at which the onset of hypoglycemia is likely to occur, said base parameters including;

skin impedance, heart rate, QT interval, and mean or peak frequency of an alpha wave;

continuously monitoring the patient'"'"'s parameters comprising;

skin impedance, heart rate, QT interval, and mean or peak frequency of the alpha wave;

establishing whether one or more of those monitored parameters changes, and if so, the rate of change of that parameter or parameters;

feeding data obtained from said monitoring and said establishing into a neural network processor programmed with a fast learning algorithm;

comparing the data to the base parameters for that patient; and

based on said comparing, causing a signal to be generated either when said neural network establishes conditions that suggest a presence or imminent onset of a hypoglycemic condition, or when said neural network has estimated a value of said hypoglycemic condition.

2. The non-invasive method according to claim 1 wherein the monitoring of the heart rate and QT interval is done with an ECG.

3. The non-invasive method according to claim 1 wherein the monitoring of the alpha wave is done with an EEG.

4. The non-invasive method according to claim 1 wherein the fast learning algorithm has either a magnified gradient function or an optimal gradient function.

5. The non-invasive method according to claim 1 wherein the fast learning algorithm is a robust sliding mode algorithm.

6. An apparatus for generating an alarm when hypoglycemia is present or imminent in a patient known to be susceptible to hypoglycemia, said apparatus comprising:

sensors for sensing a patient'"'"'s parameters comprising;

skin impedance, heart rate, QT interval, and mean or peak frequency of an alpha wave;

means for establishing when one or more of the sensed parameters changes and when so established, a rate of change of that parameter or parameters;

a neural network linked to said sensors and said means for establishing so as to receive a substantially continuous data stream from said sensors and said means for establishing, the neural network being programmed with a fast learning algorithm and adapted to establish when the sensed parameters, and any change to those parameters, for a particular person are such as to indicate a presence or imminent onset of a-hypoglycemic condition;

and alarm means linked to said neural network and adapted to be triggered when the presence or imminent onset of said hypoglycemic condition is established.

7. The apparatus according to claim 6 wherein the fast learning algorithm has either a magnified gradient function or an optimal gradient function.

8. The apparatus according to claim 6 wherein the fast learning algorithm is a robust sliding mode algorithm.

9. The apparatus according to claim 6 wherein the sensors used to sense the heart rate and QT interval include an ECG.

10. The apparatus according to claim 6 wherein the sensors used to sense the mean or peak alpha wave are an EEG.

11. The apparatus according to claim 6 wherein data is transmitted between the sensors and the neural network by radio frequency.

12. The apparatus according to claim 6 wherein the apparatus is adapted to estimate an actual value of said hypoglycemic condition of the patient.

13. The apparatus according to claim 12 wherein the hypoglycemic condition which the apparatus is adapted to estimate is a blood glucose level of the patient.

14. An apparatus for generating an alarm when hypoglycemia is present or imminent in a patient known to be susceptible to hypoglycemia, said apparatus comprising:

sensors for sensing a patient'"'"'s parameters comprising;

skin impedance, heart rate, QT interval, and mean or peak frequency of an alpha wave;

a comparator that establishes when one or more of the sensed parameters changes and when so established, a rate of change of that parameter or parameters;

a neural network linked to said sensors and said comparator so as to receive a substantially continuous data stream from said sensors and said comparator, the neural network being programmed with a fast learning algorithm and adapted to establish when the sensed parameters, and any change to those parameters, for a particular person are such as to indicate a presence or imminent onset of a-hypoglycemic condition;

and an alarm linked to said neural network and adapted to be triggered when the presence or imminent onset of said hypoglycemic condition is established.

15. The apparatus according to claim 14 wherein the fast learning algorithm has either a magnified gradient function or an optimal gradient function.

16. The apparatus according to claim 14 wherein the fast learning algorithm is a robust sliding mode algorithm.

17. The apparatus according to claim 14 wherein the sensors used to sense the hear rate and QT interval parameters include an ECG.

18. The apparatus according to claim 14 wherein the sensors used to sense the mean or peak alpha wave parameters are an EEG.

19. The apparatus according claim 14 wherein data is transmitted between the sensors and the neural network by radio frequency.