Pattern analysis system and method

• US 7,409,373 B2
• Filed: 12/30/2002
• Issued: 08/05/2008
• Est. Priority Date: 12/28/2001
• Status: Expired due to Fees

• Current Assignee: Concepta AB
• Original Assignee: Concepta AB
• Inventors: Knagenhjelm, Petter
• Primary Examiner(s): Hirl; Joseph P.
• Assistant Examiner(s): Fernandez Rivas; Omar F
• Application Number:
  US10/330,673
• Publication Number:
  US 20030153817A1
• Time in Patent Office: 2,045 Days
• Field of Search: 706/8, 706 10- 21, 706/25, 706 46- 51, 706/61, 395/10, 395/20, 395/21, 395/54, 395/62, 395/63, 395/75, 395/77
• US Class Current: 706/20
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Method and arrangement for providing a computerized system having an interface arrangement for interfacing a data source. The data source delivering data related to motion of a person, a memory arrangement for storing said data, a processor for processing the data, an artificial neural network (ANN) using the processor, means for collecting a second set of data from the person, means for calculating one or several parameters distinctive of various features of said person, and means for feeding the parameter values to the ANN trained to recognize the various features.

Claims

1. A method for the detection of a characteristic of a person by means of a computer which generates a report placing said person in a special category in need of treatment, said computer employing a trained artificial neural network (ANN) in which motion data are analyzed, said method comprising:

measuring motion data from said person;

collecting other measured data from said person, under influence of a drug;

calculating the values of one or several parameters distinctive of various characteristics;

feeding said parameter values to said ANN trained to recognize said various characteristics;

analyzing said parameter values in said trained ANN;

wherein said parameters comprise at least the variance of continuous performance task (CPT) variables, said variance of CPT variables comprising variance of latency t defined as;

2. The method of claim 1, wherein said characteristics include at least one psychological syndrome.

3. In a computerized system, a method for the detection of patients with ADHD employing a trained artificial neural network (ANN) in which motion data are analyzed, said method comprising:

measuring motion data on a patient;

collecting other measured data from the patient;

calculating, from said motion data and other measured data, the values of one or several parameters distinctive of ADHD;

feeding said parameter values to said ANN trained to recognize ADHD;

analyzing said parameter values in said trained ANN; and

wherein said parameters comprise;

the variance of distance, the variance of continuous performance task (CPT) variables, the residual signal defined as difference between the input signal and a smoothed version of the same, an estimate of immobility duration, and one or more parameters suited to detect periodicity in the one or more of the input signals;

said variance of CPT variables comprising variance of latency t defined as;

4. The method of claim 3, wherein said ANN is trained with data collected from patients being under influence of drugs.

5. The method of claim 3, wherein said ANN comprises a number of nodes representing sets of training data.

6. The method of claim 3, wherein the ANN is a Kohonen-map type ANN.

7. The method of claim 3, further comprising the use of linear predictive coding (LPC) to analyze the parameter values fed to the ANN.

8. The method of claim 3, wherein said parameters are used for optimal correlation between parameter distance and conceptual distance.

9. A method for the detection of a characteristic of a person by means of a computer which generates a report placing said person in a special category in need of treatment, said computer employing a single trained artificial neural network (ANN) in which motion data are analyzed, said method comprising:

measuring motion data from said person;

collecting other measured data from said person, under influence of a drug;

calculating the values of one or several parameters distinctive of various characteristics;

feeding said parameter values to said ANN trained to recognize said various characteristics;

analyzing said parameter values in said trained ANN;

wherein said parameters comprise;

the variance of distance, the variance of continuous performance task (CPT) variables, the residual signal defined as difference between the input signal and a smoothed version of the same, an estimate of immobility duration, and at least one additional parameter suited to detect periodicity in the one or more of the input signals;

said variance of CPT variables comprising variance of latency t defined as;