EP0329356A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Physiologic waveform analysis
Assignee: Wayne State University
•
Filing: 1989-02-13
•
Granted: —
•
Expires: 2009-02-13
Abstract
Abstract A waveform analysis assembly (10) includes a sensor (12) for detecting physiological electrical and mechanical signals produced by the body. An extraction neural network (22) will learn a repetitive waveform over a first pass of the electrical signal and store the waveform in memory (18). During a second pass over the electrical signal, the waveform is extracted from the electrical signal and times of occurrence of the waveform are also stored in a buffer (30). A third pass subtracts the waveform from the electrical signal for reprocessing finding an additional waveform. The process is repeated for each significantly different waveform in the electrical signal. A reducer (20) receives the stored waveforms and times and reduces them into features characterizing the waveforms. A classifier neural network (36) analyzes the features by classifying them with standard features representing diseased states and outputs results of diseased states based on the best match of the features to the normal and patient groups.
Inventors
- 👤 Robert Spitzer
- 👤 Mohamed Hassoun
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-02 05:58
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N20/00; G06N3/0499; G06N3/08; G06N3/09; G16; G16H; G16H15/00; G16H50/00; G16H50/50; A; A61; A61B; A61B5/00; A61B5/72; A61B5/7235; A61B5/7239; A61B5/7264; G16H10/00; G16H10/60; G16H40/00; G16H40/60; G16H40/63; G16H50/20
Claims Analysis
Total Claims: 38
Claim 1
Independent Claim
85 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics, said assembly comprising; sensing means (12) for sampling a physiological signal produced within the body and for producing an electrical signal, extraction network means (22) for receiving said electrical signal and for learning repetitive waveform components within said electrical signal and for extracting said learned waveform from said electrical signal, and output means (42) for outputting information of disease diagnosis based on said extracted waveform.
Claim 2
Dependent Claim
85 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics, said assembly comprising; sensing means (12) for sampling a physiological signal produced within the body and for producing an electrical signal, extraction network means (22) for receiving said electrical signal and for learning repetitive waveform components within said electrical signal and for extracting said learned waveform from said electrical signal, and output means (42) for outputting information of disease diagnosis based on said extracted waveform.
Claim 3
Dependent Claim
28 words
An assembly as set forth in claim 1 further characterized by including preprocessing means (18) for filtering and differentiating said electrical signal to isolate spikes associated with waveforms.
Claim 4
Dependent Claim
25 words
An assembly as set forth in claim 2 further characterized by including control means (20) for identifying the location of waveforms within said electrical signal.
Claim 5
Dependent Claim
19 words
An assembly as set forth in claim 1 further characterized by said sensing means (12) including a concentric needle.
Claim 6
Dependent Claim
25 words
An assembly as set forth in claim 1 further characterized by including reducing means (34) for analyzing said waveform to produce features characterizing said waveform.
Claim 7
Dependent Claim
54 words
An assembly as set forth in claim 5 further characterized by including classifier network means (36) containing information comprising standard features and combinations thereof associated with disease states for comparing said features to said information to produce an output representative of diseased states based on the best match of said features with said information.
Claim 8
Dependent Claim
29 words
An assembly as set forth in claim 1 further characterized by said extraction network means (22) including buffer means (30) for storing said extracted waveform within said electrical signal.
Claim 9
Dependent Claim
35 words
An assembly as set forth in claim 1 further characterized by said extraction network means (22) including learning means (24) for learning said repetitive waveform and a weight matrix (26) for storing said learned waveform.
Claim 10
Dependent Claim
29 words
An assembly as set forth in claim 1 further characterized by said extraction network means (22) including subtracting means (32) for subtracting said extracted waveform from said electrical signal.
Claim 11
Dependent Claim
85 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics and including means for producing features characterizing the physiological signal, said assembly comprising; a classifier neural network (36) containing information comprising known features and combinations thereof associated with disease and normal patient states for comparing the features characterizing the physiological signal in relation to said information to produce an output representative of diseased states based on the best match of the features with said information.
Claim 12
Dependent Claim
85 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics and including means for producing features characterizing the physiological signal, said assembly comprising; a classifier neural network (36) containing information comprising known features and combinations thereof associated with disease and normal patient states for comparing the features characterizing the physiological signal in relation to said information to produce an output representative of diseased states based on the best match of the features with said information.
Claim 13
Dependent Claim
30 words
An assembly as set forth in claim 10 further characterized by including sensing means (12) for sampling a physiological signal produced within the body and for producing an electrical signal.
Claim 14
Dependent Claim
28 words
An assembly as set forth in claim 10 further characterized by including reducing means (36) for analyzing said electrical signal and for producing features characterizing said electrical signal.
Claim 15
Dependent Claim
65 words
An assembly as set forth in claim 11 further characterized by including extraction network means (22) for receiving said electrical signal to identify and learn a repetitive waveform comprising said electrical signal and for extracting said learned waveform, said extraction network means (22) including buffer means (30) for storing said extracted waveform and associated times of occurrence of substantially similar waveforms within said electrical signal.
Claim 16
Dependent Claim
28 words
An assembly as set forth in claim 11 further characterized by including preprocessing means (18) for filtering and differentiating said electrical signal to isolate spikes associated with waveforms.
Claim 17
Dependent Claim
30 words
An assembly as set forth in claim 13 further characterized by including control means (20) for controlling said extraction network means (22) and for identifying waveforms in said electrical signal.
Claim 18
Independent Claim
64 words
A method of discriminating physiological signals produced within the body and producing output indicative of disease characteristics, said method comprising the steps of: sensing the physiological signals produced within the body and producing an electrical signal, learning a repetitive waveform within the electrical signal, extracting the learned waveform from the electrical signal, and outputting information of the disease diagnosis based on the extracted waveform.
Claim 19
Independent Claim
64 words
A method of discriminating physiological signals produced within the body and producing output indicative of disease characteristics, said method comprising the steps of: sensing the physiological signals produced within the body and producing an electrical signal, learning a repetitive waveform within the electrical signal, extracting the learned waveform from the electrical signal, and outputting information of the disease diagnosis based on the extracted waveform.
Claim 20
Dependent Claim
26 words
A method as set forth in claim 16 further including filtering and differentiating the electrical signal to isolate spikes associated with occurrences of the repetitive waveform.
Claim 21
Dependent Claim
19 words
A method as set forth in claim 16 further including locating the occurrences of waveforms within the electrical signal.
Claim 22
Dependent Claim
18 words
A method as set forth in claim 16 further including reducing the waveform into features characterizing the waveform.
Claim 23
Dependent Claim
27 words
A method as set forth in claim 19 further including analyzing the features with respect to information comprising standard features and combinations thereof associated with disease states.
Claim 24
Dependent Claim
25 words
A method as set forth in claim 20 further including outputting diseased states data based on the best match of the features with the information.
Claim 25
Dependent Claim
26 words
A method as set forth in claim 16 further including storing the extracted waveform and associated times of occurrence of the waveform within the electrical signal.
Claim 26
Dependent Claim
18 words
A method as set forth in claim 16 further including subtracting the extracted waveform from the electrical signal.
Claim 27
Dependent Claim
79 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics, said assembly comprising; sensing means (12) for sampling a physiological signal produced within the body and for producing an electrical signal, an extraction neural network (22) for learning a waveform and for extracting a waveform from the electrical signal based on the learned waveform, and output means (42) for outputting information of disease diagnosis based on said extracted waveform.
Claim 28
Dependent Claim
79 words
A wave analysis assembly for discriminating physiological signals produced within the body and for producing output indicative of disease characteristics, said assembly comprising; sensing means (12) for sampling a physiological signal produced within the body and for producing an electrical signal, an extraction neural network (22) for learning a waveform and for extracting a waveform from the electrical signal based on the learned waveform, and output means (42) for outputting information of disease diagnosis based on said extracted waveform.
Claim 29
Dependent Claim
31 words
An assembly as set forth in claim 24 further characterized by said extraction neural network (16) including learning means (22) for learning a repetitive waveform in electrical signal for the extraction.
Claim 30
Dependent Claim
32 words
An assembly as set forth in claim 24 further characterized by said extraction neural network (16) including learning means (22) for learning an template waveform inputted by the user for the extraction.
Claim 31
Dependent Claim
33 words
An assembly as set forth in claim 24 further characterized by said extraction neural network (16) including extracting means (28) for extracting waveforms from said electrical signal substantially similar to said learned waveform.
Claim 32
Dependent Claim
33 words
An assembly as set forth in claim 24 further characterized by said extraction neural network (16) including extracting means (28) for extracting waveforms from said electrical signal substantially different from said learned waveform.
Claim 33
Independent Claim
58 words
A method of discriminating physiological signals produced within the body and producing output indicative of disease characteristics, the method including the steps of; sensing a physiological signal produced within the body and producing an electrical signal, learning a waveform, extracting a waveform from the electrical signal based on the learned waveform, and outputting information of the extracted waveform.
Claim 34
Independent Claim
58 words
A method of discriminating physiological signals produced within the body and producing output indicative of disease characteristics, the method including the steps of; sensing a physiological signal produced within the body and producing an electrical signal, learning a waveform, extracting a waveform from the electrical signal based on the learned waveform, and outputting information of the extracted waveform.
Claim 35
Dependent Claim
56 words
A wave analysis assembly for discriminating electrical signals, said assembly comprising; sensing means for inputting an electrical signal, extraction network means for receiving said electrical signal and for learning repetitive waveform components within said electrical signal and for extracting said learned waveform from said electrical signal, and output means for outputting information of said extracted waveform.
Claim 36
Dependent Claim
56 words
A wave analysis assembly for discriminating electrical signals, said assembly comprising; sensing means for inputting an electrical signal, extraction network means for receiving said electrical signal and for learning repetitive waveform components within said electrical signal and for extracting said learned waveform from said electrical signal, and output means for outputting information of said extracted waveform.
Claim 37
Independent Claim
40 words
A method of discriminating electrical signals, said method including the steps of; inputting an electrical signal, learning a repetitive waveform within the electrical signal, extracting the learned waveform from the electrical signal, and outputting information based on the extracted waveform.
Claim 38
Independent Claim
40 words
A method of discriminating electrical signals, said method including the steps of; inputting an electrical signal, learning a repetitive waveform within the electrical signal, extracting the learned waveform from the electrical signal, and outputting information based on the extracted waveform.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.