Plethysmograph pulse recognition processor

• US 7,988,637 B2
• Filed: 05/03/2006
• Issued: 08/02/2011
• Est. Priority Date: 12/30/1998
• Status: Active Grant

• Current Assignee: Masimo Corporation
• Original Assignee: Masimo Corporation
• Inventors: Diab, Mohamed K.
• Primary Examiner(s): Marmor, II; Charles A
• Assistant Examiner(s): Natnithithadha; Navin
• Application Number:
  US11/418,328
• Publication Number:
  US 20060206021A1
• Time in Patent Office: 1,917 Days
• Field of Search: 600500-504, 600/483, 600/481, 600/513
• US Class Current: 600/500
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00

Abstract

A time domain rule-based processor provides recognition of individual pulses in a pulse oximeter-derived waveform.

Claims

1. A patient monitor comprising:

an input which receives a sensor signal indicative of light attenuated by body tissue; and

a processor which applies a plurality of first edge analysis rules to identify potential pulses from within said sensor signal or from within signals derived from said sensor signal, the processor also applying a plurality of second pulse feature rules to identify acceptable pulses from within said potential pulses, wherein said plurality of said second rules comprise at least one signal modeling rule.

2. The monitor of claim 1, wherein the processor determines statistical pulse rate information from said acceptable pulses.

3. The monitor of claim 2, wherein said statistical pulse rate information comprises pulse period information.

4. The monitor of claim 2, wherein said statistical pulse rate information comprises pulse density information.

5. The monitor of claim 1, wherein said at least one signal modeling rule determines a difference between at least one signal model and said potential pulses.

6. The monitor of claim 5, wherein where said at least one signal modeling rule varies acceptable threshold values to be compared to said difference.

7. The monitor of claim 6, wherein said varying is pulse dependent.

8. The monitor of claim 7, wherein signal features of said potential pulses change when said pulse changes.

9. The monitor of claim 6, wherein said varying accounts for effects of a rising pulse rate on said potential pulses.

10. The monitor of claim 1, wherein the pulse feature rules relate to a pulse starting point.

11. The monitor of claim 1, wherein the pulse feature rules relate to a period.

12. The monitor of claim 1, wherein the pulse feature rules relate to a signal strength.