False positive reduction in SPO2 atrial fibrillation detection using average heart rate and NIBP
The method and system includes detecting atrial fibrillation in a patient by monitoring the blood oxygen saturation level over a period of time. The method and system produces a plethysmographic waveform from the monitored blood oxygen saturation level and analyzes the plethysmographic waveform and detected intervals and determines whether the patient is in atrial fibrillation. The method and system is preferably implemented in a software application and may be configured to report to the user on the current state of atrial fibrillation (AFIB) and a current trend.
1. A method of detecting atrial fibrillation in a human or animal subject, the method comprising:
acquiring a plethysmographic waveform of a patient from a monitoring device over a period of time;
extracting a pulse from the plethysmographic waveform;
measuring a set of pulse intervals from the plethysmographic waveform;
measuring a set of features from the plethysmographic waveform;
analyzing the set of pulse intervals and the set of pulse features from the plethysmographic waveform to determine an atrial fibrillation state of the patient;
analyzing the pulse from the plethysmographic waveform, wherein analyzing the pulse from the plethysmographic waveform includes analyzing an average heart rate increase and analyzing an average heart rate variability;
acquiring and analyzing an NIBP pulse of the patient;
acquiring and analyzing a set of medical records of the patient; and
combining results from the pulse analysis, NIBP pulse analysis and the medical records analysis and confirming the atrial fibrillation state based on said results.
2. The method as claimed in claim 1 , wherein the monitoring device is a pulse oximeter sensor.
3. The method as claimed in claim 1 , wherein one of the set of features is a set of pulse amplitudes.
4. The method as claimed in claim 1 , further comprising analyzing the set of pulse intervals and the set of pulse features from the plethysmographic waveform to detect an atrial fibrillation trend of the patient.
5. The method as claimed in claim 4 , further comprising reporting the atrial fibrillation trend.
6. The method as claimed in claim 1 , further comprising reporting the atrial fibrillation state.
7. The method as claimed in claim 1 , wherein analyzing the set of pulse intervals includes: conducting a hidden Markov model analysis on the set of pulse intervals; and conducting a contextual analysis on the set of pulse intervals.
8. The method as claimed in claim 7 , wherein the hidden Markov model analysis determines a probability of the patient having an irregular heart rhythm.
9. The method as claimed in claim 7 , wherein the contextual analysis rules out atrial fibrillation as a source of irregular heart rhythm.
10. The method as claimed in claim 1 , wherein analyzing the set of pulse features includes:
calculating amplitude variation between each consecutive one of the set of pulse amplitudes.
11. The method as claimed in claim 10 , wherein the atrial fibrillation state determination is dependent on an analysis of pulse amplitude variation.
12. The method as claimed in claim 1 , wherein analyzing the set of pulse amplitudes includes determining a set of filling time dynamics of the set of pulse amplitudes.
13. The method as claimed in claim 12 , wherein the steps of analyzing the set of pulse amplitudes and determining the set of filling time dynamics provides an indication of the degree of atrial augmentation present.
14. The method as claimed in claim 1 , wherein the pulse analyzing step contributes to determining the atrial fibrillation state of the patient.