Method for detecting Cheyne-Stokes respiration in patients with congestive heart failure
First Claim
Patent Images
1. A method for detecting Cheyne-Stokes respiration in an individual comprising:
- obtaining pulse oximetry recordings from the individual;
determining oxygen saturation levels at selected intervals;
generating a power spectrum from the oxygen saturation levels;
determining a set of parameters from the power spectrum and the oximetry readings, wherein the set of parameters comprises a delta index; and
inputting the set of parameters into a trained neural network to classify an individual as having Cheyne-Stokes respiration, obstructive sleep apnea or no sleep disordered breathing.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention provides a diagnostic tool for detection of Cheyne-Stokes Respiration (CSR). This invention also provides a method for development of the diagnostic tool. The method comprises the steps of performing overnight oximetry recordings in patients suspected of sleep disordered breathing. Spectral analysis is performed on the oximetry recordings to obtain a set of parameters which can be used in the construction of a classification tree and a trained neural network. The diagnostic tools of the present invention can be used for classification of a patient as having CSR or obstructive sleep apnea.
155 Citations
8 Claims
-
1. A method for detecting Cheyne-Stokes respiration in an individual comprising:
-
obtaining pulse oximetry recordings from the individual;
determining oxygen saturation levels at selected intervals;
generating a power spectrum from the oxygen saturation levels;
determining a set of parameters from the power spectrum and the oximetry readings, wherein the set of parameters comprises a delta index; and
inputting the set of parameters into a trained neural network to classify an individual as having Cheyne-Stokes respiration, obstructive sleep apnea or no sleep disordered breathing. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method for developing a trained neural network for classification of an individual as having CSR, OSA or no sleep breathing disorder comprising the steps of:
-
performing clinical studies to identify patients as having Cheyne-Stokes respiration, obstructive sleep apnea or no sleep breathing disorders;
obtaining overnight pulse oximetry recordings from the patients;
generating power spectra from the oxygen saturation levels;
determining a set of parameters from the power spectra and from the pulse oximetry readings;
analyzing the parameters to obtain relationships between the parameters;
expressing the relationships mathematically; and
exposing the mathematical relationships to a training set and adjusting the mathematical relationships to produce a desired effect. - View Dependent Claims (7, 8)
-
Specification