Neural networks in sedation and analgesia systems

• US 20040129271A1
• Filed: 10/03/2003
• Published: 07/08/2004
• Est. Priority Date: 10/03/2002
• Status: Active Grant

• Current Assignee: Scott Laboratories, Inc.
• Original Assignee: Scott Laboratories, Inc.
• Inventors: Hickle, Randall S.
• Granted Patent: US 7,367,339 B2
• Time in Patent Office: Days
• US Class Current: 128/204.23
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The present invention comprises systems and methods for handling large amounts of data prone to ambiguity and artifact in real-time in order to ensure patient safety while performing a procedure involving a sedation and analgesia system. The invention utilizes neural networks to weight data which may be more accurate or more indicative of true patient condition such that the patient condition reported to the controller and the user of a sedation and analgesia system will have increased accuracy and the incidence of false positive alarms will be reduced.

Claims

1. A sedation and analgesia system, comprising:

two or more patient health monitor devices adapted so as to be coupled to a patient and so as to each generate a separate input signal reflecting a parameter of a physiological condition of the patient;

a user interface;

a drug delivery controller supplying one or more drugs to the patient; and

an electronic controller interconnected with the patient health monitors, the user interface, and the drug delivery controller, wherein said electronic controller further comprises a threshold logic unit which receives said input signals, multiplies each of said input signals by a predetermined weight corresponding to each of said parameters to achieve a weighted input signal for each corresponding input signal, combines the weighted input signals, and compares the weighted input signals against a predetermined threshold value to determine an action of said electronic controller.

2. The sedation and analgesia system of claim 1, wherein said input signals are binary values.

3. The sedation and analgesia system of claim 1, wherein each of said predetermined weights is trained to be set at a value representative of the significance of each signal resulting from the corresponding input and wherein said training comprises providing a series of inputs into the threshold logic unit indicative of at least one patient condition and the predetermined weights are adjusted until the system accurately detects adverse patient conditions and retains normal functionality during non-critical situations.

4. The sedation and analgesia system of claim 1, wherein said action of said electronic controller comprises at least one of decreasing drug levels, increasing oxygen delivery, delivering a pharmacological antagonist, alarming clinicians, requesting additional patient information from patient monitors, testing patient responsiveness, and delivering positive airway pressure.

5. The sedation and analgesia system of claim 1, wherein said patient monitoring devices comprise at least two of a sensor monitoring nasal airway pressure, a sensor monitoring oral airway pressure, a sensor monitoring nasal capnometry, and a sensor monitoring oral capnometry.

6. A sedation and analgesia system, comprising:

two or more patient health monitor devices adapted so as to be coupled to a patient and so as to each generate a separate input signal reflecting a parameter of a physiological condition of the patient;

a user interface;

a drug delivery controller supplying one or more drugs to the patient; and

an electronic controller interconnected with the patient health monitors, the user interface, and the drug delivery controller, wherein said electronic controller further comprises a neural network to evaluate input signals to determine an action of said electronic controller.

7. The sedation and analgesia system of claim 6, wherein said neural network comprises a set of inputs that make up a first layer of nodes, a set of hidden nodes, and a set of output nodes, wherein said inputs are related to any suitable feature of said patient health monitors.

8. The sedation and analgesia system of claim 7, wherein each said input signal is weighted differently at each node to use parallelism of the neural network to accurately distinguish between normal and adverse patient conditions.

9. The sedation and analgesia system of claim 8, wherein each input signal propagated to said hidden nodes is weighted by a numerical coefficient that indicates the significance of the respective parameter for said input signal.

10. The sedation and analgesia system of claim 9, wherein said neural network adjusts its numerical coefficients through multiple iterations until it reduces its output error to a predefined acceptable range.

11. The sedation and analgesia system of claim 7, wherein said inputs comprise at least one of data derived from sensor fusion, data derived from orthogonally redundant monitoring, data trends, heart rate, blood pressure, data from other neural networks, pulse oximetry, capnometry, acoustical monitoring, respiratory rate, and the sum of squares from patient parameters over time.

12. The sedation and analgesia system of claim 6, wherein said action of said electronic controller comprises at least one of decreasing drug levels, increasing oxygen delivery, delivering a pharmacological antagonist, alarming clinicians, requesting additional patient information from patient monitors, testing patient responsiveness, and delivering positive airway pressure.

13. The sedation and analgesia system of claim 7, further comprising the incorporation of at least one of a perception, back-propagated, and radial basis function network, wherein said at least one network increases the accuracy of sedation and analgesia system.