Systems and methods for predicting adverse events and assessing level of sedation during medical procedures

1. A system for automatically providing a quantitative assessment of a physiological state of a patient during procedural sedation, the system comprising:

a breath receiver in fluid communication with a patient undergoing procedural sedation;

a sensor configured to measure a carbon dioxide concentration in air captured by the breath receiver, the sensor being coupled to the breath receiver;

a processor configured to:

generate, in real time, a capnogram associated with the patient, the capnogram being generated based on the carbon dioxide concentration measured by the sensor over one or more respiratory cycles;

extract, in real time, one or more features from the capnogram that are indicative of the physiological state of the patient;

determine, in real time, using a clustering technique, clusters of the one or more features indicative of the physiological state of the patient, wherein each of the clusters corresponds to a different physiological state;

compute, in real time, a metric indicative of the physiological state of the patient based, at least in part, on the determined clusters;

determine a baseline value of the metric for the patient, the baseline value corresponding to a baseline physiological state of the patient before procedural sedation begins; and

monitor, in real time, a value of the metric relative to the baseline value to assess the physiological state of the patient during the procedural sedation, wherein monitoring the value of the metric relative to the baseline value comprises determining the physiological state of the patient based, at least in part, on the determined clusters; and

a display configured to display an indication of the assessed physiological state of the patient during the procedural sedation.

2. The system of claim 1 , wherein the processor is further configured to:

detect in real time a change in the value of the metric over at least two respiratory cycles; and

determine in real time a change in the physiological state of the patient based on the change in the value of the metric.

3. The system of claim 2 , wherein the processor is further configured to:

correlate the physiological state of the patient with one or more physiological data or indicators to determine an accuracy of the determined change in physiological state.

4. The system of claim 3 , wherein the one or more physiological data or indicators are input to the clustering technique and include at least one of physiological data provided by a user, outputs from at least one of a pharmacokinetic, pharmacodynamic, and ventilatory model, and a score on a qualitative sedation scoring scheme.

5. The system of claim 1 , wherein the extracting the one or more features includes fitting a portion of the capnogram to a parameterized function.

6. The system of claim 1 , wherein the one or more features include a measure of periodicity of the capnogram.

7. The system of claim 1 , wherein the one or more features include the output of at least one of a pharmacokinetic model, a pharmacodynamics model, and a ventilatory model.

8. The system of claim 1 , wherein the one or more features that are indicative of the physiological state of the patient include a terminal value of the carbon dioxide concentration on exhalation, an end-exhalation slope, and a ratio of an intermediate exhalation slope over an initial exhalation slope.

9. The system of claim 1 , wherein the clustering technique is a k-means technique, with a number “k” of clusters corresponding to a number of sedation states for the patient.

10. The system of claim 1 , wherein the clustering technique is a technique with a variable number of clusters.

11. The system of claim 1 , wherein the metric is a multi-parameter metric, where the multi-parameter metric indicates a separation from a cluster centroid.

12. The system of claim 11 , wherein a closest centroid, as determined by the multi-parameter metric, is indicative of the physiological state of the patient.

13. The system of claim 11 , wherein a separation from a nearest centroid relative to a separation from a next-closest centroid is indicative of a degree of confidence in the physiological state of the patient.

14. The system of claim 1 , wherein the physiological state of the patient pertains to a sedation level.

15. A method for automatically providing a quantitative assessment of a physiological state of a patient during procedural sedation, the method comprising:

receiving, at a processor, from a sensor, data indicating a carbon dioxide concentration in air captured by a breath receiver, the sensor being coupled to the breath receiver;

generating, in real time, a capnogram associated with the patient, the capnogram being generated based on the carbon dioxide concentration measured by the sensor over one or more respiratory cycles;

extracting, in real time, one or more features from the capnogram that are indicative of a physiological state of the patient;

determining, in real time, using a clustering technique, clusters of the one or more features indicative of the physiological state of the patient, wherein each of the clusters corresponds to a different physiological state;

computing, in real time, a metric indicative of a physiological state of the patient based, at least in part, on the determined clusters;

determining a baseline value of the metric for the patient, the baseline value corresponding to a baseline physiological state of the patient before procedural sedation begins; and

monitoring, in real time, a value of the metric relative to the baseline value to assess the physiological state of the patient during the procedural sedation, wherein monitoring the value of the metric relative to the baseline value comprises determining the physiological state of the patient based, at least in part, on the determined clusters; and

displaying an indication of the assessed physiological state of the patient during the procedural sedation.