Clinical decision support system for patient-ventilator asynchrony detection and management
The present disclosure describes a system that automatically detects patient-ventilator asynchrony and trends in patient-ventilator asynchrony. The present disclosure describes a framework that uses pressure, flow, and volume waveforms to detect patient-ventilator asynchrony and the presence of secretions in the ventilator circuit.
1. A system for detecting patient-ventilator interaction comprising:
a detection module comprising computer-executable instructions stored on a non-transitory computer-readable storage medium in operable communication with one or more computer processors, the detection module configured for and in operable communication with a ventilator for acquiring mechanical ventilator airway pressure and flow waveform data; and
a patient-ventilator interaction indicator module in operable communication with the detection module, the patient-ventilator interaction indicator module comprising computer-executable instructions stored on a non-transitory computer-readable storage medium in operable communication with one or more of the computer processors for:
generating a patient-ventilator interaction indicator waveform comprising a Delta waveform from said ventilator waveform data, wherein the Delta waveform represents the difference between normalized pressure, after correcting for positive end expiratory pressure (PEEP), and normalized flow waveforms;
extracting a set of features from said patient-ventilator interaction indicator waveform; and
determining and indicating a type of patient-ventilator asynchrony present, or absence thereof, associated with one or more breath cycles, which patient-ventilator asynchrony or absence thereof is based on the extracted set of features.
2. The system of claim 1 , wherein the detection module is configured for acquiring the ventilator waveform data directly or indirectly from a mechanical ventilator, directly or indirectly from another monitor or system for producing the ventilator waveform data, or directly or indirectly from an archive of in vivo, ex vivo, in vitro and/or in silico data.
3. The system of claim 2 , wherein one or more of the computer processors is embedded in the mechanical ventilator, or another monitor or system or a networked computer system.
4. The system of claim 1 , wherein the patient-ventilator interaction module further generates an asynchrony index based on the type of patient-ventilator asynchrony present or absence thereof.
5. The system of claim 1 , wherein the Delta waveform is defined as:
δ
(
t
)
=
p
a
w
(
t
)
-
p
e
p
a
w
(
t
*
)
-
p
e
-
q
(
t
)
q
(
t
*
)
,
t
≥
t
0
,
where t is time, t 0 is the time at the start of the breath cycle, p e is positive end expiratory pressure (PEEP), p aw is airway pressure, q is air flow, and t* is time of maximum flow (q(t)≤q(t*), t≥t 0 ).
6. The system of claim 1 , wherein the Delta waveform is defined as:
δ
(
t
)
=
p
a
w
(
t
)
-
p
e
p
a
w
(
t
*
*
)
-
p
e
-
q
(
t
)
q
(
t
*
*
)
,
t
≥
t
0
,
where t is time, t 0 is the time at the start of the breath cycle, p e is positive end expiratory pressure (PEEP), p aw is airway pressure, q is air flow, t** is a time between to and t*, and t* is time of maximum flow (q(t)≤q(t*), t≥t 0 ).
7. The system of claim 1 , wherein the extracting of the set of features comprises extracting one or more of the following features:
depth of valleys of the Delta waveform;
maximum value of the Delta waveform within inspiration phase;
area under the curve of the Delta waveform within inspiration phase;
maximum cross-correlation of the Delta waveform with a delivered tidal volume waveform;
area under the portion of the Delta waveform occurring within approximately the first third of the Delta waveform duration;
maximum value of the Delta waveform occurring within approximately the first third of the Delta waveform duration; and
locations of valleys of the Delta waveform.
8. The system of claim 1 , wherein the computer-executable instructions for determining and indicating the type of patient-ventilator asynchrony present, or absence thereof, comprise a rule-based algorithm configured to classify one or more of the breath cycles into one or more categories of patient-ventilator asynchrony.
9. The system of claim 8 , wherein the rule-based algorithm classifies one or more of the breath cycles into the one or more categories of patient-ventilator asynchrony by comparing at least one value from the set of features with a predetermined threshold.
10. The system of claim 1 , wherein the computer-executable instructions for determining and indicating the type of patient-ventilator asynchrony present, or absence thereof, comprise a machine-learning classifier trained with patient data and/or synthetic data and configured to classify one or more of the breath cycles into one or more categories of patient-ventilator asynchrony.
11. The system of claim 10 , wherein the machine-learning classifier classifies one or more of the breath cycles into the one or more categories of patient-ventilator asynchrony by comparing at least one value from the set of features with a predetermined threshold.
12. The system of claim 10 , wherein the synthetic data is derived from in vitro, in silico, or both in vitro and in silico representation of a respiratory system interacting with a mechanical ventilator.
13. The system of claim 1 , further including a graphical user interface comprising:
at least one window for displaying detection of one or more patient-ventilator asynchrony;
one or more elements within the at least one window for communicating the detected patient-ventilator asynchrony.
14. The system of claim 1 , further including a transmission module comprising computer-executable instructions stored on a non-transitory computer storage medium, which transmission module is configured for operable communication with a suitable network protocol to transmit the determined and indicated type of patient-ventilator asynchrony or absence thereof to a remote server and/or smartphone and/or tablet.
15. The system of claim 14 , wherein the patient-ventilator interaction module further generates an asynchrony index based on the type of patient-ventilator asynchrony present or absence thereof and the transmission module transmits a notification to a user when the asynchrony index exceeds a pre-determined threshold.
16. The system of claim 1 , wherein the types of patient-ventilator asynchrony comprise one or more of inadequate ventilator support, double triggering, ineffective triggering, premature termination, delayed termination, flow starvation, air trapping, buildup of fluid in lungs and/or a ventilator circuit, and/or no asynchrony.
17. The system of claim 1 , wherein the computer-executable instructions for determining and indicating the type of patient-ventilator asynchrony present, or absence thereof, comprise a cascade of classifiers configured to classify one or more of the breath cycles into one or more categories of patient-ventilator asynchrony.
18. The system of claim 1 , further including a graphical user interface comprising:
at least one window for displaying detection of one or more patient-ventilator asynchrony; one or more elements within the at least one window comprising one or more recommendations for mitigating the detected patient-ventilator asynchrony.
19. The system of claim 1 , further including a graphical user interface comprising:
at least one window for displaying detection of one or more patient-ventilator asynchrony; one or more elements within the at least one window comprising educational information on the detected patient-ventilator asynchrony.
20. The system of claim 1 , further including a graphical user interface comprising:
at least one window for displaying detection of one or more patient-ventilator asynchrony; one or more elements within the at least one window for communicating an asynchrony index.