CLINICAL METRIC FOR PREDICTING ONSET OF CARDIORESPIRATORY DETERIORATION IN PATIENTS

• US 20160135756A1
• Filed: 11/16/2015
• Published: 05/19/2016
• Est. Priority Date: 11/18/2014
• Status: Active Grant

• Current Assignee: Baylor College of Medicine (Baylor College)
• Original Assignee: Baylor College of Medicine (Baylor College)
• Inventors: Brady, Kenneth M., Vu, Eric, Acosta, Sebastian, Penny, Daniel J., Rusin, Craig
• Granted Patent: US 10,485,486 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A system generates and displays a clinical metric based on continuously collected patient physiological data, wherein the clinical metric provides a predictive measure of the likelihood of the onset of a cardiorespiratory deterioration event in the patient in a predetermined time period in the future. If the clinical metric has a configured relationship with a predetermined threshold value, embodiments may generate an alarm in addition to or instead of displaying the clinical metric. The clinical metric thus allows clinical staff to take medically indicated actions to prevent or reduce the effects of the predicted deterioration.

Claims

1. A method of predicting an onset of cardiorespiratory deterioration of a patient, comprising:

collecting real time patient physiological data from a plurality of patient physiological sensors;

generating a clinical metric associated with a likelihood of cardiorespiratory deterioration of the patient in a predetermined future time period in real time, based on the real time patient physiological data; and

generating an alarm if the clinical metric has a predetermined relationship with a threshold value.

2. The method of claim 1, wherein the predetermined relationship is greater than or equal.

3. The method of claim 1, wherein generating a clinical metric comprises:

generating the clinical metric based on the real time patient physiological data and a patient-specific baseline physiological data.

4. The method of claim 3, wherein generating the clinical metric comprises:

normalizing the clinical metric to an average risk of deterioration in a patient population; and

calculating a risk index value in real time based on the real time patient physiological data and the patient-specific baseline physiological data.

5. The method of claim 1, further comprising:

reporting the clinical metric in real time.

6. The method of claim 1, wherein the predetermined future time period is one to two hours in the future.

7. The method of claim 1, wherein generating a clinical metric comprises:

optimizing a model based upon one or more of;

heart rate;

respiration rate variability;

SPO₂,

3D ST segment variability;

ST segment; and

heart rate variability.

8. The method of claim 1, further comprising:

collecting a patient-specific baseline data from the patient physiological sensors, and

wherein generating a clinical metric comprises;

generating the clinical metric at time t based upon real time patient physiological data collected at time t and patient-specific baseline data collected at a predetermined time before time t.

9. The method of claim 1, wherein the clinical metric is a clinical metric associated with a likelihood of cardiac arrest in an infant after Stage 1 surgical palliation.

10. The method of claim 1, wherein generating a clinical metric comprises:

optimizing a model using logistic regression; and

employing the model to analyze the real time patient physiological data.

11. The method of claim 1, wherein the cardiorespiratory deterioration comprises one or more of:

an intubation event;

a shock;

a respiratory arrest;

a cardiac arrest; and

hypoxemia.

12. A non-transitory computer readable medium, on which are stored instructions, comprising instructions that when executed cause a patient data monitoring system to:

collect real time patient physiological data from a plurality of patient physiological sensors associated with a patient;

generate a real time clinical metric associated with a likelihood of cardiorespiratory deterioration of the patient within a predetermined future time period, based on the real time patient physiological data; and

generate an alarm if the clinical metric has a predetermined relationship with a predetermined threshold value.

13. The computer readable medium of claim 12, wherein the instructions that when executed cause the patient data monitoring system to generate an alarm comprise instructions that when executed cause the patient data monitoring system to generate the alarm if the clinical metric exceeds the predetermined threshold value.

14. The computer readable medium of claim 12, wherein the instructions that when executed cause the patient data monitoring system to generate a real time clinical metric comprise instructions that when executed cause the patient data monitoring system to:

generate the clinical metric based on real time patient physiological data and a patient-specific baseline physiological data.

15. The computer readable medium of claim 14, wherein the patient-specific baseline physiological data comprises real time patient physiological data collected from the plurality of patient physiological sensors a predetermined prior time period.

16. The computer readable medium of claim 12, wherein the instructions that when executed cause the patient data monitoring system to generate a real time clinical metric comprise instructions that when executed cause the patient data monitoring system to:

normalize the clinical metric to an average risk of cardiorespiratory deterioration in a patient population.

17. The computer readable medium of claim 12, wherein the instructions that when executed cause the patient data monitoring system to generate a real time clinical metric comprise instructions that when executed cause the patient data monitoring system to:

analyze the real time patient physiological data using a model optimized by logistic regression of patient population data.

18. The computer readable medium of claim 17,

wherein the patient population comprises a population of hypoplastic left heart syndrome post-surgical palliation single ventricle infants, and

wherein the model is based on one or more of:

heart rate;

respiration rate variability;

SpO₂,

3D ST segment variability;

ST segment; and

heart rate variability.

19. The computer readable medium of claim 12, wherein the cardiorespiratory deterioration comprises one or more of:

an intubation event;

a shock;

a respiratory arrest;

a cardiac arrest; and

hypoxemia.

20. The computer readable medium of claim 12, wherein the predetermined future time period is one to two hours in the future.