PREDICTING NEAR-TERM DETERIORATION OF HOSPITAL PATIENTS

• US 20140081092A1
• Filed: 11/22/2013
• Published: 03/20/2014
• Est. Priority Date: 10/08/2010
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Granted Patent: US 9,113,778 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/4884 inducing physiological or psychological stress, e.g. applications for stress testing
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• 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 5/7405 using sound
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes 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 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 40/67 for remote operation
• 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

Abstract

Methods, systems, and computer storage media are provided for predicting a probability of acute deterioration for a specific patient. Various discrete measurements are taken regarding the patient'"'"'s current health. Those measurements are used to determine a PPOD score, which is displayed for clinicians.

Claims

1. Computer storage media, not being a signal per se, storing computer-usable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform a method for determining a probability of acute deterioration for a particular patient, the method comprising:

receiving patient information comprising a plurality physiological measurements for a patient in anatomically challenged and unchallenged positions;

conditioning the patient information to create conditioned patient information; and

based on the conditioned patient information, determining a statistical probability of acute deterioration for the patient.

2. The media of claim 1, wherein the physiological measurements comprise systolic blood pressure (SBP) measurements and heart-rate measurements for the patient.

3. The media of claim 2, wherein the physiological measurements for the patient in anatomically challenged and unchallenged positions are derived from the patient in a supine position and a tilted position, respectively.

4. The media of claim 1 further comprising selectively providing a notification based on the determined statistical probability of acute deterioration.

5. The media of claim 1, wherein the plurality of physiological measurements comprises a timeseries of measurements with timeseries intervals greater than 30 minutes.

6. The media of claim 1, wherein conditioning the patient information includes determining an index of deviation of the patient'"'"'s current SBP from the patient'"'"'s usual SBP.

7. The media of claim 6, wherein conditioning the patient information further includes determining a baroreceptor reflex sensitivity (BRS).

8. The media of claim 1, wherein conditioning the patient information includes determining an anatomically challenged vs. unchallenged heart-beat interval difference timeseries and determining an anatomically challenged vs. unchallenged SBP difference timeseries.

9. The media of claim 1, wherein determining the statistical probability of acute deterioration involves determining a copula based on the conditioned patient information.

10. The media of claim 9, further comprising determining that the copula is an extreme-value copula.

11. The media of claim 10, wherein determining that the copula is an extreme-value copula involves comparing the determined copula to a rank-based nonparametric estimator of the patient'"'"'s copula.

12. The media of claim 9, wherein the statistical probability of acute deterioration for the patient comprises a score.

13. The media of claim 1, wherein the predicted probability of acute deterioration is determined from by logistic regression, K-nearest neighbor clustering, neural-network, support-vector machine classifier, or other statistical techniques.

14. The media of claim 1, further comprising determining a predicted length of stay for the patient, based at least in part on the determined probability of acute deterioration for the patient.

15. The media of claim 1, further comprising allocating healthcare resources for treating the patient, based at least in part on the determined probability of acute deterioration for the patient.

16. The media of claim 4, wherein the notification comprises a visual or audible alert, email, SMS text message, or electronic notification provided to a caregiver for the patient.

17. A method to prevent acute deterioration of health in a population of patients, the method comprising providing an electronic notification to caregivers of a set of members of the population who exhibit above-threshold values of a predicted probability of acute deterioration (PPOD) score calculated from a timeseries of physiological measurements acquired from a patient in anatomically challenged and unchallenged positions.

18. The method of claim 17, wherein calculating the PPOD score involves computation of a baroreceptor reflex sensitivity, an index of the deviation of the patient'"'"'s current systolic blood pressure from the pressure that is usual for the patient, and the probability that the copula of the anatomically challenged vs. unchallenged heart rate difference timeseries and the anatomically challenged vs. unchallenged systolic blood pressure difference timeseries is an extreme-value copula.

19. A computer-implemented method for providing a predicted probability of acute deterioration for a particular patient comprising:

receiving patient-specific data from a health record, the data comprising plurality of physiological measurements;

conditioning the patient-specific data to create conditioned data;

calculating, from the conditioned data, a predicted probability of acute deterioration for the particular patient by applying logistic regression, K-nearest neighbor clustering, neural network, support-vector machine classifier, or other statistical technique; and

selectively providing a notification based on the calculated predicted probability of acute deterioration.

20. The computer-implemented method of claim 19, wherein the calculation of a predicted probability of acute deterioration for the particular patient involves computation of a baroreceptor reflex sensitivity, an index of the deviation of the patient'"'"'s current systolic blood pressure from the pressure that is usual for the patient, and the probability that the copula of the anatomically challenged vs. unchallenged heart rate difference timeseries and the anatomically challenged vs. unchallenged systolic blood pressure difference timeseries is an extreme-value copula.