System and method for optimizing the frequency of data collection and thresholds for deterioration detection algorithm

• US 10,039,451 B2
• Filed: 11/25/2013
• Issued: 08/07/2018
• Est. Priority Date: 12/03/2012
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Gross, Brian David, Frassica, Joseph James
• Primary Examiner(s): Murillo Garcia, Fabricio R
• Application Number:
  US14/646,030
• Publication Number:
  US 20150297078A1
• Time in Patent Office: 1,716 Days
• Field of Search: 34087007
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• 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 5/082 Evaluation by breath analysis, e.g. determination of the chemical composition of exhaled breath A61B5/083, A61B5/091 take precedence
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• 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: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method of monitoring a patient includes receiving patient data from one or more sensors a patient monitoring system, comparing the received patient data with preselected thresholds indicative of patient status, determining a patient status from comparing the received patient data with the preselected thresholds, and adjusting a sampling frequency of the one or more sensors based on the determined patient status.

Claims

1. A patient monitoring system comprising:

one or more sensors configured to sample patient data of a patient;

a controller configured to receive the sampled patient data from the one or more sensors, the controller programmed to;

control the one or more sensors to sample the patient data with a sampling frequency;

determine a patient status with the sampled patient data;

determine a baseline of the sampled patient data;

calculate a propensity score for deterioration and probability thresholds based on the baseline of the sampled patient data;

calculate an initial probability curve from the propensity score and the probability thresholds;

determine at least one of a predisposition for a deterioration event and a probability of deterioration used to optimize the sampling frequency of the one or more sensors based on the patient status and based on the calculated initial probability curve;

adjust the sampling frequency based on the determined predisposition for the deterioration event and the probability of deterioration; and

control the one or more sensors to sample the sampled patient data at the adjusted sampling frequency.

2. The patient monitoring system according to claim 1, wherein the sampled patient data includes at least one of a currently monitored physiological data and an inputted clinical data.

3. The patient monitoring system according to claim 1, wherein the controller is further programmed to determine a patient clinical profile based on the sampled patient data and the at least one of the predisposition for a deterioration event and the probability of deterioration.

4. The patient monitoring system according to claim 3, wherein the controller is further programmed to adjust the sampling frequency of the one or more predetermined sensors which measure parameters of interest according to the patient clinical profile.

5. The patient monitoring system according to claim 1, wherein the patient status is determined by comparing the received patient data against previously received patient data.

6. The patient monitoring system according to claim 1, wherein the controller is further configured to receive clinical data, including electronic medical records, from a patient information system, the controller further programmed to:

determine the patient status from the clinical data.

7. The patient monitoring system according to claim 6, wherein the clinical data includes electronic medical records.

8. The patient monitoring system according to claim 1, wherein the controller is further configured to display the determined predisposition for deterioration and probability of deterioration and the adjusted sample frequency to a user.

9. A method of monitoring a patient, the method comprising:

receiving patient data from one or more sensors of a patient monitoring system;

receiving clinical data from a patient information system;

comparing the received patient data with preselected patient status thresholds;

determining a patient status from comparing the received patient data with the preselected patient status thresholds and the received clinical data;

determining a baseline of the received patient data;

calculating a propensity score indicative of a probability of deterioration and probability thresholds based on the baseline of the received patient data and the received clinical data;

calculating an initial probability curve from the propensity score and the calculated probability thresholds;

determining at least one of a predisposition for a deterioration event and a probability of deterioration based on the calculated initial probability curve; and

adjusting a sampling frequency of the one or more sensors based on the determined predisposition for the deterioration event and the probability of deterioration.

10. The method according to claim 9, wherein the patient data includes at least one of a currently monitored physiological data and an inputted clinical data.

11. The method according to claim 9, further including:

determining a patient clinical profile based on the patient and the received clinical data and the at least one of a predisposition for a deterioration event and the probability of deterioration.

12. The method according to claim 11, further including:

adjusting the sampling frequency of the one or more sensors, the sensors being configured to measure parameters of interest according to the patient clinical profile.

13. The method according to claim 9, wherein the patient data includes at least one of currently monitored physiological data and inputted clinical data and the patient status is determined by comparing the received patient data against previously received patient data.

14. A non-transitory computer readable medium containing software which, when loaded into a processor, programs the processor to

receive patient data from one or more sensors of a patient monitoring system;

receive clinical data from a patient information system;

compare the received patient data with preselected patient status thresholds;

determine a patient status from comparing the received patient data with the preselected patient status thresholds and the received clinical data;

determine a baseline of the received patient data;

calculate a propensity score indicative of a probability of deterioration and probability thresholds based on the baseline of the received patient data and the received clinical data;

calculate an initial probability curve from the propensity score and the calculated probability thresholds;

determine at least one of a predisposition for a deterioration event and a probability of deterioration based on the calculated initial probability curve; and

adjust a sampling frequency of the one or more sensors based on the determined predisposition for the deterioration event and the probability of deterioration.

15. A patient monitoring station comprising:

one or more sensors via which physiological data is received; and

one or more processors programmed to

receive patient data from one or more sensors of a patient monitoring system;

receive clinical data from a patient information system;

compare the received patient data with preselected patient status thresholds;

determine a patient status from comparing the received patient data with the preselected patient status thresholds and the received clinical data;

determine a baseline of the received patient data;

calculate a propensity score indicative of a probability of deterioration and probability thresholds based on the baseline of the received patient data and the received clinical data;

calculate an initial probability curve from the propensity score and the calculated probability thresholds;

determine at least one of a predisposition for a deterioration event and a probability of deterioration based on the calculated initial probability curve; and

adjust a sampling frequency of the one or more sensors based on the determined predisposition for the deterioration event and the probability of deterioration.

16. A patient monitoring system comprising:

one or more sensors which sample patient data of a patient at a sampling frequency;

a patient information system which receives patient data, treatment, imaging and procedure results, medication, interventions, and physiological data for the patient, the patient information system including a controller, a communication processor, memory for storing the received patient data, at least one or more user input devices, and a display for displaying the patient data;

a deterioration detection system configured to;

receive the sampled patient data from the one or more sensors;

determine a patient status with the sampled patient data;

determine a baseline of the sampled patient data;

calculate a propensity score for deterioration and probability thresholds based on the baseline of the sampled patient data;

calculate an initial probability curve from the propensity score and the probability thresholds;

determine at least one of a predisposition for a deterioration event and a probability of deterioration to optimize the sampling frequency of the one or more sensors based on the calculated initial probability curve; and

adjust the sampling frequency of the one or more sensors based on the determined predisposition for deterioration event and the probability of deterioration; and

a communication network including transmitters and receivers configured to send and receive data.

17. The patient monitoring system according to claim 16, wherein deterioration detection system further determines a clinical profile based on the sampled patient data and at least one of a predisposition for a deterioration event and a probability of deterioration.

18. The patient monitoring system according to claim 17, wherein deterioration detection system further adjusts the sampling frequency of the one or more sensors which measure parameters of interest according to the clinical profile.

19. The patient monitoring system according to claim 16, wherein the sampled patient data includes at least one of currently monitored physiological data and inputted clinical data and the patient status is determined by comparing the received patient data against previously received patient data.

20. The patient monitoring system according to claim 16, further including:

a controller configured to receive the sampled patient data from the one or more sensors and control the one or more sensors to sample the sampled patient data at the adjusted sampling frequency based on the determined predisposition for deterioration event and the probability of deterioration.

21. The patient monitoring system according to claim 20, wherein the controller is further configured to display the determined predisposition for deterioration and probability of deterioration and the adjusted sample frequency to a user.