Between-patient comparisons for risk stratification of future heart failure decompensation
First Claim
Patent Images
1. A method comprising:
- receiving, at an implantable medical device, patient data of a current patient;
determining, at the implantable medical device, a reference group related to the current patient, the reference group including patients with at least one similar characteristic to the current patient;
detecting, at the implantable medical device, a triggering event, the triggering event comprising an interrogation of the implantable medical device;
updating, at the implantable medical device, the population of the reference group related to the patient in response to detecting the triggering event;
determining, at the implantable medical device, a reference group dataset selected from the updated reference group, wherein the dataset includes patient data that is of a similar type received from the implantable medical device;
generating, at the implantable medical device, a model of the reference group dataset, wherein the model is generated using a probability distribution function; and
deriving a numerical index by calculating an area under the probability distribution function and using the area as the numerical index that indicates an activity index of the current patient, and wherein calculating the area under the probability distribution function comprises;
identifying a plurality of points on the probability distribution function, the plurality of points having equivalent probability density and defining an interval or area of integration; and
calculating the area of the interval or area of integration; and
using the numerical index to determine at least one of;
a similarity of the patient to the reference group, how likely the patient is to decompensate within a timeframe relative to a reference group'"'"'s likelihood of heart failure decompensation in the timeframe, how likely the patient is to die in a timeframe relative to a reference group'"'"'s likelihood of dying in the timeframe, how likely the patient'"'"'s quality of life is to change a timeframe relative to a reference group'"'"'s likelihood of quality of life changing in the timeframe, or stratify the patient into one or more discrete groups associated with one or more risk levels.
1 Assignment
0 Petitions
Accused Products
Abstract
This document discusses, among other things, systems and methods for using between-patient comparisons for risk stratification of future heart failure decompensation. A method comprises receiving patient data of a current patient, the patient data collected by a patient monitoring device; determining a reference group related to the patient; determining a reference group dataset selected from the reference group, wherein the dataset includes patient data that is of a similar type received from the patient monitoring device; generating a model of the reference group dataset; and automatically comparing the received physiological data to a model to derive an index for the patient.
78 Citations
20 Claims
-
1. A method comprising:
-
receiving, at an implantable medical device, patient data of a current patient; determining, at the implantable medical device, a reference group related to the current patient, the reference group including patients with at least one similar characteristic to the current patient; detecting, at the implantable medical device, a triggering event, the triggering event comprising an interrogation of the implantable medical device; updating, at the implantable medical device, the population of the reference group related to the patient in response to detecting the triggering event; determining, at the implantable medical device, a reference group dataset selected from the updated reference group, wherein the dataset includes patient data that is of a similar type received from the implantable medical device; generating, at the implantable medical device, a model of the reference group dataset, wherein the model is generated using a probability distribution function; and deriving a numerical index by calculating an area under the probability distribution function and using the area as the numerical index that indicates an activity index of the current patient, and wherein calculating the area under the probability distribution function comprises; identifying a plurality of points on the probability distribution function, the plurality of points having equivalent probability density and defining an interval or area of integration; and calculating the area of the interval or area of integration; and using the numerical index to determine at least one of;
a similarity of the patient to the reference group, how likely the patient is to decompensate within a timeframe relative to a reference group'"'"'s likelihood of heart failure decompensation in the timeframe, how likely the patient is to die in a timeframe relative to a reference group'"'"'s likelihood of dying in the timeframe, how likely the patient'"'"'s quality of life is to change a timeframe relative to a reference group'"'"'s likelihood of quality of life changing in the timeframe, or stratify the patient into one or more discrete groups associated with one or more risk levels. - View Dependent Claims (2, 3, 4, 5, 6, 8, 9, 10)
-
-
7. The method of 1, wherein using the numerical index includes comparing the numerical index to one or more threshold values to categorize the patient into a risk level.
-
11. A system comprising:
-
an implantable patient device comprising; a communication module adapted to receive patient data associated with a patient; a reference group module adapted to; select and store reference group data corresponding to the patient; detect a triggering event, the triggering event comprising an interrogation of the patient device; and update the population of the reference group corresponding to the patient in response to detecting the triggering event; and an analysis module adapted to; generate a model of the updated reference group data; and compare the patient data to the model to calculate a numerical index for the patient by calculating an area under a probability distribution function, and using the area as the numerical index that indicates an activity index of the current patient, and wherein to calculate the area under the probability distribution function, the analysis module is adapted to; identify a plurality of points on the probability distribution function, the plurality of points having equivalent probability density and defining an interval or area of integration; and calculate the area of the interval or area of integration; and use the numerical index to determine at least one of;
a similarity of the patient to the reference group, how likely the patient is to decompensate within a timeframe relative to a reference group'"'"'s likelihood of heart failure decompensation in the timeframe, how likely the patient is to die in a timeframe relative to a reference group'"'"'s likelihood of dying in the timeframe, how likely the patient'"'"'s quality of life is to change a timeframe relative to a reference group'"'"'s likelihood of quality of life changing in the timeframe, or stratify the patient into one or more discrete groups associated with one or more risk levels. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A non-transitory computer-readable medium, including instructions that, when performed by an implantable medical device, cause the implantable medical device to:
-
receive patient data of a current patient, the patient data collected by a patient monitoring device; determine a reference group related to the current patient; detect a triggering event, the triggering event comprising an interrogation of the patient monitoring device; update the population of the reference group related to the current patient in response to detecting the triggering event; determine a reference group dataset selected from the updated reference group, wherein the dataset includes patient data that is of a similar type received from the patient monitoring device; generate a model of the updated reference group dataset, wherein the model is generated using a probability distribution function; and derive a numerical index by calculating an area under the probability distribution function and using the area as the numerical index that indicates an activity index of the current patient, and wherein the instructions to calculate the area under the probability distribution function comprises instructions to; identify a plurality of points on the probability distribution function, the plurality of points having equivalent probability density and defining an interval or area of integration; and calculate the area of the interval or area of integration; and use the numerical index to determine at least one of;
a similarity of the patient to the reference group, how likely the patient is to decompensate within a timeframe relative to a reference group'"'"'s likelihood of heart failure decompensation in the timeframe, how likely the patient is to die in a timeframe relative to a reference group'"'"'s likelihood of dying in the timeframe, how likely the patient'"'"'s quality of life is to change a timeframe relative to a reference group'"'"'s likelihood of quality of life changing in the timeframe, or stratify the patient into one or more discrete groups associated with one or more risk levels. - View Dependent Claims (17, 18, 19, 20)
-
Specification