Granted Patent B2

US 12,220,263 · App. 16/650,581 · Granted Feb 11, 2025

Inventors: Amir Hossein Hayeri (Vancouver, CA); Ricardo Cacho (Vancouver, CA); Suvan Ashok Ramchandani (Vancouver, CA); Nicolas Brandt (Vancouver, CA); Aleksey Sher (Vancouver, CA)

Assignee: BIO-CONSCIOUS TECHNOLOGIES INC.

A61B5/7275A61B5/024A61B5/14532G16H40/63G16H40/67G16H50/20G16H50/30G16H50/70

Abstract

Claims (102)

1. A computer-implemented method of facilitating physiological property forecasting for detecting disease complications, the method comprising:

receiving signals representing sensed physiological property indicators, each of the sensed physiological property indicators representing a sensed physiological property of a patient at a respective time;

receiving signals representing one or more contextual indicators associated with the sensed physiological property indicators;

applying at least one classification criterion to the one or more contextual indicators to determine a patient state of a plurality of possible patient states, each patient state associated with a respective set of forecasting parameters; and

applying the set of forecasting parameters associated with the determined patient state to the sensed physiological property indicators to determine at least one forecast physiological property indicator representing a forecast physiological property of the patient at a future time;

wherein each of the sets of forecasting parameters includes a plurality of sets of historical physiological property indicators, each of the sets of historical physiological property indicators representing physiological properties of the patient during a respective historical time period, and wherein applying the set of forecasting parameters associated with the determined patient state comprises:

comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state;

selecting at least one of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state based on said comparing;

generating a time-dependent function representing the selected at least one of the sets of historical physiological property indicators;

determining the at least one forecast patient physiological property indicator using the generated time-dependent function;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a sum of differences between the sensed patient physiological property indicators and respective ones of the historical physiological property indicators included in the set of historical physiological indicators;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical patient physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a weight associated with the set of historical physiological property indicators and applying the weight to the determined sum of differences;

wherein determining the weight associated with the set of historical physiological property indicators comprises:

determining a change over time of at least some of the historical physiological property indicators included in the set;

applying a probability density function to the change to determine a probability density for the change occurring within a time period associated with the sensed physiological property indicators; and

determining the weight based on the determined probability density;

wherein each of the at least one forecast physiological property indicators includes a blood glucose value representing a forecast future blood glucose level of the patient; and

wherein the method further comprises:

adjusting, by a computer for managing insulin injection, an insulin injection to correct blood glucose levels in response to the forecast future blood glucose levels indicated by the at least one forecast physiological property indicator.

2. The method of claim 1 wherein the sensed physiological property indicators are sensed first physiological property indicators, each representing a sensed first physiological property of the patient, and wherein the one or more contextual indicators include sensed second physiological property indicators, each representing a second physiological property of the patient, said second physiological property being a different physiological property from the first physiological property.

3. The method of claim 1 wherein the one or more contextual indicators includes a heart rate value representing a heart rate of the patient and wherein applying the at least one classification criterion to the one or more contextual indicators comprises determining whether the heart rate value is within one of a plurality of heart rate value ranges.

4. The method of claim 1 wherein the one or more contextual indicators includes an activity value representing an activity level of the patient and wherein applying the at least one classification criterion to the one or more contextual indicators comprises determining whether the activity value is within one of a plurality of activity value ranges.

5. The method of claim 1 further comprising:

receiving signals representing physiological property forecasting training information, the training information including:

the historical physiological property indicators included in the plurality of sets of historical physiological property indicators; and

contextual indicators, each associated with at least one of the historical physiological property indicators;

identifying the plurality of sets of historical physiological property indicators from the historical physiological property indicators;

classifying each of the sets of historical physiological property indicators based on the contextual indicators associated with the physiological indicators included in the sets, said classifying comprising, for each of the sets of historical physiological property indicators:

applying at least one classification criterion to one or more of the contextual indicators associated with the set of historical physiological property indicators; and

associating the set of historical physiological property indicators with one of the plurality of possible patient states.

6. A system for facilitating physiological property forecasting for detecting disease complications, the system comprising a forecaster device having at least one processor configured to:

receive signals representing sensed physiological property indicators, each of the sensed physiological property indicators representing a sensed physiological property of a patient at a respective time;

receive signals representing one or more contextual indicators associated with the sensed physiological property indicators;

apply at least one classification criterion to the one or more contextual indicators to determine a patient state of a plurality of possible patient states, each patient state associated with a respective set of forecasting parameters; and

apply the set of forecasting parameters associated with the determined patient state to the sensed physiological property indicators to determine at least one forecast physiological property indicator representing a forecast physiological property of the patient at a future time;

wherein each of the sets of forecasting parameters includes a plurality of sets of historical physiological property indicators, each of the sets of historical physiological property indicators representing physiological properties of the patient during a respective historical time period, and wherein applying the set of forecasting parameters associated with the determined patient state comprises:

comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state;

selecting at least one of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state based on said comparing;

generating a time-dependent function representing the selected at least one of the sets of historical physiological property indicators; and

determining the at least one forecast patient physiological property indicator using the generated time-dependent function;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a sum of differences between the sensed patient physiological property indicators and respective ones of the historical physiological property indicators included in the set of historical physiological indicators;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical patient physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a weight associated with the set of historical physiological property indicators and applying the weight to the determined sum of differences;

wherein determining the weight associated with the set of historical physiological property indicators comprises:

determining a change over time of at least some of the historical physiological property indicators included in the set;

applying a probability density function to the change to determine a probability density for the change occurring within a time period associated with the sensed physiological property indicators; and

determining the weight based on the determined probability density;

wherein each of the at least one forecast physiological property indicators includes a blood glucose value representing a forecast future blood glucose level of the patient;

wherein the system further comprises a computer for managing insulin injection; and

wherein the computer for managing insulin injection is configured to:

receive the at least one forecast physiological property indicators; and

adjust an insulin injection to correct blood glucose levels in response to the forecast future blood glucose levels indicated by the at least one forecast physiological property indicators.

7. The system of claim 6 , further comprising:

a blood glucose sensor;

a patient device; and

a server computing device separate from the patient device and the blood glucose sensor;

wherein the server computing device includes the forecaster device; and

wherein the patient device is configured to transmit the signals representing the sensed physiological property indicators to the server computing device.

8. The system of claim 6 , further comprising:

a blood glucose sensor; and

a patient device;

wherein the patient device is configured to receive the signals representing the sensed physiological property indicators from the blood glucose sensor; and

wherein the patient device includes the forecaster device.

9. A non-transitory computer readable medium having stored thereon codes which when executed by at least one processor cause the at least one processor to:

receive signals representing sensed physiological property indicators, each of the sensed physiological property indicators representing a sensed physiological property of a patient at a respective time;

receive signals representing one or more contextual indicators associated with the sensed physiological property indicators;

apply at least one classification criterion to the one or more contextual indicators to determine a patient state of a plurality of possible patient states, each patient state associated with a respective set of forecasting parameters; and

apply the set of forecasting parameters associated with the determined patient state to the sensed physiological property indicators to determine at least one forecast physiological property indicator representing a forecast physiological property of the patient at a future time;

wherein each of the sets of forecasting parameters includes a plurality of sets of historical physiological property indicators, each of the sets of historical physiological property indicators representing physiological properties of the patient during a respective historical time period, and wherein applying the set of forecasting parameters associated with the determined patient state comprises:

comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state;

selecting at least one of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state based on said comparing;

generating a time-dependent function representing the selected at least one of the sets of historical physiological property indicators; and

determining the at least one forecast patient physiological property indicator using the generated time-dependent function;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a sum of differences between the sensed patient physiological property indicators and respective ones of the historical physiological property indicators included in the set of historical physiological indicators;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical patient physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a weight associated with the set of historical physiological property indicators and applying the weight to the determined sum of differences;

wherein determining the weight associated with the set of historical physiological property indicators comprises:

determining a change over time of at least some of the historical physiological property indicators included in the set;

applying a probability density function to the change to determine a probability density for the change occurring within a time period associated with the sensed physiological property indicators; and

determining the weight based on the determined probability density;

wherein each of the at least one forecast physiological property indicators includes a blood glucose value representing a forecast future blood glucose level of the patient; and

wherein the codes further cause the at least one processor to:

cause a computer for managing insulin injection to adjust an insulin injection to correct blood glucose levels in response to the forecast future blood glucose levels indicated by the at least one forecast physiological property indicator.

10. A system for facilitating physiological property forecasting for detecting disease complications, the system comprising:

means for receiving signals representing sensed physiological property indicators, each of the sensed physiological property indicators representing a sensed physiological property of a patient at a respective time;

means for receiving signals representing one or more contextual indicators associated with the sensed physiological property indicators;

means for applying at least one classification criterion to the one or more contextual indicators to determine a patient state of a plurality of possible patient states, each patient state associated with a respective set of forecasting parameters; and

means for applying the set of forecasting parameters associated with the determined patient state to the sensed physiological property indicators to determine at least one forecast physiological property indicator representing a forecast physiological property of the patient at a future time;

wherein each of the sets of forecasting parameters includes a plurality of sets of historical physiological property indicators, each of the sets of historical physiological property indicators representing physiological properties of the patient during a respective historical time period, and wherein applying the set of forecasting parameters associated with the determined patient state comprises means for:

comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state;

selecting at least one of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state based on said comparing;

generating a time-dependent function representing the selected at least one of the sets of historical physiological property indicators; and

determining the at least one forecast patient physiological property indicator using the generated time-dependent function;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a sum of differences between the sensed patient physiological property indicators and respective ones of the historical physiological property indicators included in the set of historical physiological indicators;

wherein comparing the sensed patient physiological property indicators to each of the sets of historical physiological property indicators comprises, for each of the sets of historical patient physiological property indicators included in the set of forecasting parameters associated with the determined patient state, determining a weight associated with the set of historical physiological property indicators and applying the weight to the determined sum of differences;

wherein determining the weight associated with the set of historical physiological property indicators comprises:

determining a change over time of at least some of the historical physiological property indicators included in the set;

applying a probability density function to the change to determine a probability density for the change occurring within a time period associated with the sensed physiological property indicators; and

determining the weight based on the determined probability density;

wherein each of the at least one forecast physiological property indicators includes a blood glucose value representing a forecast future blood glucose level of the patient;

wherein the system further comprises means for managing insulin injection; and

wherein the means for managing insulin injection includes:

means for receiving the at least one forecast physiological property indicators; and

means for adjusting an insulin injection to correct blood glucose levels in response to the forecast future blood glucose levels indicated by the at least one forecast physiological property indicators.

Assignments (2)

Continuity (3)

References Cited (19)