IP Library Granted Patent US 12670979
Granted Patent B2
US 12670979 · App. 18/638,277 · Granted Jun 30, 2026

System and method for improving cardiovascular health of humans

Inventor: Dylan Richards (Chicago, IL)
Assignee: Prolaio, Inc.
G16H20/30G06N3/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12670979
App. No.
18/638,277
Granted
Jun 30, 2026
Kind
B2
Abstract

An estimate of a functional capacity such as VO2Max is made by applying the vital signs of a monitored human to a trained encoding neural network producing a cardio profile vector. The vector is applied to a trained functional capacity (VO2Max) neural network to estimate the functional capacity. Once estimated, an action is taken.

Claims (47)

1 . A method comprising:

providing a duration of monitored data from a monitored human to an encoding neural network, the encoding neural network configured to output a cardio profile for the monitored human, wherein the encoding neural network is trained using an error metric derived from an estimation neural network, the estimation neural network configured to receive a subset of the monitored data omitting at least one excluded cardiopulmonary variable and to generate an estimate of the at least one excluded cardiopulmonary variable;

providing the cardio profile to a functional capacity estimator;

receiving from the functional capacity estimator an estimate of a functional capacity of the monitored human; and

based on the estimate of the functional capacity, at least one of:

displaying the estimate in a time series with prior estimates to a clinician for review of possible health changes in the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon an alert is triggered to a clinician to investigate a health of the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon a request for information is sent to the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon an entry is made in a medical record of the monitored human indicating a change in the health of the monitored human has occurred;

comparing the estimate to estimates from other monitored humans to quantify health affects between at least a control group receiving a first intervention and a test group receiving a second intervention in a clinical trial;

controlling an operation of a medical device associated with treating or monitoring the monitored human; or

setting a parameter of the medical device associated with treating or monitoring the monitored human.

2 . The method of claim 1 , wherein the duration of monitored data comprises a time series of a plurality of cardiopulmonary variables.

3 . The method of claim 1 , wherein the monitored data is obtained from one or more wearable sensors configured to obtain electrocardiogram data, 3-axis accelerometer waveform data, and vital sign data.

4 . The method of claim 3 , wherein the vital sign data comprises activity data and heart rate data for the monitored human.

5 . The method of claim 1 , wherein the cardio profile comprises a set of features representing general cardiopulmonary function of the monitored human.

6 . The method of claim 1 , wherein the cardio profile comprises a plurality of real numbers associated with one or more cardiopulmonary variables in the duration of monitored data.

7 . The method of claim 1 , wherein the functional capacity estimator is configured to perform a regression to provide the estimate of the functional capacity.

8 . The method of claim 7 , wherein the regression is performed using a neural network.

9 . The method of claim 7 , wherein the regression is performed using at least one of linear regression, a decision tree, a random forest model, a gradient boosting model, a support vector machines model, or a k-nearest neighbor model.

10 . The method of claim 1 , wherein the functional capacity estimator was trained using a plurality of matched examples, each matched example comprising a cardio profile vector matched with a corresponding measured functional capacity metric.

11 . The method of claim 1 , wherein the functional capacity is VO2Max.

12 . The method of claim 1 , further comprising providing at least one physical attribute for the monitored human as input to the functional capacity estimator.

13 . A system comprising:

at least one sensor configured to obtain a duration of monitored data from a monitored human; and

one or more computer processors programmed to perform operations comprising: providing the duration of the monitored data to an encoding neural network, the

encoding neural network configured to output a cardio profile for the monitored human; providing the cardio profile to a functional capacity estimator, wherein the encoding neural network is trained using an error metric derived from an estimation neural network, the estimation neural network configured to receive a subset of the monitored data omitting at least one excluded cardiopulmonary variable and to generate an estimate of the at least one excluded cardiopulmonary variable;

receiving from the functional capacity estimator an estimate of a functional capacity of the monitored human; and

based on the estimate of the functional capacity, at least one of:

displaying the estimate in a time series with prior estimates to a clinician for review of possible health changes in the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon an alert is triggered to a clinician to investigate a health of the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon a request for information is sent to the monitored human;

comparing the estimate to prior estimates and testing for a change whereupon an entry is made in a medical record of the monitored human indicating a change in the health of the monitored human has occurred;

comparing the estimate to estimates from other monitored humans to quantify health affects between at least a control group receiving a first intervention and a test group receiving a second intervention in a clinical trial;

controlling an operation of a medical device associated with treating or monitoring the monitored human; or

setting a parameter of the medical device associated with treating or monitoring the monitored human.

14 . The system of claim 13 , wherein the duration of monitored data comprises a time series of a plurality of cardiopulmonary variables.

15 . The system of claim 13 , wherein the monitored data is obtained from one or more wearable sensors configured to obtain electrocardiogram data, 3-axis accelerometer waveform data, and vital sign data.

16 . The system of claim 15 , wherein the vital sign data comprises activity data and heart rate data for the monitored human.

17 . The system of claim 13 , wherein the cardio profile comprises a set of features representing general cardiopulmonary function of the monitored human.

18 . The system of claim 13 , wherein the cardio profile comprises a plurality of real numbers associated with one or more cardiopulmonary variables in the duration of monitored data.

19 . The system of claim 13 , wherein the functional capacity estimator is configured to perform a regression to provide the estimate of the functional capacity.

20 . The system of claim 19 , wherein the regression is performed using a neural network.

21 . The system of claim 19 , wherein the regression is performed using at least one of linear regression, a decision tree, a random forest model, a gradient boosting model, a support vector machines model, or a k-nearest neighbor model.

22 . The system of claim 13 , wherein the functional capacity estimator was trained using a plurality of matched examples, each matched example comprising a cardio profile vector matched with a corresponding measured functional capacity metric.

23 . The system of claim 13 , wherein the functional capacity is VO2Max.

24 . The system of claim 13 , the operations further comprising providing at least one physical attribute for the monitored human as input to the functional capacity estimator.