Identifying fall risk using machine learning algorithms
AssigneeiShoe
InventorsKatharine Forth, Erez Lieberman Aiden
Life of this patent
Estimating the term…
Abstract
A person's fall risk may be determined based on machine learning algorithms. The fall risk information can be used to notify the person and/or a third party monitoring person (e.g. doctor, physical therapist, personal trainer, etc.) of the person's fall risk. This information may be used to monitor and track changes in fall risk that may be impacted by changes in health status, lifestyle behaviors or medical treatment. Furthermore, the fall risk classification may help individuals be more careful on the days they are more at risk for falling. The fall risk may be estimated using machine learning algorithms that process data from load sensors by computing basic and advanced punctuated equilibrium model (PEM) stability metrics.
Claims20
A method, comprising:
- receiving, by a processor, a plurality of load data points over a period of time from at least two load detecting modules;
- and
- estimating, by the processor, a fall risk by applying a machine learning algorithm to the plurality of load data points, wherein the step of estimating the fall risk comprises:
- calculating center of pressure (COP) data based, at least in part, on the plurality of load data points;
- determining a plurality of posture states identified with Hidden Markov Model techniques based, at least in part, on the center of pressure (COP) data;
- calculating one or more base punctuated equilibrium model (PEM) stability metrics based, at least in part, on the plurality of posture states;
- calculating one or more advanced punctuated equilibrium model (PEM) stability metrics based, at least in part, on the plurality of posture states;
- and
- determining the fall risk based, at least in part, on the one or more base punctuated equilibrium model (PEM) stability metrics and on the one or more advanced punctuated equilibrium model (PEM) stability metrics.
The method of claim 2, wherein the step of estimating the fall risk further comprises calculating at least one basic non-PEM metric from COP.
A system for determining postural stability and fall risk of a person, comprising:
- two or more load detecting modules configured to acquire a plurality of load data points;
- a signal preparation module coupled to the load detecting modules and configured to convert the plurality of load data points to a transmittable form;
- a communication module coupled to the signal preparation module, the communication module configured to:
- receive the plurality of load data points from the signal preparation module;
- transmit the plurality of load data points;
- and
- a data analysis module configured to analyze the plurality of load data points received from the signal preparation module, wherein the data analysis module is configured to perform steps comprising:
- calculating center of pressure (COP) data based, at least in part, on the plurality of load data points;
- determining a plurality of posture states identified with Hidden Markov Model techniques based, at least in part, on the center of pressure (COP) data;
- calculating one or more base punctuated equilibrium model (PEM) stability metrics based, at least in part, on the plurality of posture states;
- calculating one or more advanced punctuated equilibrium model (PEM) stability metrics based, at least in part, on the plurality of posture states;
- and
- determining the fall risk based, at least in part, on the one or more base punctuated equilibrium model (PEM) stability metrics and on the one or more advanced punctuated equilibrium model (PEM) stability metrics;
- and
- a display module coupled to the data analysis module and configured to display results from the data analysis module comprising at least an indication of the fall risk.
An apparatus, comprising:
- two or more load detecting modules configured to acquire a plurality of load data points;
- a signal preparation module coupled to the load detecting modules and configured to convert the plurality of load data points to a transmittable form;
- a communications module coupled to the signal preparation module and configured to:
- transmit the plurality of load data points to a data analysis module;
- and
- receive, from the data analysis module, a fall risk calculated by a machine learning algorithm based, at least in part, on one or more base punctuated equilibrium model (PEM) stability metrics and on one or more advanced punctuated equilibrium model (PEM) stability metrics;
- and
- a display module configured to display an indication of the received fall risk.
Dependencies are inferred from the claim text.