Granted Patent B2

US 12,558,594 · App. 17/739,906 · Granted Feb 24, 2026

Inventors: Steven Mason (Las Vegas, NV); Daniel Posnack (Fort Lauderdale, FL); Peter Arn (Roxbury, CT); Wendy Para (Las Vegas, NV); S. Adam Hacking (Nashua, NH); Micheal Mueller (Oil City, PA); Joseph Guaneri (Merrick, NY); Jonathan Greene (Denver, CO)

Assignee: ROM Technologies, Inc.

A63B24/0075A63B21/0058A63B24/0062G06N20/00G16H10/60G16H20/30A63B2022/0094A63B22/0605A63B2024/0093

Abstract

Claims (50)

1 . A computer-implemented system, comprising:

an electromechanical device configured to be manipulated by a user;

a user portal comprising an output device and input device, the output device configured to communicate a plan to the user; and

a computing device configured to:

receive user data relating to the user, wherein the user data comprises health history data relating to health indicators of the user,

receive treatment data relating to a set of treatment plans and outcomes, wherein the set of treatment plans is capable of being offered to the user,

generate the plan by using a machine learning model to process the user data and the treatment data,

select, for the electromechanical device, an electromechanical device configuration that enables one or more exercises of the plan to be performed by the user, wherein the electromechanical device configuration enables the one or more exercises to be performed to improve performance of an area of the user's body, and wherein the electromechanical device configuration modifies one or more positions of one or more radially-adjustable couplings to modify one or more diameters of one or more ranges of motion provided by one or more pedals, and

provide the electromechanical device configuration to the electromechanical device to cause a control system to modify the one or more positions.

2 . The computer-implemented system of claim 1 , wherein the treatment data comprises treatment plan data relating to the set of treatment plans and treatment outcome data relating to outcomes of the set of treatment plans.

3 . The computer-implemented system of claim 1 , wherein the computing device, when generating the plan, is configured to:

provide the user data and the treatment data as inputs to the machine learning model such that the machine learning model is configured to generate machine learning scores for electromechanical device configurations capable of being selected for the plan, wherein the machine learning scores relate to probabilities of a given device configuration being suitable for a given application or applications for the user.

4 . The computer-implemented system of claim 3 , wherein, based on the selected device configuration corresponding to a threshold probability of improving the performance of the area of the user's body, the selected electromechanical device is suitable for the given user application or applications.

5 . The computer-implemented system of claim 3 , wherein, based on the selected device configuration corresponding to a threshold probability of preventing a health-related event from occurring that affects the area of the user's body, the selected electromechanical device configuration is suitable for the given application or applications for the user.

6 . The computer-implemented system of claim 1 , wherein the electromechanical device configuration is configured such that the user, when performing the one or more exercises on the electromechanical device, is enabled to repeat one or more motions associated with at least one of developing muscle memory or improving muscle memory.

7 . The computer-implemented system of claim 1 , wherein the one or more exercises are one or more rehabilitation exercises, wherein the electromechanical device configuration comprises data related to one or more positions at which to configure one or more components of the electromechanical device, and wherein the one or more positions are configured such that the one or more rehabilitation exercises are performed by the user prior to a health-related event occurring that affects the area of the user's body.

8 . A method for using machine learning to control an electromechanical device, comprising:

receiving user data relating to a user capable of operating the electromechanical device;

receiving treatment data relating to a set of treatment plans and outcomes, wherein the set of treatment plans is capable of being offered to the user;

generating a plan by using a machine learning model to process the user data and the treatment data, wherein the plan includes at least one exercise session comprising one or more exercises to be performed on the electromechanical device;

enabling the plan to be distally accessible by one or more user portals;

selecting, for the electromechanical device, an electromechanical device configuration that enables the one or more exercises of the plan to be performed by the user, wherein the electromechanical device configuration enables the one or more exercises to be performed to improve performance of an area of the user's body, and wherein the electromechanical device configuration modifies one or more positions of one or more radially-adjustable couplings to modify one or more diameters of one or more ranges of motion provided by one or more pedals; and

enabling the electromechanical device to implement the electromechanical device configuration by providing the electromechanical device configuration to the electromechanical device, wherein a control system of the electromechanical device modifies the one or more positions.

9 . The method of claim 8 , wherein the treatment data comprises treatment plan data relating to the set of treatment plans and treatment outcome data relating to outcomes of the set of treatment plans.

10 . The method of claim 8 , wherein generating the plan comprises:

providing the user data and the treatment data as inputs to the machine learning model such that the machine learning model is configured to generate machine learning scores for electromechanical device configurations capable of being selected for the plan, wherein the machine learning scores relate to probabilities of a given device configuration being suitable for a given application or applications for the user.

11 . The method of claim 10 , wherein the selected electromechanical device is suitable for the given user application or applications based on the selected device configuration corresponding to a threshold probability of improving performance of the area of the user's body.

12 . The method of claim 10 , wherein the selected electromechanical device configuration is suitable for the given application or applications for the user based on the selected device configuration corresponding to a threshold probability of preventing a health-related event from occurring that affects the area of the user's body.

13 . The method of claim 8 , wherein the electromechanical device configuration is configured such that the user, when performing the one or more exercises on the electromechanical device, is enabled to repeat one or more motions associated with at least one of developing muscle memory or improving muscle memory.

14 . The method of claim 8 , wherein the one or more exercises are one or more rehabilitation exercises, wherein the electromechanical device configuration comprises data related to one or more positions at which to configure one or more components of the electromechanical device, and wherein the one or more positions are configured such that the one or more rehabilitation exercises are performed by the user prior to a health-related event occurring that affects that area of the user's body.

15 . The method of claim 8 , wherein the one or more exercises relate to one or more rehabilitation exercises; wherein the electromechanical device configuration comprises data related to one or more forces to apply to one or more components of the electromechanical device, and wherein said one or more forces, when applied to the one or more components of the electromechanical device, are capable of being applied by a motor of the electromechanical device as part of a rehabilitation exercise that is one of the one or more rehabilitation exercises.

16 . A system for operating an electromechanical device, comprising:

a memory device storing instructions; and

a processing device communicatively coupled to the memory device, wherein the processing device, when executing the instructions, is configured to:

receive user data relating to a user capable of operating the electromechanical device;

receive treatment data relating to a set of treatment plans and outcomes, wherein the set of treatment plans is capable of being offered to the user;

generate a plan by using a machine learning model to process the user data and the treatment data, wherein the plan includes at least one exercise session comprising one or more exercises to be performed on the electromechanical device;

enable the plan to be distally accessible by one or more user portals;

select, for the electromechanical device, an electromechanical device configuration that enables the one or more exercises of the plan to be performed by the user, wherein the electromechanical device configuration enables the one or more exercises to be performed to improve performance of an area of the user's body, and wherein the electromechanical device configuration modifies one or more positions of one or more radially-adjustable couplings to modify one or more diameters of one or more ranges of motion provided by one or more pedals; and

enable the electromechanical device to implement the electromechanical device configuration by providing the electromechanical device configuration to the electromechanical device, wherein a control system of the electromechanical device modifies the one or more positions.

17 . The system of claim 16 , wherein the processing device is further configured such that the one or more exercises, when performed by the user on the electromechanical device, enable the user to improve at least one of ROM, strength, and endurance.

18 . The system of claim 16 , wherein the processing device is further configured to further distally control, while the user is performing the one or more exercises, the electromechanical device based on the plan.

19 . The system of claim 16 , wherein the processing device is further configured to:

receive sensor data comprising one or more data values related to determining the user's progress in the plan; and

control, while the user is performing the one or more exercises, the electromechanical device based on the sensor data.

20 . The system of claim 16 , wherein the processing device is further configured to:

receive sensor data comprising one or more data values related to determining the user's progress in the plan;

provide the sensor data as an input to the machine learning model such that the machine learning model is configured to output a set of machine learning scores, wherein the set of machine learning scores relates to a set of configuration values capable of being used to modify the electromechanical device configuration;

select one or more configuration values, from the set of configuration values, based on the one or more configuration values relating to a machine learning score that satisfies a threshold machine learning score; and

provide, to the electromechanical device, a modification comprising the one or more configuration values, such that the electromechanical device is enabled to implement the modification.

Assignments (5)

Continuity (5)

References Cited (400)