# US 2019/0172585 A1 · Method and system for injury risk prediction and corrective action for high contact type activity

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0172585 A1
- Document ID: US20190172585A1
- Status: Published application
- Kind: A1
- Application number: 16/208,095
- Filed: 2018-12-03
- Published: 2019-06-06
- Earliest claimed: 2017-12-01
- Assignees: Tata Consultancy Services Limited
- Applicants: Tata Consultancy Services Limited
- Inventors: Oishee MAZUMDER; Aniruddha SINHA; Kingshuk CHAKRAVARTY; Debatri CHATTERJEE
- Web page: https://patentgrep.com/patent/US20190172585A1

## CPC

- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 50/50: for simulation or modelling of medical disorders
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system and method for risk prediction and corrective action for a contact type activity is provided. The method includes generating a personalized full body musculoskeletal model to depict the knee and ankle joint behavior of a subject during the contact type activity. Various contact type activities are simulated using the personalized full body musculoskeletal model. Injury biomarkers and their parameters based on the contact type activities are identified, parameters are indicative of risk of injury to participating muscle groups said activity. Based on the injury biomarkers, optimal muscle co-activation parameters are analyzed by a neuro-muscular controller, to adapt the participating muscle groups for providing the correction action against the predicted risk of injury. Said optimal muscle co-activation parameters are indicative of muscle synergy during the contact type activity.

## Claims

### Claim 1

A processor-implemented method for risk prediction and corrective action for a contact type activity, the method comprising:
generating a personalized full body musculoskeletal model to depict a knee and ankle joint behavior of a subject during the contact type activity, via one or more hardware processors;
simulating one or more contact type activities using the personalized full body musculoskeletal model, via the one or more hardware processors;
identifying a plurality of injury biomarkers based on the one or more contact type activities, via the one or more hardware processors;
analyzing, via the one or more hardware processors, a plurality of parameters indicative of risk of injury to a plurality of participating muscle groups during the one or more contact type activities calculated with respect to the plurality of injury biomarkers to predict said risk of injury; and
generating, based on at least the plurality of injury biomarkers, a plurality of optimal muscle co-activation parameters by a neuro-muscular controller via the one or more hardware processors, to adapt the plurality of participating muscle groups for providing the correct action against the risk of injury being predicted, the plurality of optimal muscle co-activation parameters indicative of muscle synergy during the one or more contact type activities.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the personalized full body musculoskeletal model comprises a 92 muscle actuators, a 3 degrees of freedom (DoF) knee with ligament connectivity, and 9 ligament bundles designed and placed with respect to anatomical constraints and bounds of the subject.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the plurality of injury biomarkers comprises hip abduction angle, knee adduction load, knee flexion and ankle inversion angle.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein the plurality of participating muscles groups comprises quadriceps Hamstring, and Tibialis anterior and Gastrocnemius, wherein a change in a co-activation ratio of the plurality of participating muscles groups produce detectable changes in the plurality of injury biomarkers.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the plurality of injury biomarkers are identified through inverse dynamics simulation of the personalized full body musculoskeletal model.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the plurality of parameters are indicative of the risk of injury comprises muscle condition, joint kinematics and kinetics associated with said risk.

### Claim 7 (depends on 4)

The method as claimed in claim 4, further comprising:
designing a plurality of neuro-muscular controllers by varying the co-activation ratios associated with the plurality of muscle groups during the contact type activity; and
selecting, from the plurality of neuro-muscular controllers, the neuro-muscular controller capable of generating the plurality of optimal muscle co-activation parameters, wherein selecting the neuro-muscular controller comprises, performing for each of the plurality of neuro-muscular controllers:
optimally adjusting the co-activation ratios of the plurality of muscle groups by assigning incremental values to the co-activation ratios corresponding to a plurality of combinations of the plurality of muscles groups;
performing, for the plurality of combinations:
calculating a muscle tendon dynamics using muscle characteristics and force, velocity relation,
computing multibody dynamic equation and deriving kinematic parameters, the kinematic parameters comprising acceleration, velocity and position;
calculating values of the plurality of injury biomarkers for the plurality of combinations and comparing till a set of predefined constraints are satisfied; and
determining, based on the set of predefined constraints, a combination of the plurality of combinations as the optimal muscle co-activation parameters.

### Claim 8 (depends on 7)

The method as claimed in claim 7, wherein the set of predefined constraints comprises: hip abduction angle be minimum, knee flexion angle be maximum, knee abduction loading be minimum, and ankle inversion angle be minimum.

### Claim 9 (depends on 8)

The method as claimed in claim 8, wherein the set of predefined constraints follows an order of priority comprising Hip abduction angle being at highest priority, followed by Knee loading, followed by the knee flexion, followed by ankle inversion.

### Claim 10

A system for risk prediction and corrective action for a contact type activity, the system comprising:
one or more memories; and
one or more hardware processors, the one or more memories coupled to the one or more hardware processors, wherein the one or more hardware processors are capable of executing programmed instructions stored in the one or more memories to:
generate a personalized full body musculoskeletal model to depict a knee and ankle joint behavior of a subject during the contact type activity;
simulate one or more contact type activities using the personalized full body musculoskeletal model;
identify a plurality of injury biomarkers based on the one or more contact type activities;
analyze a plurality of parameters indicative of risk of injury to a plurality of participating muscle groups during the one or more contact type activities calculated with respect to the plurality of injury biomarkers to predict said risk of injury; and
generate, based on at least the plurality of injury biomarkers, a plurality of optimal muscle co-activation parameters by a neuro-muscular controller, to adapt the plurality of participating muscle groups for providing the correct action against the risk of injury being predicted, the plurality of optimal muscle co-activation parameters indicative of muscle synergy during the one or more contact type activities.

### Claim 11 (depends on 10)

The system as claimed in claim 10, wherein the personalized full body musculoskeletal model comprises a 92 muscle actuators, a 3 degrees of freedom (DoF) knee with ligament connectivity, and 9 ligament bundles designed and placed with respect to anatomical constraints and bounds of the subject.

### Claim 12 (depends on 10)

The system as claimed in claim 10, wherein the plurality of injury biomarkers comprises hip abduction angle, knee adduction load, knee flexion and ankle inversion angle.

### Claim 13 (depends on 10)

The system as claimed in claim 10, wherein the plurality of participating muscles groups comprises quadriceps Hamstring, and Tibialis anterior and Gastrocnemius, wherein a change in an co-activation ratio of the plurality of participating muscles groups produce detectable changes in the plurality of injury biomarkers.

### Claim 14 (depends on 10)

The system as claimed in claim 10, wherein the plurality of injury biomarkers are identified through inverse dynamics simulation of the personalized full body musculoskeletal model.

### Claim 15 (depends on 10)

The system as claimed in claim 10, wherein the plurality of parameters are indicative of the risk of injury comprises muscle condition, joint kinematics and kinetics associated with said risk.

### Claim 16 (depends on 10)

The system as claimed in claim 10, wherein the one or more hardware processors are further configured by the instructions to:
design a plurality of neuro-muscular controller by varying the co-activation ratio associated with the plurality of muscle groups during the contact type activity; and
select, from the plurality of neuro-muscular controllers, the neuro-muscular controller capable of generating the plurality of optimal muscle co-activation parameters, wherein to select the neuro-muscular controller, the one or more hardware processors are further configured by instruction to performing for each of the plurality of neuro-muscular controllers:
optimally adjust the co-activation ratio of the plurality of muscle groups by assigning incremental values to the co-activation ratios corresponding to a plurality of combinations of the plurality of muscles groups, and for the plurality of combinations, performing:
calculate a muscle tendon dynamics using muscle characteristics and force, velocity relation,
compute multibody dynamic equation and deriving kinematic parameters, the kinematic parameters comprising acceleration, velocity and position;
calculate values of the plurality of injury biomarkers for the plurality of combinations and compare till a set of predefined constraints are satisfied; and
determine, based on the set of predefined constraints, a combination of the plurality of combinations as the optimal muscle co-activation parameters.

### Claim 17 (depends on 16)

The system as claimed in claim 16, wherein the set of predefined constraints comprises: hip abduction angle be minimum, knee flexion angle be maximum, knee abduction loading be minimum, and ankle inversion angle be minimum.

### Claim 18 (depends on 17)

The system as claimed in claim 17, wherein the set of predefined constraints follows an order of priority comprising Hip abduction angle being at highest priority, followed by Knee loading, followed by the knee flexion, followed by ankle inversion.

### Claim 19 (depends on 19)

One or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors causes the one or more hardware processor to perform a method for risk prediction and corrective action for a contact type activity, said method comprising:
generating a personalized full body musculoskeletal model to depict a knee and ankle joint behavior of a subject during the contact type activity, via one or more hardware processors;
simulating one or more contact type activities using the personalized full body musculoskeletal model, via the one or more hardware processors;
identifying a plurality of injury biomarkers based on the one or more contact type activities, via the one or more hardware processors;
analyzing, via the one or more hardware processors, a plurality of parameters indicative of risk of injury to a plurality of participating muscle groups during the one or more contact type activities calculated with respect to the plurality of injury biomarkers to predict said risk of injury; and
generating, based on at least the plurality of injury biomarkers, a plurality of optimal muscle co-activation parameters by a neuro-muscular controller via the one or more hardware processors, to adapt the plurality of participating muscle groups for providing the correct action against the risk of injury being predicted, the plurality of optimal muscle co-activation parameters indicative of muscle synergy during the one or more contact type activities.
The one or more non-transitory machine readable information storage mediums of claim 19, wherein the personalized full body musculoskeletal model comprises a 92 muscle actuators, a 3 degrees of freedom (DoF) knee with ligament connectivity, and 9 ligament bundles designed and placed with respect to anatomical constraints and bounds of the subject.
