Acute-Stage mTBI Identification Using Bayesian MRI Connectomics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current diagnostic tools for mild traumatic brain injury (mTBI) are limited in their ability to provide accurate and timely identification, especially in cases lacking neuroradiological findings, leading to potential delays in treatment and increased risk of neurocognitive sequelae.

Innovation Solution

A system utilizing a Bayesian machine learning classifier for cortico-cortical connectome mapping from magnetic resonance imaging (MRI) to identify mTBI through analysis of white matter connections, particularly sensitive to mTBI, enabling near-ideal classification accuracy without relying on conventional neuroradiological MRI findings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional diagnostic tools (neurological, neuroradiological, neurocognitive examinations) are used for mTBI diagnosis, then the diagnostic process is simple and readily available, but the measurement precision and reliability are insufficient leading to doubtful diagnoses

Engineering Contradiction:

Improvediagnostic accuracyVSAvoiddiagnostic system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary computational layer (machine learning classifier) that processes MRI data to bridge the gap between conventional imaging and accurate mTBI diagnosis. This intermediary system analyzes connectome features and generates diagnostic probabilities, thereby improving measurement precision without requiring complete redesign of the diagnostic workflow

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces subjective neurological examinations and conventional neuroradiological interpretation with an automated machine learning system that objectively analyzes MRI connectome data. This substitution transforms the diagnostic mechanism from human-dependent assessment to algorithm-driven classification, significantly improving diagnostic accuracy and consistency

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If conventional neuroradiological MRI findings are required for mTBI diagnosis, then the diagnostic criteria are clear and objective, but the productivity and availability are reduced due to limited ability to diagnose cases without visible findings

Engineering Contradiction:

Improvediagnosis availabilityVSAvoiddiagnosis reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent changes the diagnostic parameters from conventional MRI findings (visible structural abnormalities) to connectome-based features (white matter connection patterns). By transforming the data representation and analysis approach, the system can reliably diagnose mTBI cases without traditional neuroradiological findings, thereby improving both productivity and reliability simultaneously

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent transitions from analyzing spatial anatomy in conventional MRI to analyzing functional connectivity in the connectome domain. This dimensionality change allows detection of mTBI through network-level disruptions rather than focal structural abnormalities, expanding diagnostic capability to cases previously considered undiagnosable

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Loss of time

If early diagnosis of mTBI is pursued to prevent sequelae, then the time for intervention is reduced, but the measurement precision requirement increases due to equivocal examinations in early stages

Engineering Contradiction:

Improvetime to diagnosisVSAvoiddiagnostic confidence

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The patent performs preliminary analysis of connectome features that are sensitive to early mTBI changes before conventional symptoms become evident. By establishing baseline connectivity patterns and identifying early deviations, the system enables timely diagnosis while maintaining high measurement precision through robust machine learning classification

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250217977A1Reproducible identification of acute-stage mild traumatic brain injury using machine learning and connectomics

Publication Date: 2025.07.03 UNIV OF SOUTHERN CALIFORNIA

AI summary

A system and method operates for diagnosis of mild traumatic brain injury (mTBI) to prevent sequelae and improve neurocognitive outcomes. The system may have a processor that receives, from a magnetic resonance imaging machine, data corresponding to magnetic resonance imaging images. By using a machine learning classifier of the processor, such as a Bayesian machine learning classifier, the processor identifies mild traumatic brain injury in a person through cortico-cortical connectome mapping from magnetic resonance imaging. The processor can also generate a human readable screen display indicative of the identified mild traumatic brain injury.