Computational Model Predicts Injection Frequency for Macular Edema

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current treatments for macular edema due to retinal vein occlusion require frequent and variable injections, leading to burdensome clinical outcomes and resource inefficiencies, as clinicians struggle to accurately determine individual patient needs for long-term management.

Innovation Solution

A computational model using best corrected visual acuity (BCVA) data, along with demographic and image-derived data, is employed to predict injection frequency, enabling personalized treatment schedules and reducing unnecessary evaluations and resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If frequent and variable injections are administered to treat macular edema, then treatment effectiveness is improved, but patient burden and resource consumption increase

Engineering Contradiction:

Improvetreatment effectivenessVSAvoidpatient burden

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent implements dynamic treatment scheduling where injection frequency is adjusted based on individual patient response patterns. The system transitions from static fixed schedules to dynamic adaptive schedules that modify injection intervals according to measured visual acuity changes and treatment response, thereby maintaining effectiveness while reducing unnecessary injections and patient burden

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of injection frequency from a fixed value to a variable parameter determined by patient-specific factors including baseline visual acuity, disease severity, and treatment response rate. This parameter optimization allows customization of treatment protocols to achieve minimum effective dosing while avoiding overtreatment

Inventive Principle:

Principle #35Parameter changes

2Reliability

If continuous monthly injections are administered, then visual outcomes are maintained, but treatment complexity and monitoring requirements increase

Engineering Contradiction:

Improvevisual outcomesVSAvoidtreatment complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies partial action by administering injections only when clinically necessary rather than on a fixed continuous schedule. The system determines minimum effective treatment frequency based on individual patient needs, allowing extension intervals between injections while maintaining visual outcomes, thereby reducing overall treatment complexity

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent uses preliminary action by establishing predictive models and baseline assessments before treatment initiation. These pre-established parameters allow for predetermined treatment protocols that reduce the need for complex real-time decision-making and frequent monitoring adjustments

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If treat and extend dosing is used, then treatment flexibility is improved, but prediction accuracy of injection needs deteriorates

Engineering Contradiction:

Improvetreatment flexibilityVSAvoidprediction accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent implements feedback mechanisms where treatment response is continuously measured through visual acuity assessments and other clinical parameters. This feedback information is fed back into the prediction model to refine and update injection frequency predictions, thereby maintaining both treatment flexibility and improved prediction accuracy over time

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces the manual clinical judgment and experience-based treatment extension decisions with computational prediction models. These models use patient data to objectively predict injection needs, substituting subjective mechanical decision-making with data-driven algorithms that improve prediction accuracy while preserving treatment flexibility

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Manufacturing precision

If frequent subject monitoring and evaluations are conducted, then treatment precision is improved, but time consumption and resource allocation increase

Engineering Contradiction:

Improvetreatment precisionVSAvoidtime consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent implements dynamic monitoring schedules that adjust evaluation frequency based on patient stability and treatment response. Patients with stable responses undergo less frequent monitoring, while those with variable responses receive more intensive monitoring, thereby optimizing treatment precision while minimizing time consumption and resource allocation

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20230317288A1Machine learning prediction of injection frequency in patients with macular edema

Publication Date: 2023.10.05 GENENTECH INC

AI summary

A method and system for managing a treatment of a subject diagnosed with a macular edema condition. Subject data for a subject is received. The subject data comprises best corrected visual acuity (BCVA) data for the subject. An input for a computational model is generated using the subject data. An injection frequency for the treatment of the subject diagnosed with the macular edema condition is predicted, via the computational model, based on the input.