Patient Response Classifier for Anti-TNF Treatment Stratification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current anti-TNF therapies for autoimmune diseases like rheumatoid arthritis exhibit inconsistent response rates, leading to delayed treatment, increased disease progression, and significant side effects, with existing predictive tools failing to accurately identify responder versus non-responder patients.

Innovation Solution

A classifier is developed using gene expression analysis and single nucleotide polymorphism (SNP) data to predict responsiveness to anti-TNF therapies, allowing for personalized treatment decisions by distinguishing between responsive and non-responsive patients.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If anti-TNF therapies are administered to all rheumatoid arthritis patients, then some patients achieve clinical response and remission, but response rates remain low (34%) and inconsistent across patient populations

Engineering Contradiction:
Improvetreatment response consistencyVSAvoidpredictive accuracy of responder status
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by developing and validating predictive classifiers (such as the 38-gene signature and machine learning models) that can identify responder versus non-responder status before anti-TNF therapy is administered. This allows clinicians to pre-stratify patients into likely responder and non-responder groups, enabling informed treatment decisions prior to therapy initiation, thereby improving treatment response consistency while reducing unnecessary exposure to ineffective therapies

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If patients are switched to alternative therapies after failing anti-TNF treatment, then treatment options are available, but disease progression continues during the switching period causing delayed treatment and increased difficulty in reaching treatment targets

Engineering Contradiction:
Improvetreatment option availabilityVSAvoidtreatment delay
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements preliminary action by establishing predictive classifiers that identify non-responder status before anti-TNF therapy is initiated or early in the treatment course. This enables clinicians to avoid switching therapies after treatment failure has already occurred, instead making proactive decisions to select alternative treatments upfront, thereby eliminating the time loss associated with disease progression during therapy switching

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies feedback by using validated predictive models (such as the 38-gene signature with machine learning algorithms) that provide real-time or near-real-time prediction of treatment response. This feedback mechanism allows clinicians to adjust treatment plans based on predicted responder status, enabling dynamic treatment selection that prevents the time loss associated with trial-and-error therapy switching

Inventive Principle:
Principle #23Feedback

3Ease of operation

If anti-TNF therapy is administered to non-responder patients, then treatment is provided, but patients experience significant side effects including serious infection and malignancy risks requiring black box warnings

Engineering Contradiction:
Improvetreatment accessibilityVSAvoidside effect severity
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by developing and validating predictive classifiers (including the 38-gene signature and machine learning models) that can accurately identify non-responder patients before they receive anti-TNF therapy. This enables clinicians to prevent non-responders from receiving ineffective treatment, thereby avoiding the significant side effects including serious infections and malignancies that would occur with unnecessary therapy exposure, while still maintaining treatment accessibility for true responders

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism - the predictive classifier system comprising gene expression analysis and machine learning algorithms - that acts as a mediator between the patient and anti-TNF therapy decision. This intermediary provides objective, data-driven prediction of treatment response, enabling clinicians to filter out non-responders before therapy administration, thereby reducing harmful side effects while preserving treatment accessibility for those who will benefit

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3990656B1Developing classifiers for stratifying patients
Publication Date: 2026.04.22 SCIPHER MEDICINE CORP
  • EP3990656B1 patent drawingFigure 1
  • EP3990656B1 patent drawingFigure 2
  • EP3990656B1 patent drawingFigure 3

AI summary

Presented herein are systems and methods for developing classifiers useful for predicting response to particular treatments. For example, in some embodiments, the present disclosure provides a method of treating subjects suffering from an autoimmune disorder, the method comprising a step of: administering an anti-TNF therapy to subjects who have been determined to be responsive via a classifier established to distinguish between responsive and non-responsive prior subjects in a cohort who have received the anti-TNF therapy.