Post

New research · AI in Medicine
The Journal of allergy and clinical immunology · 1w
Randomized trialThe Journal of allergy and clinical immunology · 2026

Epitope-Specific IgE Profiles are Predictive of Desensitization and Remission in the IMPACT Trial.

Julie Wang, Samane Khoshbakht, Kyung Won Lee … Hugh A Sampson
Read paper
AI in MedicineRandomized trial

A 9-antibody epitope IgE model predicted peanut immunotherapy remission with 88.2% accuracy

Epitope-Specific IgE Profiles are Predictive of Desensitization and Remission in the IMPACT Trial.

Julie Wang … Hugh A Sampson
The Journal of allergy and clinical immunology · 2026
Background

From the IMPACT trial suggest that initiation of peanut oral immunotherapy (pnOIT) before age 4 years can increase chances of achieving desensitization and remission.

Purpose

We sought to assess sequential (linear) epitope-specific (es-)IgE and es-IgG4 profiles over the course of pnOIT and determine whether they can predict desensitization and remission outcomes.

Methods

In the IMPACT trial (NCT03345160) were randomized to pnOIT or placebo for 134 weeks.

Results

Model correctly classified 88.2% of children as achieving remission or not

83.3%
Sensitivity
90%
Specificity
More results

PnOIT was associated with an overall decrease in es-IgE and increase in es-IgG4 levels.

Younger subjects (<2.3 years of age) had lower baseline es-IgE binding and lower fold-change in es-IgE and es-IgG4 binding during pnOIT.

“
Conclusion · 1 of 3

Baseline epitope IgE profiles can predict remission outcome for children undergoing pnOIT. Age and baseline peanut IgE remain important factors across models.

Conclusion · 2 of 3

Notably, pnOIT prevented the epitope spreading of es-IgE observed in placebo-treated children, suggesting a treatment effect on the breadth of the allergic response that may be especially relevant in young children.

Conclusion · 3 of 3

These profiles may help identify patients who are more likely to benefit from pnOIT.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
r = .70-.81
GPT-4's depression ratings closely matched standard questionnaires and expert clinicians' judgments
Cohort Study
AUC = 0.856
how well the model separated infants whose own liver survived 2 years from those who needed a transplant; higher means b
Guideline
“This approach enables improved data consistency, facilitates national health information exchange, and lays a foundation for advanced applications, such as clinical decision support and artificial intelligence-driven analytics.”
AI / Informatics
0.80
the AI's calls on who was at high psychosis risk were mostly correct
Cohort Study
0.80
Model's accuracy score (AUROC) for spotting long COVID; 1.0 is perfect, 0.80 is good
AI / Informatics
88.5%
Top-5 genetic diagnoses were more accurate with Retina4IRD-assisted specialists.
AI / Informatics
27,624 words
total Simplified Chinese words with new AI familiarity estimates now available
AI / Informatics
89%
Artificial intelligence/machine learning models correctly identified 89% of high-grade glioma recurrences and non-recurrences.