Longitudinal treatment selection under irreversible discontinuation: History-aware prediction and trajectory-aware learning in peanut-allergy prevention
Year: 2026
Type: preprint
Abstract: Clinical decision-support systems that guide longitudinal treatment must determine not only which treatment is preferred, but also when the available evidence is sufficient to change course. This challenge is especially important when discontinuation is irreversible, because stopping too early prevents later information from informing care. Food allergy is a growing public-health concern that can cause severe reactions and imposes substantial medical, dietary, and psychosocial burdens. Prevention is therefore a major clinical priority. In peanut-allergy prevention, this longitudinal decision is particularly consequential because resuming peanut consumption after discontinuation may be unsafe without renewed clinical assessment. In this work, we introduce a framework for preferred-treatment prediction and evaluate it using data from 628 children assigned to early peanut consumption or avoidance in the Learning Early About Peanut Allergy trial. We first introduced visit-wise and history-aware models that update recommendations as clinical and immunological measurements accumulate. Preferred treatment was poorly discriminated at baseline but became substantially more predictable during follow-up, with history-aware models achieving area-under-the-curve values of about 0.9 at later visits. However, imposing irreversible discontinuation after training significantly reduce the performance of these models. We therefore developed TreatNet, which jointly optimizes visit-specific predictors through a trajectory-level objective representing the downstream consequences of early discontinuation. Under the same irreversible constraint, TreatNet achieved accuracies of 0.805–0.839 and area-under-the-curve values of 0.819–0.869 across follow-up visits and two alternative preferred-treatment definitions. TreatNet generally preserved consumption while baseline evidence was limited and selectively recommended discontinuation after more informative measurements became available. These findings show that longitudinal information is most useful when model training reflects how current actions restrict future options. Although evaluated in peanut-allergy prevention, TreatNet provides a general framework for decision-support problems involving irreversible or difficult-to-reverse treatment changes. Author summary Food allergy can cause severe reactions and places substantial medical, dietary, and emotional burdens on children and their families. Early peanut consumption can prevent peanut allergy, but whether an individual child should continue or stop consumption may become clearer only as new clinical information is collected. This creates an important challenge: stopping too early may be difficult to reverse and can prevent later information from guiding care. We used data from 628 children in a major peanut-allergy prevention trial to study how recommendations can be updated over time. We first developed models that reconsider the preferred treatment at each visit, including models that use the child’s complete measurement history. We found that the preferred treatment was difficult to identify at baseline but became substantially more predictable during follow-up. However, models trained to make each decision separately lost much of this benefit when stopping was treated as irreversible. We therefore developed TreatNet, which learns how an early decision affects the choices available later. TreatNet generally continued consumption while evidence was limited and recommended stopping selectively after more informative measurements became available. Although tested in peanut-allergy prevention, this approach could support many healthcare decisions in which stopping or changing treatment restricts future options.
Authors: Ronen Taub, Tanya Wasserman, Yonatan Savir
Institution: Technion – Israel Institute of Technology
Language: English
Subfield: Immunology and Allergy
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7222477438