# Artificial Intelligence and Machine Learning in Pediatric Endocrine Tumors: Opportunities, Pitfalls, and a Roadmap for Trustworthy Clinical Translation

## TL;DR

This paper explores how AI and machine learning can help diagnose and treat rare pediatric endocrine tumors, while addressing challenges in data and translation to clinical practice.

## Contribution

The paper introduces a pediatric-focused framework for AI/ML applications in endocrine tumors, including a checklist for trustworthy clinical translation and a roadmap leveraging existing infrastructures.

## Key findings

- Early signals suggest AI can predict non-remission/recurrence in pediatric DTC and predict survival in ACT.
- Current evidence for PGL and GEP-NEN is mostly adult-led and provides methodological scaffolding for pediatric applications.
- Translation is limited by small datasets, domain shifts, and evolving regulatory standards.

## Abstract

Artificial intelligence (AI) and machine learning (ML) are reshaping cancer research and care. In pediatric oncology, early evidence—most robust in imaging—suggests value for diagnosis, risk stratification, and assessment of treatment response. Pediatric endocrine tumors are rare and heterogeneous, including intra- and extra-adrenal paraganglioma (PGL), adrenocortical tumors (ACT), differentiated and medullary thyroid carcinoma (DTC/MTC), and gastroenteropancreatic neuroendocrine neoplasms (GEP-NEN). Here, we provide a pediatric-first, entity-structured synthesis of AI/ML applications in endocrine tumors, paired with a methods-for-clinicians primer and a pediatric endocrine tumor guardrails checklist mapped to contemporary reporting/evaluation standards. We also outline a realistic EU-anchored roadmap for translation that leverages existing infrastructures (EXPeRT, ERN PaedCan). We find promising—yet preliminary—signals for early non-remission/recurrence modeling in pediatric DTC and interpretable survival prediction in pediatric ACT. For PGL and GEP-NEN, evidence remains adult-led (biochemical ML screening scores; CT/PET radiomics for metastatic risk or peptide receptor radionuclide therapy response) and serves primarily as methodological scaffolding for pediatrics. Cross-cutting insights include the centrality of calibration and validation hierarchy and the current limits of explainability (radiomics texture semantics; saliency ≠ mechanism). Translation is constrained by small datasets, domain shift across age groups and sites, limited external validation, and evolving regulatory expectations. We close with pragmatic, clinically anchored steps—benchmarks, multi-site pediatric validation, genotype-aware evaluation, and equity monitoring—to accelerate safe, equitable adoption in pediatric endocrine oncology.