PPGL-Swarm: Integrated Multimodal Risk Stratification and Hereditary Syndrome Detection in Pheochromocytoma and Paraganglioma

2026-03-23

AI Summary

This work addresses the limitations of current pheochromocytoma and paraganglioma (PPGL) diagnosis, where the GAPP scoring system suffers from subjectivity, high workload, and an inability to effectively integrate critical metastatic risk factors such as SDHB mutations and hereditary syndrome information, often leading to missed identification of high-risk patients. To overcome these challenges, we propose PPGL-Swarm, a novel multi-agent diagnostic system that, for the first time, incorporates knowledge-augmented agents and traceable reasoning chains into PPGL assessment. By decomposing diagnostic tasks and coordinating specialized agents, the system fuses multimodal data—including genotypic, pathological, and clinical information—to automatically generate auditable reports featuring quantified GAPP scores, genetic risk alerts, and evidence provenance. Integrated modules for automated Ki-67 and cell density analysis, combined with reinforcement learning–optimized tool invocation and task allocation, significantly enhance the objectivity and comprehensiveness of risk stratification and hereditary syndrome recognition, thereby supporting precise clinical decision-making.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Multiagent Systems: Adversarial Agents
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Pheochromocytomas and paragangliomas (PPGLs) are rare neuroendocrine tumors, of which 15-25% develop metastatic disease with 5-year survival rates reported as low as 34%. PPGL may indicate hereditary syndromes requiring stricter, syndrome-specific treatment and surveillance, but clinicians often fail to recognize these associations in routine care. Clinical practice uses GAPP score for PPGL grading, but several limitations remain for PPGL diagnosis: (1) GAPP scoring demands a high workload for clinician because it requires the manual evaluation of six independent components; (2) key components such as cellularity and Ki-67 are often evaluated with subjective criteria; (3) several clinically relevant metastatic risk factors are not captured by GAPP, such as SDHB mutations, which have been associated with reported metastatic rates of 35-75%. Agent-driven diagnostic systems appear promising, but most lack traceable reasoning for decision-making and do not incorporate domain-specific knowledge such as PPGL genotype information. To address these limitations, we present PPGL-Swarm, an agentic PPGL diagnostic system that generates a comprehensive report, including automated GAPP scoring (with quantified cellularity and Ki-67), genotype risk alerts, and multimodal report with integrated evidence. The system provides an auditable reasoning trail by decomposing diagnosis into micro-tasks, each assigned to a specialized agent. The gene and table agents use knowledge enhancement to better interpret genotype and laboratory findings, and during training we use reinforcement learning to refine tool selection and task assignment.

Problem

• PPGL
• risk stratification
• hereditary syndrome
• GAPP score
• metastatic risk

Innovation

• PPGL-Swarm
• multimodal risk stratification
• hereditary syndrome detection
• agentic diagnostic system
• reinforcement learning