SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems
This addresses reliability and interpretability issues in AI-driven medical diagnosis, with potential broader applications in abductive reasoning domains, though it appears incremental as it builds on existing methods like expert knowledge and constrained language model use.
The paper tackled the problem of unreliable and uninterpretable AI symptom analysis by introducing SymptomWise, a framework that separates language understanding from deterministic diagnostic reasoning, resulting in the correct diagnosis appearing in the top five differentials in 88% of cases in a preliminary evaluation on pediatric neurology cases.
AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches often lack traceability and may produce unsupported or inconsistent diagnostic outputs in safety-critical settings. We present SymptomWise, a framework that separates language understanding from diagnostic reasoning. The system combines expert-curated medical knowledge, deterministic codex-driven inference, and constrained use of large language models. Free-text input is mapped to validated symptom representations, then evaluated by a deterministic reasoning module operating over a finite hypothesis space to produce a ranked differential diagnosis. Language models are used only for symptom extraction and optional explanation, not for diagnostic inference. This architecture improves traceability, reduces unsupported conclusions, and enables modular evaluation of system components. Preliminary evaluation on 42 expert-authored challenging pediatric neurology cases shows meaningful overlap with clinician consensus, with the correct diagnosis appearing in the top five differentials in 88% of cases. Beyond medicine, the framework generalizes to other abductive reasoning domains and may serve as a deterministic structuring and routing layer for foundation models, improving precision and potentially reducing unnecessary computational overhead in bounded tasks.