SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems

TL;DR

SymptomWise introduces a deterministic reasoning layer for AI symptom analysis, enhancing reliability, interpretability, and safety in diagnostic systems by combining expert knowledge with controlled language model use.

Contribution

It presents a novel architecture that separates language understanding from diagnostic reasoning, improving traceability and reducing unsupported conclusions.

Findings

Achieved 88% top-five diagnosis overlap with clinicians on pediatric neurology cases.

Demonstrated modular evaluation of system components for better interpretability.

Generalizes to other abductive reasoning domains beyond medicine.

Abstract

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.