LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis
2026-06-15 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed LiteOdyssey, a medical AI system for diagnosing rare diseases that works by carefully guiding one AI model through a step-by-step clinical reasoning process rather than relying on lots of extra data or multiple AI systems. They created this approach using a mix of human input and public biomedical tools, which helped the AI improve without retraining. LiteOdyssey performed very well on tough tests with many ultra-rare diseases, beating baseline models by a large margin. Their method shows that it is possible to build accurate and simpler AI tools for rare disease diagnosis that are easier for doctors to use and check.
rare disease diagnosisdiagnostic policyhuman-AI collaborationlanguage modelPolicy Iteration with Human Feedbackbiomedical toolsRecall@1ultra-rare diseasesclinical genetics workflowfine-tuning
Authors
Minh-Ha Nguyen, Erica Gray, Chih-Ting Yang, Rizwan Hamid, Lingyao Li, Siyuan Ma, Thomas A. Cassini, Cathy Shyr
Abstract
Most medical AI systems improve by scaling additional machinery: more fine-tuning data, more agents, and/or larger retrieval databases. In rare-disease diagnosis, however, such scaling can produce systems that are difficult to deploy, audit, and maintain. We asked whether state-of-the-art diagnostic performance could instead be achieved by extending the reasoning chain of a single AI agent: guiding it with a diagnostic policy, developed through human-AI collaboration and augmenting with freely available biomedical tools. We introduce LiteOdyssey, a lightweight rare-disease diagnostic framework that guides reasoning language model through a clinical genetics workflow. This framework was developed through Policy Iteration with Human Feedback (PIHF) and uses dynamic access to public biomedical tools. On two challenging benchmarks that provide only patient clinical features, LiteOdyssey achieved state-of-the-art performance, with an overall disease Recall@1 of 59.3% over the combined 1,243 cases of LIRICAL (n = 370) and the PhenoPacket Store (n = 873). Both benchmarks have a high proportion of ultra-rare disease (a prevalence below 1 in 1,000,000, with ultra-rare shares of approximately 45% and 52.8%, respectively). On the more difficult PhenoPacket subset, where causal diseases were not mapped to Orphanet in our rarity-mapping pipeline, LiteOdyssey achieved 60.7% Recall@1, compared with 10.7% for the same baseline model (GPT-5.4) without tools. This performance was achieved without fine-tuning, multi-agent ensembles, or a large case-retrieval database. Gains were also observed in the following: on cases never seen during development, on a private cohort of real-world rare disease patients, and on a smaller open-weights model. LiteOdyssey suggests a path toward rare-disease AI systems that are accurate, easier to deploy, and more transparent for physician review.