RAG Without Persona Modeling Fails Patient Clinical Relevance

All health platforms ship a RAG pipeline that answers medical questions. None of them know who is asking. A system that cannot match the answer to the patient has not solved relevance. It has automated a liability. At a Global AI Hackathon, HPPIE (Hyper-Personalized Patient Insights Engine) was built to test whether integrating persona modeling at the retrieval stage closes the clinical relevance gap. HPPIE placed 2nd of 300+. Patients receive results without the system knowing their medical history. If two users produce the same cosine similarity, they are the same patient to the pipeline. This was described as "fragmented awareness," where a lack of persistent profiles capturing medications, allergies, or conditions across sessions creates friction. Each interaction starts cold. The patient filters the results themselves, using the clinical judgment they came to the platform to get help with. A three-stage pipeline of Context Aware Clinical RAG architecture on FastAPI, Qdrant, and Ollama, each targeting a specific failure mode. Above: Context Aware Clinical RAG Architecture Before retrieval, HPPIE models a patient persona from structured clinical attributes: age, sex, active medications, diagnosed conditions, allergies, and health goals. This persona reshapes the embedding space before the query hits the vector store. Most RAG systems treat personalization as post-retrieval reranking: retrieve top-k, then filter. The architecture rejected that because post-retrieval filtering from a 20-document pool will never surface a document ranked 47th in a generic query. HPPIE injects the persona into the query embedding. The vector space processes a distinct query for each persona. Embedding similarity misses hard keyword dependencies in the medical domain. HPPIE integrates three components: embedding cosine similarity from Qdrant (w: 0.5), BM25 keyword matching weighted toward clinical terms (0.3), and a behavioral relevance score from the persona model (0.2). Embeddings capture semantics. Keywords prevent clinical misses. Behavioral scoring is where the persona earns its value. A compliance decision, not a performance one. Dockerized Ollama models run on-prem. The moment a persona-modified query containing a medication list leaves the local network, a BAA with the inference provider is required. The tradeoff: a 7B model will not match GPT-4 on clinical summarization. This was accepted because sending enriched patient data to third-party APIs renders the system undeployable in regulated healthcare. HPPIE pre-seeded Qdrant with curated medical data, then created summaries linked to specific personas. A 35-year-old runner querying "chest pain" received musculoskeletal content. A 65-year-old with hypertension received cardiac risk assessment. Different retrieval sets because the query was different, not because a filter was applied after. 2nd of 300+, evaluated on AI innovation, technical architecture, clinical applicability, and production readiness. Clinical relevance is an identity problem. The patient is a clinical context that should reshape retrieval before it begins. Pipelines that treat the patient as a downstream filter are solving the wrong problem at the wrong stage. The persona model depends on structured clinical input. Incomplete data produces a distorted persona, and the system returns confidently wrong results. That failure mode is worse than generic RAG because the patient trusts personalized output. This remains an open challenge. A production deployment needs a persona validation layer and systematic evaluation across comorbidity complexity tiers. Can persona-modified retrieval outperform post-retrieval reranking at scale? In the prototype, yes. At production scale with millions of documents and thousands of concurrent personas, the computational cost has not been benchmarked. Does local inference constrain clinical utility? 7B models produce shorter summaries than 70B+ cloud models. For patient education, acceptable. For clinical decision support requiring exhaustive differential analysis, insufficient. How does this connect to identity infrastructure? HPPIE treats a patient persona as an identity primitive that governs what the system does. Citation format: Sharma, Riddhi Mohan. "HPPIE: RAG Without Persona Modeling Fails Patient Clinical Relevance." Riddhimohan.com, March 2026. https://riddhimohan.com/blog/hppie-rag-without-persona-modeling-fails-patient-clinical-relevance Version history: March 29, 2026: Initial case study published. Expanded from a Global AI Hackathon entry (2025). 0009-0000-3757-5818DOI:[Pending Registration]This research is open for academic citation and peer-review. Established to support the advancement of AI Governance and Industrial Ethics. Identity integration starts post-close. That is not the problem. The problem is whether the platform was built for serial acquisition before the first deal closed.

RAG Without Persona Modeling Fails Patient Clinical Relevance

Key takeaways

Also covered by

RAG Without Persona Modeling Fails Patient Clinical Relevance

Key takeaways

Also covered by

More in computer-science