Evidex
AI Clinical Search (RAG over PubMed/OpenAlex and SOAP Notes)
Details
- External ID
- 46422812
- Source
- HN
- Company
- —
- Product
- Evidex
- Website domain
- getevidex.com
- Launched
- Dec. 29, 2025
- Cohort
- —
- Upvotes
- 36
- Upvotes percentile
- 0.7585877862595419
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Hi HN,I’m a solo dev building a clinical search engine to help my wife (a resident physician) and her colleagues.The Problem: Current tools (UpToDate/OpenEvidence) are expensive, slow, or increasingly heavy with pharma ads.The Solution: I built Evidex to be a clean, privacy-first alternative. Search Demo (GIF): https://imgur.com/a/zoUvINtTechnical Architecture (Search-Based RAG): Instead of using a traditional pre-indexed vector database (like Pinecone) which can serve stale data, I implemented a Real-time RAG pattern:Orchestrator: A Node.js backend performs "Smart Routing" (regex/keyword analysis) on the query to decide which external APIs to hit (PubMed, Europe PMC, OpenAlex, or ClinicalTrials.gov).Retrieval: It executes parallel fetches to these APIs at runtime to grab the top ~15 abstracts.Local Data: Clinical guidelines are stored locally in SQLite and retrieved via full-text search (FTS) ensuring exact matches on medical terminology.Inference: I’m using Gemini 2.5 Flash to process the concatenated abstracts. The massive context window allows me to feed it distinct search results and force strict citation mapping without latency bottlenecks.Workflow Tools (The "Integration"): I also built a "reasoning layer" to handle complex patient histories (Case Mode) and draft documentation (SOAP Notes). Case Mode Demo (GIF): https://imgur.com/a/h01Zgkx Note Gen Demo (GIF): https://imgur.com/a/DI1S2Y0Why no Vector DB? In medicine, "freshness" is critical. If a new trial drops today, a pre-indexed vector store might miss it. My real-time approach ensures the answer includes papers published today.Business Model: The clinical search is free. I plan to monetize by selling billing automation tools to hospital admins later.Feedback Request: I’d love feedback on the retrieval latency (fetching live APIs is slower than vector lookups) and the accuracy of the synthesized answers.
Enrichment
- Theme
- healthcare operations and clinical workflows
- Vertical
- Healthcare
- Function
- Search & retrieval
- Audience
- B2B
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- clinical research search with rag
- Manually corrected
- False
Could you build this?
Partial Building the RAG UI and basic API wrapper is straightforward, but building a production clinical search engine requires indexing millions of PubMed/OpenAlex papers, clinical knowledge validation, and strict hallucination safeguards.
What it would actually take: A real implementation needs a high-scale ingestion pipeline indexing tens of millions of biomedical papers via OpenAlex/PubMed into a hybrid search engine (e.g., Elasticsearch with dense biomedical embeddings like BioBERT). The RAG pipeline requires specialized biomedical entity extraction, clinical prompt chains, citation-grounding verification, and compliance with medical accuracy standards. Expertise in medical informatics and large-scale data retrieval is required.
Discussion
20 comments analyzed.
Competitors mentioned: MediSearch, ChatGPT 5.2 Extended, Gemini 3 Pro, Cochrane reviews
Concerns raised: LLMs miss fatal methodological flaws and subtleties in medical papers, Author/institutional bias and reputation masking not detectable by algorithms, Freshness without appraisal creates accelerated firehose of noise, Live APIs introduce latency and rate limit headaches, Keyword-based routing misses semantic similarity of search intents
Feature requests: Author reputation and career-wide bias analysis across bibliography, Filter dial to toggle between tight constraints (clinical safety) and loose constraints (research discovery), Deep workflow integration into clinician's existing systems, not separate tool, Multi-discipline expert prompting for paper-specific methodological review, Semantic search beyond regex/keyword matching for domain experts
Competitors
Other products that read as similar to this one — 21 launches clear the similarity bar, closest 8 shown.
Attention rank: #10 of 22 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 52 days after the earliest competitor.
- PaxMed · ph · 2026-09-30 · 1 upvotes · similarity 0.42
- real-time-retrieval · github · 2026-09-12 · 8 upvotes · similarity 0.39
- Spent 2.5 years building better job search (now using it to find a job) · hn · 2026-01-16 · 8 upvotes · similarity 0.37
- AIhaoyisheng · ph · 2026-09-06 · 1 upvotes · similarity 0.35
- I've been using AI to analyze every supplement on the market · hn · 2026-01-22 · 94 upvotes · similarity 0.35
- Better Search Lab · ph · 2026-09-17 · 4 upvotes · similarity 0.35
- Context Link RAG API · ph · 2026-09-08 · 3 upvotes · similarity 0.34
- OSS AI agent that indexes and searches the Epstein files · hn · 2026-01-14 · 211 upvotes · similarity 0.34
Other launches for this product
- No other launches for this product.