Helix Insight

Documentation / AI Clinical Assistant

AI Clinical Assistant

Helix AI is a clinical genetics assistant embedded in the Helix Insight platform. It provides conversational access to patient variant data, biomedical literature, and automated clinical interpretation -- all through natural language. The assistant is designed for geneticists and clinical laboratory professionals who need to interrogate genomic analysis results, correlate findings with clinical phenotype, and produce diagnostic reports.

The assistant runs on a large language model hosted entirely on EU-based infrastructure. No patient data is sent to external AI services. All inference happens on-premise through a secure internal connection.

How It Works

1

Context Loading

When a conversation starts, the assistant loads the complete analysis context for the current case: ACMG classifications, pathogenic variants, phenotype matching results, screening tiers, clinical profile, and any previously generated interpretation.

2

Natural Language Interaction

The geneticist asks questions in natural language. The assistant can answer directly from its clinical knowledge, or invoke tools to query the patient database or search the literature database.

3

Tool Execution

When a question requires data, the assistant automatically translates it to SQL, executes it against the appropriate database, and incorporates the results into its response. Up to five sequential tool calls can be chained in a single interaction.

4

Streaming Response

Responses are streamed in real-time via Server-Sent Events. Text appears token by token, with structured events for query results, literature findings, and visualization suggestions.

Key Principles

The assistant only discusses genes and variants that are present in the patient's data. It does not invent findings or add textbook examples that are not in the actual results.

All responses are grounded in the analysis data. When the assistant references a variant, it has either seen it in the loaded context or queried it from the database.

The assistant uses a phenotype-first approach: it considers the patient's clinical presentation to identify candidate genes, then checks whether those genes appear in the variant data.

Clinical interpretation reports clearly separate AI-generated content from template-based sections (patient demographics, legal disclaimer). The AI never fabricates patient information.

Conversation history is maintained for 24 hours in an encrypted cache, enabling multi-turn discussions that build on previous questions and findings.

On-Premise AI

Helix AI runs on a large language model hosted on dedicated GPU infrastructure within the EU. The model is accessed through a secure internal tunnel -- no patient data leaves the server environment. This architecture ensures full GDPR compliance while providing the clinical reasoning capabilities of a large language model.

In This Section