Skip to main content
LIF-02 · Life Sciences & Pharmaceuticals

Clinical Trial Protocol Copilot

Outcome​

Accelerate clinical trial protocol authoring by drafting sections from prior protocols, regulatory standards, and study assumptions while surfacing feasibility and patient-burden risks for the study team to resolve.

Portfolio attributeValue
Primary personaClinical operations lead
Primary aggregateProtocolDocument
Cosmos DB containers2
Grounding dataprotocols, standards, study assumptions
Development estimateUSD 60-220 monthly dev estimate
Runtime optionsPython FastAPI and C# ASP.NET Core

Productivity hypothesis​

These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.

Impact typeMeasureConservative internal assumptionCustomer measurement
ProductivityProtocol task cycle time10-18% reduction(baseline median protocol-task minutes - assisted median minutes) / baseline median minutes * 100
Quality or riskRework rate5-12% reduction(baseline corrected or repeated protocol-task rate - assisted rate) / baseline rate * 100

Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.

Rationale: Standards and study assumptions support faster protocol drafting and review preparation in an approval-gated workflow.

Pilot guardrail: Clinical, statistical, regulatory, ethical, and operational approvals remain mandatory.

Customer validation plan​

  1. Baseline the current workflow with representative users and tasks.
  2. Run the accelerator on the same task mix with human review retained.
  3. Measure protocol task cycle time and rework rate with the documented formulas.
  4. Replace internal assumptions with customer-observed results before a business case.

Why Azure Cosmos DB​

This AI solution needs an operational data plane, not only a vector index:

  • Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
  • Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
  • Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
  • Change feed reacts to source and operational updates without polling.
  • Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.

Domain workflow​

Domain workflow

StageActorInput → outputApproval
1. Define study assumptions and comparatorsClinical operations leadIndication, phase, endpoints, and prior study references → ProtocolDocument shell with assumption setPolicy controlled
2. Retrieve precedent protocols and standardsRetrieval agentIndication and phase filters → Precedent sections and applicable guidance clausesPolicy controlled
3. Draft protocol sections with lineageAuthoring agentPrecedents, standards, and assumptions → ProtocolSectionDraft set with source lineagePolicy controlled
4. Model feasibility and patient burdenFeasibility analytics serviceEligibility criteria and visit schedule → FeasibilityAssessment with recruitment estimatesPolicy controlled
5. Study team review and version releaseMedical monitor and study teamDrafted protocol with feasibility findings → Released protocol version for review board submissionHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
protocolDocuments/tenantId, /studyIdProtocolDocument, ProtocolSectionDraft, EligibilityCriterion, FeasibilityAssessment/sectionVectorEmbedding, /criterionVectorEmbedding, /sectionVector, /criterionVector
regulatoryStandardsLibrary/tenantId, /standardIdRegulatoryStandardClause/clauseVectorEmbedding, /clauseVector

Query contract​

QueryContainerScopePurpose
Protocol assembly by sectionprotocolDocumentssingle-partitionRead the current draft of every section for the study in one partition query.
Restrictive criteria reviewprotocolDocumentssingle-partitionFind eligibility criteria whose modelled screening impact is severe.
Applicable guidance lookupregulatoryStandardsLibrarycross-partition-boundedKnowledge-container query against regulatoryStandardsLibrary (bounded fan-out across the /tenantId + /standardId partitions named by the shortlist): retrieve the clauses in force for the standards that govern this study, fanned out across the small fixed set of applicable standard ids.
Open protocol issuesprotocolDocumentssingle-partitionList sections carrying unresolved authoring issues before version release.

Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.

Azure deployment​

Azure deployment

Clone the source repository, authenticate with Azure, and run:

Set-Location accelerators/life-sciences-pharmaceuticals/clinical-trial-protocol-copilot
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators