name: healthsim-trialsim description: "Generate realistic clinical trial synthetic data including study definitions, sites, subjects, visits, adverse events, efficacy assessments, and disposition. Use when user requests: clinical trial data, CDISC/SDTM/ADaM datasets, trial cohorts (Phase I/II/III/IV), FDA submission test data, or specific therapeutic areas like oncology or biologics/CGT."

TrialSim

Status: Active Development

TrialSim generates realistic synthetic clinical trial data for testing, training, and development purposes.

For Claude

Use this skill when the user requests clinical trial data, CDISC-compliant datasets, or regulatory submission test data. This is the primary skill for generating realistic synthetic clinical trial data.

When to apply this skill:

User mentions clinical trials, studies, or protocols
User requests CDISC, SDTM, or ADaM datasets
User specifies trial phases (Phase I, II, III, IV)
User mentions FDA/EMA submission data or regulatory requirements
User asks for adverse events, safety data, or efficacy endpoints
User mentions specific therapeutic areas (oncology, cardiovascular, CNS)
User requests SDTM domains (DM, AE, VS, LB, CM, EX, DS, MH)

Key capabilities:

Generate complete study definitions with protocol parameters
Create multi-site, multi-country trial configurations
Produce subject-level longitudinal data with realistic patterns
Generate safety data (adverse events, labs, vitals) with MedDRA/LOINC coding
Create efficacy endpoints for various therapeutic areas
Output CDISC-compliant formats (SDTM, ADaM)

For specific trial phases, therapeutic areas, or SDTM domains, load the appropriate skill from the tables below.

Overview

TrialSim provides:

Complete study lifecycle data (protocol to closeout)
Multi-site, multi-country trial configurations
Subject-level longitudinal data with realistic patterns
Safety data (adverse events, labs, vitals)
Efficacy endpoints (primary, secondary, exploratory)
CDISC-compliant output (SDTM, ADaM)

Trigger Phrases

Activate TrialSim when user mentions:

"clinical trial" or "clinical study"
"Phase I/II/III/IV" or "pivotal trial"
"CDISC", "SDTM", "ADaM"
"FDA submission data" or "regulatory data"
"adverse events" or "safety data"
"efficacy endpoints"
Trial therapeutic areas (oncology, cardiology, etc.)
SDTM domains (DM, AE, VS, LB, CM, EX, DS)

Quick Links

Core Skills

Topic	Skill	Description
Domain Knowledge	clinical-trials-domain.md	Core trial concepts, phases, regulatory
Recruitment	recruitment-enrollment.md	Screening funnel, enrollment patterns

Trial Phase Skills

Phase	Skill	Description
Phase 1	phase1-dose-escalation.md	FIH, dose escalation, MTD (3+3, BOIN, CRM)
Phase 2	phase2-proof-of-concept.md	POC, dose-ranging, futility (Simon's, MCP-Mod)
Phase 3	phase3-pivotal.md	Pivotal registration trials, NDA/BLA

SDTM Domain Skills

Domain	Skill	Description
DM	domains/demographics-dm.md	Subject demographics, treatment arms
AE	domains/adverse-events-ae.md	Adverse events with MedDRA coding
VS	domains/vital-signs-vs.md	Vital sign measurements
LB	domains/laboratory-lb.md	Laboratory results with LOINC
CM	domains/concomitant-meds-cm.md	Concomitant medications with ATC
EX	domains/exposure-ex.md	Study drug exposure, dose modifications
DS	domains/disposition-ds.md	Subject disposition, discontinuation
MH	domains/medical-history-mh.md	Medical history, comorbidities
Domain Index	domains/README.md	All SDTM domains overview

Therapeutic Areas

Area	Skill	Key Endpoints
Oncology	therapeutic-areas/oncology.md	RECIST, ORR, PFS, OS
Cardiovascular	therapeutic-areas/cardiovascular.md	MACE, CV outcomes
CNS	therapeutic-areas/cns.md	Cognitive scales, imaging
CGT	therapeutic-areas/cgt.md	CAR-T, gene therapy

Real World Evidence

Topic	Skill	Description
RWE Overview	rwe/overview.md	RWE concepts, data sources
Synthetic Controls	rwe/synthetic-control.md	External control arm generation

Output Formats

Format	Skill	Use Case
SDTM	../../formats/cdisc-sdtm.md	Regulatory submission
ADaM	../../formats/cdisc-adam.md	Statistical analysis
Dimensional	../../formats/dimensional-analytics.md	BI dashboards, analytics
JSON	Default	API integration
CSV	../../formats/csv.md	Spreadsheet analysis

Data Models & References

Resource	Location	Description
Canonical Models	../../references/data-models.md#trialsim-models	15 entity schemas (Subject, Study, Site, AE, etc.)
Dimensional Schema	../../formats/dimensional-analytics.md#trialsim-clinical-trial-analytics	Star schema for BI (7 dims, 6 facts)
Code Systems	../../references/code-systems.md	MedDRA, LOINC, ATC

Core Entities

TrialSim uses 15 canonical entity schemas. See Data Models Reference for complete JSON schemas.

Entity Overview

Entity	SDTM Domain	Description
Subject	DM	Trial participant (extends Person)
Study	TS	Protocol definition
Site	-	Investigational site
TreatmentArm	TA	Study arm definition
VisitSchedule	TV	Protocol visits
ActualVisit	SV	Subject visit occurrence
Randomization	DM/SE	Subject randomization
AdverseEvent	AE	Safety events with MedDRA
Exposure	EX	Study drug dosing
ConcomitantMed	CM	Prior/concomitant meds with ATC
TrialLab	LB	Lab results with LOINC
EfficacyAssessment	RS/TR	Response assessments
MedicalHistory	MH	Pre-existing conditions
DispositionEvent	DS	Subject disposition
ProtocolDeviation	DV	Protocol deviations

Key Entity Examples

Study:

{
  "study_id": "ABC-123-001",
  "protocol_title": "A Phase 3, Randomized, Double-Blind Study...",
  "phase": "Phase 3",
  "therapeutic_area": "Oncology",
  "indication": "Non-Small Cell Lung Cancer",
  "sponsor": "Example Pharma Inc.",
  "status": "Ongoing"
}

Subject (with cross-product linking):

{
  "subject_id": "0001",
  "usubjid": "ABC-123-001-001-0001",
  "site_id": "001",
  "patient_ref": "MRN-12345",
  "screening_date": "2024-01-15",
  "randomization_date": "2024-01-22",
  "treatment_arm": "TRT",
  "status": "Active"
}

Integration with Other Products

TrialSim integrates with other HealthSim products for complete clinical trial data:

From	To	Integration Pattern
PatientSim	TrialSim	Patient → Subject (add consent, randomization, protocol visits)
NetworkSim	TrialSim	Provider → Investigator (add credentials, training, delegation log)
PopulationSim	TrialSim	Demographics → Recruitment pool (geographic, demographic eligibility)

Cross-Product: PatientSim

Trial subjects are patients with additional trial-specific data:

../patientsim/oncology/ - Oncology trial subjects
../patientsim/heart-failure.md - CV outcomes trial subjects
../patientsim/behavioral-health.md - CNS trial subjects
../patientsim/diabetes-management.md - Metabolic trial subjects

Integration Pattern: Use PatientSim for baseline clinical characteristics. TrialSim adds protocol-specific assessments (RECIST, NYHA class changes), randomization, and SDTM-formatted data.

Cross-Product: PopulationSim Integration

PopulationSim v2.0 provides embedded real-world data for evidence-based trial planning, site selection, and diversity compliance. When geographies are specified, TrialSim uses actual CDC PLACES, SVI, and ADI data to ground feasibility estimates and enrollment projections.

Data-Driven Trial Planning Pattern

Step 1: Look up real population data for potential sites

# For site feasibility in Houston metro (Harris County, FIPS: 48201)
Read from: skills/populationsim/data/county/places_county_2024.csv
→ DIABETES_CrudePrev: 12.1% (for diabetes trial)
→ CHD_CrudePrev: 6.4% (for CV outcomes trial)
→ CANCER_CrudePrev: 6.2% (for oncology trial)
→ TotalPopulation: 4,731,145

Read from: skills/populationsim/data/county/svi_county_2022.csv
→ RPL_THEMES: 0.68 (moderate-high vulnerability)
→ EP_MINRTY: 72.1% (supports diversity requirements)

Step 2: Apply to site feasibility estimation

{
  "site_feasibility": {
    "county_fips": "48201",
    "county_name": "Harris County, TX",
    "indication": "Type 2 Diabetes",
    "eligible_population": {
      "total_population": 4731145,
      "disease_prevalence": 0.121,
      "prevalent_patients": 572467,
      "age_eligible_18_75": 458974,
      "funnel_to_screenable": 0.05,
      "annual_screenable": 22949
    },
    "diversity_metrics": {
      "minority_percentage": 0.721,
      "meets_fda_diversity_guidance": true
    },
    "data_provenance": {
      "source": "CDC_PLACES_2024",
      "data_year": 2022
    }
  }
}

Step 3: Generate realistic enrollment projections

Site catchment based on real prevalence (not national averages)
Diversity enrollment reflecting actual demographics
Screening-to-randomization rates adjusted for SVI (access barriers)

Embedded Data Sources for Trial Planning

Source	File	Use in TrialSim
CDC PLACES County	`populationsim/data/county/places_county_2024.csv`	Disease prevalence for feasibility
CDC PLACES Tract	`populationsim/data/tract/places_tract_2024.csv`	Catchment area analysis
SVI County	`populationsim/data/county/svi_county_2022.csv`	Diversity planning, access barriers
SVI Tract	`populationsim/data/tract/svi_tract_2022.csv`	Site-level vulnerability context
Geography Crosswalk	`populationsim/data/crosswalks/cbsa_definitions.csv`	Metro area site clustering

Trial-Specific Applications

Application	Data Used	TrialSim Integration
Site Feasibility	PLACES disease prevalence + population	Eligible patient pool sizing
Diversity Planning	SVI EP_MINRTY, demographics	FDA diversity guidance compliance
Enrollment Projection	PLACES + SVI access indicators	Screening/randomization rates
Site Selection	Multi-county PLACES comparison	Optimal site network design
Catchment Analysis	Tract-level PLACES	Drive-time eligible population

Example: Data-Grounded Phase III Site Selection

Request: "Identify top 5 US counties for a Phase III NASH trial based on patient availability"

Data Lookup Process:

Query places_county_2024.csv for:
  - High OBESITY_CrudePrev (NASH proxy)
  - High DIABETES_CrudePrev (comorbidity)
  - Large TotalPopulation (volume)

Query svi_county_2022.csv for:
  - EP_MINRTY (diversity potential)
  - EP_UNINSUR (access consideration)

Output with Provenance:

{
  "recommended_sites": [
    {
      "rank": 1,
      "county_fips": "48201",
      "name": "Harris County, TX",
      "obesity_prevalence": 0.328,
      "diabetes_prevalence": 0.121,
      "population": 4731145,
      "minority_pct": 0.721,
      "estimated_eligible": 45000,
      "diversity_score": "excellent"
    }
  ],
  "data_provenance": {
    "sources": ["CDC_PLACES_2024", "CDC_SVI_2022"],
    "methodology": "prevalence_weighted_ranking"
  }
}

Integration with Trial-Support Skills

PopulationSim Skill	TrialSim Application	Data Source
data-lookup.md	Exact prevalence for feasibility	CDC PLACES 2024
county-profile.md	Site catchment demographics	PLACES + SVI
svi-analysis.md	Diversity and access analysis	CDC SVI 2022
feasibility-estimation.md	Protocol feasibility funnel	All sources
diversity-planning.md	FDA diversity compliance	SVI demographics

Key Principle: When planning trials, always ground feasibility and diversity estimates in real PopulationSim data. This enables evidence-based site selection and realistic enrollment projections.

Development Status

Component	Status
SKILL.md (this file)	✅ Complete
clinical-trials-domain.md	✅ Complete
recruitment-enrollment.md	✅ Complete
phase3-pivotal.md	✅ Complete
domains/ (DM, AE, VS, LB, CM, EX, DS, MH)	✅ Complete
therapeutic-areas/	✅ Complete
rwe/	✅ Complete
phase1-dose-escalation.md	✅ Complete
phase2-proof-of-concept.md	✅ Complete

Related Skills

PatientSim - Clinical patient data
MemberSim - Claims integration
Code Systems - Standard terminologies

Output Formats

TrialSim supports multiple output formats:

Format	Use Case	Skill Reference
Canonical JSON	Internal processing, API integration	data-models.md
CDISC SDTM	Regulatory submission, FDA/EMA	cdisc-sdtm.md
CDISC ADaM	Analysis datasets, statistical programming	cdisc-adam.md
Dimensional (Star Schema)	Analytics, BI dashboards, DuckDB/Databricks	dimensional-analytics.md

Dimensional Analytics

For trial operations analytics and BI dashboards, request dimensional output:

Generate Phase III trial with 100 subjects as star schema for DuckDB

This produces:

Dimensions: dim_study, dim_site, dim_subject, dim_treatment_arm, dim_visit_schedule, dim_meddra, dim_lab_test
Facts: fact_enrollment, fact_visit, fact_adverse_event, fact_exposure, fact_efficacy, fact_lab_result

See dimensional-analytics.md for full DDL and example queries.

Usage Examples

Example 1: Basic Phase 3 Trial

Prompt: "Generate a Phase 3 oncology trial with 200 subjects"

Output:

{
  "study": {
    "study_id": "ONCO-2025-001",
    "protocol_title": "A Phase 3, Randomized, Double-Blind, Placebo-Controlled Study of ABC-123 in Advanced NSCLC",
    "phase": "Phase 3",
    "therapeutic_area": "Oncology",
    "indication": "Non-Small Cell Lung Cancer",
    "design": "Randomized, Double-Blind, Placebo-Controlled",
    "primary_endpoint": "Overall Survival",
    "target_enrollment": 200,
    "arms": [
      { "arm_id": "A", "name": "ABC-123 + SOC", "allocation_ratio": 1 },
      { "arm_id": "B", "name": "Placebo + SOC", "allocation_ratio": 1 }
    ]
  },
  "sites": [
    { "site_id": "001", "name": "Memorial Cancer Center", "country": "USA", "enrolled": 25 },
    { "site_id": "002", "name": "University Oncology", "country": "USA", "enrolled": 22 }
  ],
  "subjects": [
    {
      "subject_id": "001-0001",
      "site_id": "001",
      "arm": "A",
      "status": "Active",
      "randomization_date": "2025-01-15"
    }
  ]
}

Example 2: Adverse Events with MedDRA

Prompt: "Generate adverse events for a 50-subject immunotherapy trial"

Output:

{
  "domain": "AE",
  "adverse_events": [
    {
      "USUBJID": "IO-001-0023",
      "AESEQ": 1,
      "AETERM": "Fatigue",
      "AEDECOD": "Fatigue",
      "AEBODSYS": "General disorders and administration site conditions",
      "AESEV": "MILD",
      "AESER": "N",
      "AEREL": "POSSIBLY RELATED",
      "AESTDTC": "2025-02-10",
      "AEENDTC": "2025-02-18",
      "AEOUT": "RECOVERED/RESOLVED"
    },
    {
      "USUBJID": "IO-001-0007",
      "AESEQ": 1,
      "AETERM": "Immune-mediated colitis",
      "AEDECOD": "Colitis",
      "AEBODSYS": "Gastrointestinal disorders",
      "AESEV": "SEVERE",
      "AESER": "Y",
      "AESHOSP": "Y",
      "AEREL": "RELATED",
      "AEACN": "DRUG INTERRUPTED",
      "AESTDTC": "2025-03-05",
      "AEOUT": "NOT RECOVERED/NOT RESOLVED"
    }
  ]
}

Example 3: Screening and Enrollment

Prompt: "Generate screening data with 30% screen failure rate for 100 subjects"

Output:

{
  "screening_summary": {
    "total_screened": 143,
    "screen_passed": 100,
    "screen_failed": 43,
    "screen_failure_rate": 0.30
  },
  "screen_failures": [
    {
      "screening_id": "SCR-0015",
      "failure_reason": "Inclusion criteria not met",
      "failure_detail": "EGFR mutation negative",
      "screening_date": "2025-01-20"
    },
    {
      "screening_id": "SCR-0028",
      "failure_reason": "Exclusion criteria met",
      "failure_detail": "Prior immunotherapy within 6 months",
      "screening_date": "2025-01-25"
    }
  ]
}

Example 4: DM Domain SDTM Output

Prompt: "Generate DM domain for 10 subjects as SDTM"

Output:

{
  "domain": "DM",
  "records": [
    {
      "STUDYID": "ONCO-2025-001",
      "DOMAIN": "DM",
      "USUBJID": "ONCO-2025-001-001-0001",
      "SUBJID": "0001",
      "SITEID": "001",
      "RFSTDTC": "2025-01-22",
      "RFENDTC": null,
      "BRTHDTC": "1958-05-15",
      "AGE": 66,
      "AGEU": "YEARS",
      "SEX": "M",
      "RACE": "WHITE",
      "ETHNIC": "NOT HISPANIC OR LATINO",
      "ARMCD": "TRT",
      "ARM": "ABC-123 + SOC",
      "COUNTRY": "USA"
    }
  ]
}

Example 5: Laboratory Results with LOINC

Prompt: "Generate LB domain with liver function tests for safety monitoring"

Output:

{
  "domain": "LB",
  "records": [
    {
      "STUDYID": "SAFE-001",
      "DOMAIN": "LB",
      "USUBJID": "SAFE-001-001-0042",
      "LBSEQ": 1,
      "LBTESTCD": "ALT",
      "LBTEST": "Alanine Aminotransferase",
      "LBCAT": "CHEMISTRY",
      "LBORRES": "32",
      "LBORRESU": "U/L",
      "LBSTRESN": 32,
      "LBSTRESU": "U/L",
      "LBSTNRLO": 7,
      "LBSTNRHI": 56,
      "LBNRIND": "NORMAL",
      "LBLOINC": "1742-6",
      "LBBLFL": "Y",
      "VISITNUM": 2,
      "VISIT": "BASELINE"
    }
  ]
}

Generative Framework Integration

TrialSim integrates with the Generative Framework for specification-driven generation at scale.

Profile-Driven Generation

Use profile specifications to generate trial subject populations:

"Generate 150 subjects for an oncology Phase 3 trial"

The Profile Executor will:

Sample demographics meeting I/E criteria
Generate baseline disease characteristics
Apply randomization to treatment arms
Create screening and baseline assessments

Journey-Driven Generation

Attach protocol journey specifications to create visit sequences:

"Add a 6-cycle treatment protocol journey"

The Journey Executor will:

Generate protocol visits at specified windows
Create assessments per visit schedule
Apply visit variance within windows
Handle protocol deviations and early termination

Cross-Domain Sync

When generating across products, TrialSim entities are automatically linked:

TrialSim Entity	Links To
Subject	PatientSim Patient (via SSN)
Site	NetworkSim Facility
Investigator	NetworkSim Provider
Conmed	RxMemberSim Fill (if applicable)

See: ../generation/executors/cross-domain-sync.md

healthsim-trialsim

$ Installieren

TrialSim

For Claude

Overview

Trigger Phrases

Quick Links

Core Skills

Trial Phase Skills

SDTM Domain Skills

Therapeutic Areas

Real World Evidence

Output Formats

Data Models & References

Core Entities

Entity Overview

Key Entity Examples

Integration with Other Products

Cross-Product: PatientSim

Cross-Product: PopulationSim Integration

Data-Driven Trial Planning Pattern

Embedded Data Sources for Trial Planning

Trial-Specific Applications

Example: Data-Grounded Phase III Site Selection

Integration with Trial-Support Skills

Development Status

Related Skills

Output Formats

Dimensional Analytics

Usage Examples

Example 1: Basic Phase 3 Trial

Example 2: Adverse Events with MedDRA

Example 3: Screening and Enrollment

Example 4: DM Domain SDTM Output

Example 5: Laboratory Results with LOINC

Generative Framework Integration

Profile-Driven Generation

Journey-Driven Generation

Cross-Domain Sync

Repository

Actions

Related Skills