All apps

Advanced Analytics · Analysts / Researchers

↔ shared

CuRE Calculate

Analytics hub — cohorts, characterization, and submission-grade outputs.

What it does

Analytics hub — cohorts, characterization, and submission-grade outputs. Cross-modal questions become native: ask whether cryopreservation, manufacturing variance, shipping time, biomarkers, ePRO, and EHR history affect CAR-T outcomes in one workspace.

Key capabilities

  • In-app reactive data-science IDE (SQL/Python/R, governed)
  • OMOP-native cohort definitions
  • Characterization studies
  • Briefings template engine (AI-authored reports)
  • Submission outputs (CIBMTR-style)
  • Trial-design simulation + program economics (operating characteristics, GSD sizing, eNPV/VoI)
  • PLE study-diagnostics + reliability gate
  • Causal-design breadth (SCCS / case-control / TTE)
  • Independent double-programming QC
  • CEA/BIA + indirect-treatment-comparison methodology
CuRE Calculate — analytics workbench Cohorts view with portfolio metrics, AI-authored cohort narrative, and saved cohorts including a CAR-T grade-≥3 CRS prediction cohort
Sandbox preview — synthetic demo data

What sets it apart

  • Cross-modal questions become native: ask whether cryopreservation, manufacturing variance, shipping time, biomarkers, ePRO, and EHR history affect CAR-T outcomes in one workspace.
  • A governed in-app data-science IDE is the primary surface: a reactive SQL/Python/R notebook (dependency-inferred cell-DAG, live co-editing, publish-as-data-app) on the Conduct-governed enclave, with every result egress-checked and snapshot-pinned for reproducibility — JupyterLab stays as a per-session escape hatch. Governed AI cells ride the same enclave: generate code from natural language or narrate a cell's output in prose, each egress-checked before any data reaches the model.
  • PLE study-diagnostics — MDRR, equipoise overlap, negative-control calibration — gate every real-world estimate, the discipline RWE buyers judge first.
  • Double-programming QC, empirical calibration, negative-control diagnostics, Atlas-style characterization, and no-code builders are part of the analytics surface.
  • Briefings AI-author submission-grade documents directly from the analysis — narrative, tables, and citations stay tied to the data, no copy/paste pipeline.
  • Offline + live execution modes — develop against a snapshot, run against live OMOP.
  • Translational PK/PD, biomarker-bridging, and empirical first-in-human dose methodology (MABEL / NOAEL→HED, SEND / Module 4) extend Calculate upstream toward IND enablement — the Translational bundle's move to first-in-human (ADR-PLT-100).
CuRE Calculate · Cohort characterization
Live demo — synthetic data, runs in your browser

Characterize a cohort, live

Define inclusion criteria over a synthetic OMOP CDM slice and watch the characterization table recompute in your browser — demographics, condition and drug prevalence, and lab distributions, each compared against the background population. Filter to a condition and the enriched comorbidities and shifted labs fall out of the real aggregation, not a script.

Inclusion criteria over a synthetic OMOP CDM slice of 600 persons.

Cohort size
600
100.0% of 600 persons
Mean age
55.1
±16.8 · median 55
Female
48%
Age range
18–90

Condition prevalence

ConditionCohort vs. sourceCohortΔ
Hypertensive disorder
28.3% (170)
Obesity
26.2% (157)
Hyperlipidemia
21.7% (130)
Osteoarthritis
19.2% (115)
Major depressive disorder
13.2% (79)
Type 2 diabetes mellitus
12.5% (75)
Atrial fibrillation
9.5% (57)
Chronic kidney disease
9.0% (54)
Asthma
8.3% (50)

Lab measurements

MeasurementNMean (SD)MedianSource mean
Hemoglobin A1c %5455.6 (0.8)5.45.6
Systolic blood pressure mmHg566127 (13)125127
Body mass index kg/m²54728.1 (5.4)27.928.1
Total cholesterol mg/dL522194 (35)193194
eGFR mL/min/1.73m²52586 (13)8886

Drug exposure

DrugCohort vs. sourceCohortΔ
Lisinopril
21.2% (127)
Atorvastatin
14.7% (88)
Sertraline
9.3% (56)
Metformin
9.2% (55)
Albuterol
7.3% (44)

Bars show the cohort rate; the vertical marker is the rate in the full synthetic source population, so an enriched feature reads as a bar overshooting its marker. Every figure is aggregated in your browser from 600 synthetic OMOP persons — change a criterion and watch it recompute.

Why this is more than a toy

This is the OHDSI cohort-characterization pattern — the same shape as FeatureExtraction — running on real OMOP standard concept IDs (SNOMED conditions, RxNorm drugs, LOINC labs). Every count, prevalence, and mean is aggregated client-side from a synthetic population of 600 persons; nothing here calls a backend. In the product, CuRE Calculate runs this characterization methodology over a governed OMOP store and emits submission-grade, validated outputs.

See CuRE Calculate in action

Every research ecosystem is unique. Let's discuss how CuRE can be configured for your needs.