GigaTIME: Multimodal AI generates virtual population for tumor microenvironment modeling (Cell)

Python toolkit for Medicaid claims data analysis — preprocessing, cleaning, risk adjustment (Elixhauser, CDPS-Rx), quality measures (PQI, BETOS, low-value care), and patient-level analytic file construction for MAX and TAF CMS data. Built on Dask for scalable processing of large-scale healthcare claims datasets.

R SDK for OMOP/OHDSI vocabularies. Query 10M+ medical concepts across SNOMED, ICD-10, RxNorm, LOINC & 90+ terminologies via simple API

Code for the paper "Clinical connectivity map for drug repurposing: using laboratory results to bridge drugs and diseases". Accepted by BMC Medical Informatics and Decision Making, 2021

Example code for the handbook "Comparative effectiveness and personalized medicine using real-world data"

Python SDK for OMOP/OHDSI vocabularies - query 10M+ medical concepts across SNOMED, ICD-10, RxNorm, LOINC & 90+ terminologies via simple API

Code and Datasets for the paper "A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data", published on Nature Machine Intelligence in 2021.

ATLAS is an open source software tool for researchers to conduct scientific analyses on standardized observational data

AI-powered FDA drug label intelligence platform — production RAG with 5-stage retrieval, multi-agent orchestration, clinical guardrails, and 54 automated tests

[Experimental] Federated Partial Identification for Causal Inference with OMOP CDM

Make EHR easier to work with

Read Personalis datasets into MultiAssayExperiment objects

Author: Cong Zhu. Purpose: code for paper "Investigating safety profiles of human papillomavirus vaccine across group differences using VAERS data and MedDRA."

Production-grade Real-World Evidence platform for vaccine researchers. Next.js 16 · React 19 · Supabase · TypeScript. Features PICO protocol builder, PRISMA screening pipeline, RoB 2/ROBINS-I assessment, meta-analysis forest plots, real-time CRDT collaboration (Yjs), and FDA/EMA/CDISC regulatory exports. 76 API routes · 27 DB tables · 1,400+ tests.

HL7 FHIR R4 → OMOP CDM → Snowflake → dbt → Dagster. RCM: classifies 257K denied claims by root cause — systematic vs. documentation failures. RWE: T2D+CKD metformin utilization cohort. 12 dbt models, 83 tests, CI green.

Maurice Zeegers / Observational Studies

A literature review exploring how missing data was handled across the pipeline of commonly used UK clinical prediction models

An interactive platform for CPRD Aurum data extraction, code list development, and cohort assembly

Date cleaning and preprocessing | Data wrangling | Date merging | Data visualization | Descriptive & inferential statistics | Report Writing | Real world data

Stroke2Work analyzes return-to-work and health outcomes in stroke survivors, using statistical models to identify patient subgroups most likely to benefit, optimize work reintegration timing, and segment individuals by projected recovery and long-term quality-of-life.