What does the Clinical Trial Matching project do?

It is a clinical-data pipeline that ingests studies from ClinicalTrials.gov, extracts trial eligibility criteria with NLP, and matches patient profiles to trials with explainable results rather than a black-box score. It was built by Omar Abdalla as an agentic, spec-driven engineering exercise.

How does Clinical Trial Matching extract eligibility criteria?

A spaCy / SciSpaCy NLP pipeline extracts eligibility criteria from dense trial descriptions. Because this is clinical data, it adds terminology-grounding for safety and provenance tracking so every extracted fact traces back to its source.

What stack does Clinical Trial Matching use and is it interoperable?

It is split into clean application, frontend, and data layers: a FastAPI and PostgreSQL backend behind a Next.js and TypeScript frontend. It exports matches as FHIR ResearchStudy resources for healthcare interoperability.

All work

Case study · 2026

Clinical Trial Matching

A spec-driven engineering exercise, not a product: a clinical-data pipeline that reads trial eligibility the way a coordinator would, and explains its matches.

GitHub

FHIR

ResearchStudy export

NLP

eligibility extraction

Explainable

match results

The exercise.

I built this as an agentic, spec-driven exercise to work through a hard domain end to end. It ingests studies from ClinicalTrials.gov and turns dense eligibility text into something matchable.

Extracting eligibility.

A spaCy/SciSpaCy NLP pipeline extracts eligibility criteria from trial descriptions. Because this is clinical data, I leaned on terminology-grounding for safety and tracked provenance so every extracted fact traces back to its source.

Matching, explainably.

The system matches patient profiles to trials and returns explainable results rather than a black-box score, with FHIR ResearchStudy export for interoperability.

It's split into clean application, frontend, and data layers: FastAPI and PostgreSQL behind a Next.js and TypeScript frontend.

Stack.

FastAPIPostgreSQLspaCy / SciSpaCyNext.jsTypeScript

FAQ.

What does the Clinical Trial Matching project do?: It is a clinical-data pipeline that ingests studies from ClinicalTrials.gov, extracts trial eligibility criteria with NLP, and matches patient profiles to trials with explainable results rather than a black-box score. It was built by Omar Abdalla as an agentic, spec-driven engineering exercise.
How does Clinical Trial Matching extract eligibility criteria?: A spaCy / SciSpaCy NLP pipeline extracts eligibility criteria from dense trial descriptions. Because this is clinical data, it adds terminology-grounding for safety and provenance tracking so every extracted fact traces back to its source.
What stack does Clinical Trial Matching use and is it interoperable?: It is split into clean application, frontend, and data layers: a FastAPI and PostgreSQL backend behind a Next.js and TypeScript frontend. It exports matches as FHIR ResearchStudy resources for healthcare interoperability.

Let's talk.

Happy to walk through the architecture and the decisions behind it.

Get in touch Résumé