HealthcarePrivacyData Engineering

De-id.org

Automated PHI de-identification for medical datasets and clinical research.

De-id.org
RoleProduct Lead
Timeframe12 Months
ImpactDelivered
StackFull Stack Architecture
01 / Context

The Problem

Clinical research requires PHI de-identification. Manual redaction is slow and error-prone. Most automated tools miss contextual identifiers or over-redact, destroying data utility.

De-id.org uses NLP to intelligently strip identifiers while preserving medical meaning. Built for researchers who need compliant datasets, fast.

02 / Strategy

Approach

Build Principles

  • • Ship fast, iterate on real feedback
  • • Start with constraints, not features
  • • Measure what actually matters

Technical Moat

Domain expertise in Healthcare. Systems built for scale without overengineering. Pragmatic tech choices that ship.

03 / Execution

What We Built

Systems Architecture

Detailed technical schematics and documentation for De-id.org are proprietary and available upon request for deep-dive discussions.

Technical constraints forced creative solutions. We optimized for Healthcare from day one, which meant rethinking architecture at every layer. Shipped incrementally, validated with real users, and scaled what worked.

04 / Results

Impact

SHIPPED

Delivered on scope, timeline, and technical requirements

What I Learned

SaaS margin lives in simplicity. Cut scope aggressively, automate everything, and let pricing scale with value delivered.

More Projects

Building the Next Inflection

I'm drawn to hard problems at the intersection of emerging technology and human behaviour especially in spaces that are ripe for disruption powered through innovation.