Skip to main content

Patient Record Linkage at Scale

1 min

Overview #

I designed and built a large-scale patient matching system combining learned representations with deterministic constraints.

The system used neural embeddings, blocking strategies, clustering, and precision/recall evaluation techniques to link records across healthcare datasets while balancing accuracy and scalability.

Why it matters #

Entity resolution is a foundation problem for healthcare data. Small errors have large downstream effects, and the system must combine statistical learning with domain knowledge.

Themes #

  • Representation learning
  • Entity resolution
  • Evaluation methodology
  • Production ML systems