Freelance data scientist · All case studies

Five years of hospital claims, built for the case.

A litigation-grade dataset against improper 99285 emergency billing.

Client: Law firm — healthcare fraud litigation. Built by Dilshad Raza.

Counsel needed a defensible view of hospital emergency billing — specifically CPT 99285, the highest-level ED visit code. The raw extract was huge, inconsistent across years and facilities, and unusable as a case file until it was cleaned, mapped, and transformed into something a lawyer could argue from.

I ingested the full multi-year hospital claims history, standardised fields across vintages, and built a repeatable pipeline: quality rules, CPT 99285 isolation, facility and provider mapping, and transforms the law firm could replay. The output was not a slide. It was a case-ready table with a trail.

Hire Dilshad Raza for similar freelance data science, machine learning, and AI automation in the UK, United States, and Australia.