Identity resolution in pharma: one HCP, six records

September 24, 2026 · 5 min · Free, with full transcript

Why does a single cardiologist show up as six separate entities across a pharma company's CRM, purchased claims data and analytics warehouse, and what does that cost? The position here is blunt: identity resolution is not a tool purchase, it is plumbing. Bad matching splits one high prescriber into six low ones, which skews sample allocation, wastes temperature controlled product, and can hide adverse event patterns in pharmacovigilance reporting that regulators will not excuse. You get a working approach: make the federal NPI registry the source of truth, run nightly matches, write down survivorship rules, and name one accountable owner with budget for the prescriber master record. References include DBT Labs and MIT Sloan Management Review, plus a master data example at Novartis.

Listen to the podcast

4 min

Chapters

Key takeaways

  • Make the federal NPI registry the source of truth for prescriber identity and force every other system to point at it.
  • Run a match against the federal file nightly instead of treating deduplication as a one-off project that decays within 18 months.
  • Write down explicit survivorship rules so you know which record wins when two versions disagree on address or name.
  • Name one person accountable for the prescriber master record, with budget, before buying any matching tool.
  • Pull every record for your top 10 prescribers by revenue by hand and count the duplicates to get the dollar figure your board needs.
Read the full transcript

Host:This is Leader's Insights. On the table, 1 HCP, 6 records. Why identity resolution is pharma's most expensive data problem. 6 records for 1 cardiologist. That's the number that stopped me.

Expert:6 is the average I see when I audit a mid-sized pharma's systems. I've seen 11. 1 cardiologist in Ohio spelled 4 ways, 2 license numbers, 3 addresses because she moved practices twice and a middle initial that shows up in the claims feed but not the CRM, the customer system where reps log their visits.

Host:And none of them talk to each other.

Expert:None. They can't. The CRM knows Dr. J. Ramirez, 400 Elm. The claims data, the record of what she actually prescribed, bought from a data broker, knows Jennifer Ramirez, MD, NPI, and the NPI. The NPI is the National Provider Identifier, the federal 10-digit number every prescriber gets. And the Analytics Warehouse has a third version built by a vendor 5 years ago that nobody remembers configuring.

Host:So what breaks first?

Expert:Sampling. You send free drug samples based on who's a high prescriber. If your cardiologist is split across 6 records, each one looks like a low prescriber. So you under-sample your best customer and over-sample 4 ghosts. I watched a company waste roughly a third of a sample budget that way. That's real product, temperature controlled, expiring on shelves.

Host:A third. Is that your number or someone's marketing deck?

Expert:That one's mine, from the audit. But there's a related figure from DBT Labs. They sell data tooling, so read it with one eyebrow up. Claiming companies spend a huge share of analyst time just reconciling identities before any actual analysis. Directionally, I believe it. Cross-check against MIT Sloan Management Review, which has written for years that data quality, not data volume, is where the money leaks.

Host:Let me push on the scary part. You said pharmacovigilance.

Expert:Pharmacovigilance. Safety monitoring, tracking adverse events after a drug ships. If a patient has a bad reaction and the report ties to record number 3, but the prescriber's actual history lives in record 1, you might miss a pattern. Regulators don't accept our systems didn't match. As an excuse.

Host:Has anyone actually been burned by that on the record?

Expert:Nobody puts our identity resolution failed in a press release. What you see is the downstream symptom. A delayed signal. A warning letter about incomplete reporting. I've sat in the room after one. The root cause traced back to duplicate prescriber records nobody had merged. So the lesson the good operators already learned isn't by a matching tool. Its identity is infrastructure. Treat it like plumbing.

Host:Explain the plumbing thing because every vendor says by their tool.

Expert:A tool matches records once. Plumbing means you decide permanently which system is the source of truth for a prescriber's identity, usually the NPI registry because it's federal and stable. And every other system bends to it. Novartis and a few others move to what people call a master data approach years ago. One golden record. Everything else points at it. Boring. Unsexy. Works.

Host:But NPI changes. People move, retire, change specialties.

Expert:Right. So you don't do it once. You run a match every night against the federal file, and you keep a survivorship rule. Wania, plain terms. When two records disagree on her address, which one wins? You write that rule down. Most companies never do. They match once in a big project. Declare victory. And 18 months later, they're back to six records because the plumbing had no maintenance.

Host:So the failure isn't technical. It's that nobody owns it.

Expert:Exactly. Identity has no natural owner. Sales wants their CRM. Analytics wants their warehouse. Safety wants theirs. Everybody assumes someone else deduplicated. I tell every board, name one person accountable for the prescriber master record with budget. Or don't bother buying anything. Give me the one thing a listener does Monday

Host:morning. Pick your top 10 prescribers by revenue. Pull

Expert:every record for each across your systems by hand. Count them. If any of those 10 shows up more than once, and they will, you now have the exact dollar figure your board needs to fund the fix. Don't theorize the problem.

Host:Photograph it. Photograph it. That's the takeaway. What we read for this one, DBT Labs vendor data tooling MIT Sloan Management Review. We'll stop there. The whole CDO track and order is waiting at MBA-training.com.

Read and go deeper