Speaker program compliance that scores every program on the OIG's red flags, before and after it runs
Every speaker program scored on the OIG's red flags, before and after it runs.
See one case, screen by screen ↓Software that monitors promotional HCP speaker programs for the risks the OIG and the PhRMA Code describe. Speaker Program Compliance reads every program request and, after the event, its sign-in sheet and invoice, scores both against the OIG's eight red flags, and aims unannounced audits at the programs most likely to fail. A compliance monitor decides and signs.
How to choose AI solutions for life sciences →
Updated
A speaker program is approved on a checklist, from the request: the venue, the deck, the RSVP list, an estimated cost per head. The red flags that matter most — who actually came, who had no business reason to be there, what the invoice says was served — only show up after the event, on a handwritten sign-in sheet and a venue invoice that are read weeks later, if at all, when the quarter's sample comes round.
The OIG's Special Fraud Alert names the signs of a speaker program that is really a kickback: a restaurant or entertainment venue, little or no new medical information, alcohol or a meal above modest value, many programs on the same topic, the same HCPs attending again and again, guests with no legitimate business reason, speakers chosen by sales, and pay above fair market value. Monitors attend only a few percent of programs live, and audits are drawn at random, not aimed at the programs most likely to fail.
Estimated split for one high-risk program, from the request to a signed monitoring report, in days — by hand with a quarterly sample before, and with the solution.
Seven specialist agents read, check, score and report on every program; a compliance monitor decides to clear, change, audit or refer.
Wednesday, October 7. Last night Dr. Neil Brandt spoke on Corventa at Bricktown Chophouse in Oklahoma City — program SP-24106, requested by Casey Morgan in territory OK-112. Here is what happens next, screen by screen, in the working solution.
Lena owns monitoring for seven territories. Each row is a program and each column one of the OIG's eight red flags; every cell has two squares, the left scored before the event from the request, the right after it from the sign-in sheet and invoice. SP-24106 scored 48 from its request, and its sign-in sheet is in. Upcoming, SP-24117 at The Ember Room in Tulsa scores 86.
“each cell: left square before the event, right square after”
One click on a cell shows its evidence. For SP-24117, Dr. Raymond Kessler's dinner in two days, sales-driven speaker choice scores +12: the nomination by Jordan Blake in sales cites the speaker's prescribing, and the territory plan books his dinners for top targets. Each statement links to the document it came from.
From the nomination: “top-decile Corventa writer in OK-114, with strong ROI on his programs”
The reader takes 15 handwritten rows and a $92-a-head invoice with no alcohol. The repeat attendee tracker matches the names by NPI: five have come to this topic two or more times, and Dr. Raymond Kessler, another paid Corventa speaker, walked in without an RSVP. Two people signed in without an NPI. Attendance and repeat attendees turn red, and the score moves from 48 to 76.
“5 of 15 attendees have come to this topic two or more times in 12 months, including another Corventa speaker, Dr. Raymond Kessler, who was not on the RSVP list.”
Because Dr. Brandt's October 6 program turned red at sign-in, his next one — SP-24158, Bricktown Chophouse again, on October 21 — rises from 60% to 84% fail odds and to the top of the unannounced audit picks. Lena clicks Plan. A live audit is booked for her, and the field is not told.
“Unannounced live audit planned · SP-24158 · Lena Ortiz · Oct 21 — the field is not told”
The program review shows the dial at 76, high risk from 60, and each OIG factor with its points: restaurant venue +18, no new medical information +8, many programs on one topic +10, repeat attendees +14, attendees with no business reason +14, sales-driven speaker choice +12. Meal and speaker pay stay clear. Dr. Brandt is at 62% of his annual cap, 73% with programs booked.
Topic & Label Checker: “412 programs on CRV-HF-03 in 12 months · last label change 19 months ago”
Every document behind the program sits in one viewer: the request, the attendance list, the sign-in sheet scan, the venue invoice, the deck and label, the nomination, the speaker agreement and the territory plan. Lena checks the printed names, NPIs and signatures against what the agents read. The reader never guesses an NPI — a blank stays blank.
Lena asks for the draft. The report reconciles attendance: 10 RSVPs, 15 signed in, 2 without an NPI — Chris Doyle, signed in as a guest, and Lauren Pike, a practice manager — 5 repeat attendees, and food and beverage at $92 against $95. Six findings follow, each with its OIG factor and source, then recommended actions.
“Drafted by the Monitoring Report Writer from 8 documents · every finding cites its source · intent is not concluded.”
The recommended actions include referring the Kessler–Brandt pairing to investigations, moving Dr. Brandt's remaining 2026 programs to office or virtual formats and excluding the five repeat attendees from same-topic invitations for six months. Lena can edit, sign and close, or sign and refer with the evidence pack to Dana Okafor. She signs; the program closes and the signature goes on its activity trail.
“Report signed · program closed”
The repeat attendees view draws the last 12 months of sign-in sheets and RSVP lists as a network. Dr. Kessler and Dr. Brandt each attended 5 of the other's Corventa programs this year — a pattern the OIG alert names. Five people came to four or more of Dr. Kessler's programs on one topic, and all five are invited again on October 9.
Guests at Harbor Grill: “2 people without an NPI signed in at two Alvarez programs — one shares the speaker's surname.”
The audit plan puts every unannounced live and virtual audit on a three-week calendar: risk-based picks first, then a 2% random sample of the week's programs. SP-24158 now sits on October 21. Two high-risk programs are still uncovered — SP-24117 and SP-24142, both Dr. Kessler's — each one click from an audit.
“No advance notice. Audits are visible only to compliance. Reps and the bureau see a monitor arrive, never a calendar entry.”
The same programs, seen by the four people who monitor, audit, investigate and answer for them — what their month looked like, and what it looks like now.
Seven specialist agents read, check, score and report on every program; a compliance monitor decides to clear, change, audit or refer.
Reads each program request from the events platform, then the scanned sign-in sheet and venue invoice after the event: venue, format, deck, RSVP list, cost per head, any bar or alcohol line, and every sign-in row with name, NPI, signature and handwritten notes.
Classifies the venue — office, hospital, hotel meeting room, restaurant, wine bar, country club, entertainment — compares the cost per head with the cap for the city, and finds alcohol, a bar or a wine pairing, planned or invoiced.
Matches every invitee and signer to the HCP master by NPI, then name and city; counts same-topic programs per HCP over 12 months and spots speakers who attend each other's programs.
Counts programs per deck in the last 12 months and reads the label change history: how many months since the last substantive change, and what it was.
Reads nomination forms and the territory plan for language that ties a speaker or invitee to prescribing, revenue, ROI or writers; checks the fee against the FMV tier and year-to-date pay plus booked programs against the annual cap.
Combines the eight factors into a 0–100 score with one cited reason per factor, works out each upcoming program's odds of failing, and proposes unannounced audits — risk-based first, then a random sample.
Drafts the monitoring report after the event: program facts, attendance reconciliation, findings against policy with their evidence, and recommended actions.
Decides; investigators take referrals. The agents propose; a named person decides.
Ask in plain words, or say what to change. Every answer points to the request, sign-in sheet, invoice or nomination it came from.
Why is SP-24117 high risk?
SP-24117 scores 86 — high risk. It sits at The Ember Room steakhouse, private dining; $118 per head against the $95 cap, with a wine pairing requested; 6 of 14 invitees are repeat attendees, including speaker Dr. Brandt; the nomination says “top-decile writer … strong ROI”; and deck CRV-HF-03 has run 412 times with a label 19 months old. The event is in 2 days. Moving it to an office venue with no alcohol drops the score to about 52.
Which speakers take turns attending each other's programs?
One pair: Dr. Raymond Kessler and Dr. Neil Brandt, both paid Corventa speakers. This year each attended 5 of the other's programs on the same deck — Dr. Brandt signed in at Dr. Kessler's October 1 dinner, and Dr. Kessler at Dr. Brandt's September 29 program. Dr. Brandt is invited again on October 9. The OIG alert names HCPs who attend repeat programs as speakers or attendees.
Plan unannounced audits for every uncovered high-risk program
Done. I added 3 unannounced live audits: SP-24117 · The Ember Room on October 9 (86), SP-24142 · Riverside Country Club on October 15 (76) and SP-24158 · Bricktown Chophouse on October 21 (70). Every high-risk program in the next three weeks is now covered. Nobody in the field is told.
Lower the standard meal cap to $85 per head
Done. The standard-area meal cap is now $85 per head (was $95). I re-scored the programs: SP-24142 · Riverside Country Club is now also flagged for its meal — $92 per head — and its score rises from 76 to 86. No other program changes band. The change is in Settings and the audit trail, and Priya Raman is asked to approve it.
13 screens from the working solution, on its sample data. Pick one to see it large.
The rules every program is scored against come from the OIG Special Fraud Alert, the PhRMA Code and company policy. A change re-scores every open program and is recorded in the audit trail.
| Setting | Default | Choose from |
|---|---|---|
| Meal cap per head | $95 in standard areas, food and beverage, tax and tip included | Step up or down; shows how many programs it flags now |
| Repeat attendance | Flag an HCP at 2 same-topic programs in 12 months | Step up or down |
| Deck review line | Flag a topic when its deck runs more than 250 times in 12 months | Step up or down |
| No new information | Flag when the last label change is older than 12 months | Step up or down |
| Speaker cap alert | 75% of the $50,000 annual cap | Step up or down |
| High-risk line | Score 60 — a person decides every program at or above it | Step up or down |
| Venues and meals | Flag restaurants; flag wine bars, country clubs and entertainment venues; no alcohol at any program | Each on or off · allowed venues: office, hospital, hotel meeting room, virtual |
| Audit sampling | Risk-based audits at score 60+, a 2% random sample, unannounced only | Random share steps up or down · prefer live audits within 150 miles, otherwise the monitor joins virtually |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample program data · “target” = the design goal, measured in the live solution · “estimated” = our estimate, including today's share of programs seen live · “typical” = published figures (OIG Special Fraud Alert: Speaker Programs, Nov 16, 2020, citing Open Payments data: nearly $2 billion paid to HCPs for speaker-related services over the preceding three years). Regulations and codes named as context: the Anti-Kickback Statute, 42 USC 1320a-7b(b), and the PhRMA Code (2022). People, companies, brands, venues and programs named on this page are fictional — characters and sample data in the working solution.
Software that monitors promotional HCP speaker programs for the risks the OIG and the PhRMA Code describe. Speaker Program Compliance reads every program request and, after the event, its sign-in sheet and invoice, scores both against the OIG's eight red flags, and aims unannounced audits at the programs most likely to fail. A compliance monitor decides and signs.
Specialist agents check the venue and meal, the deck's program count and label age, repeat attendees, attendees with no business reason, sales language in the nomination and the speaker's pay against the annual cap. The Risk Scorer combines them into a 0–100 score with one cited reason per flag, weighted as set in Settings.
The reader takes every handwritten row and the invoice lines, the repeat attendee tracker matches names by NPI, and the score is recalculated. On the sample program, 15 names against 10 RSVPs, two with no NPI and five repeat attendees moved the score from 48 to 76, and the monitoring report was drafted with a citation for every finding.
Each upcoming program without an audit gets fail odds from its score, raised when the speaker's recent program turned red at sign-in, when the venue added flags before, for four or more repeat invitees, or when the speaker has not been audited in 30 days. The top picks are offered for a live audit, and a random sample — 2% of the week's programs by default — is drawn on top.
No. Audit picks and plans are visible only to compliance. The speaker bureau sees change and hold requests, the brand lead sees topic saturation by deck, and reps see a monitor arrive, never a calendar entry.
Yes. A monitor decides every program at or above the high-risk line — clear, change the venue, hold, audit or refer — and signs every monitoring report. The agents never conclude intent and never contact the field; referrals go to an investigator with the evidence pack.
Yes. The meal cap per head, repeat-attendance threshold, deck review line, label age, speaker cap alert, high-risk line, venue and alcohol rules and the random sample are settings. Each change needs the chief compliance officer's approval, re-scores every open program and is recorded in the audit trail.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your speaker program policy, meal caps, FMV rate card and a sample of past program requests, sign-in sheets and invoices — and it goes live once every quality gate has passed. We will walk you through it on your own programs first.
Every recipient matched to the right NPI and licence, with the evidence
1-min demoThird-Party Due DiligenceEvery third party risk-tiered before the contract is signed, from its real owners.
1-min demoCompliance Investigation Case ManagementInvestigations close in a median of 18 days, every finding cited.
1-min demoWe'll run Speaker Program Compliance on a sample of your own past program requests, sign-in sheets and invoices.