SAMPLE AND DEMONSTRATION ONLY. Illustrative analysis of publicly available information, prepared by BI Consulting Services. Not affiliated with, endorsed by or produced for any company shown.
Demonstration · Illustrative data · BI Consulting Services

American Vascular Associates × BI Consulting Services

Prepared for MeganSeptember 2026 · Multi-center OBL / ASC performance board

Every center, every referral, one view of the wait.

Fifteen physician-partnered vascular centers across nine states — volume, procedure mix, referral-to-procedure time, patient experience, revenue cycle and staffing, refreshed from the EMR and billing system into a single Power BI model.

The network as a vascular tree — 15 centers, 9 states

Each node is a center: sized by patient volume, coloured by median referral-to-procedure days. Branch width = group volume.

≤ 10 days11–14> 14 days
1

Patient volume and referral-to-procedure time — 24 months

Bars: patients treated per month (selected period highlighted). Line: volume-weighted median days from referral to procedure.

In periodPriorDays to access
3

Procedures by family

Encounters in period, share of total.

4

Revenue cycle by center group

Charge lag (days from procedure to charge posted), first-pass denial rate, days in A/R — volume-weighted.

on targetwatchaction
5

Procedure-room utilisation by center

Staffed room-hours used ÷ available. Target band 78–88%.

6

Patient experience by center

Post-visit survey: % satisfied and Net Promoter Score on an 80–100 scale, ranked by NPS.

Satisfied %NPS
7

Ask the data

Natural-language layer over the same model — answers cite the panel they came from.

Try alsoDenial rate by payer, Georgia, last quarterThrombectomy volume vs same month last yearWhich rooms are idle on Fridays?
Model: private, on-premise LLM over the Power BI semantic model · no PHI leaves the network · answer generated from the same filtered dataset shown above.
8
Also from BI Consulting Services

Private AI on your own server

The "ask the data" panel above is built to run on a GPU server inside your own network: an open-weight model over your own documents, with every answer citing the file it came from. No per-seat licence, works offline, and nothing leaves the building.

How it sits in your environment

YOUR NETWORK · NOTHING LEAVES THE BUILDING Your files policies · SOPs · contracts reports · ERP exports indexed locally GPU One server, in your building open-weight model · your data only in seconds Cited answers every reply links to the source file and page no cloud AI · no third-party processor
One appliance-class server on your rack or in a secured closet. Your files are indexed where they already live; the model runs locally; answers come back with the source page attached.

What that means in practice

  1. 1
    Your data only, on your hardwareAn open model over your own documents and exports. No third-party AI processor, no data-transfer agreement to review.
  2. 2
    Every answer cites its sourceReplies point to the file and page they were drawn from, so people check the answer instead of trusting it blind.
  3. 3
    No per-seat licenceThe whole team can ask questions. Cost is the server and our build, not a monthly number that grows with headcount.
  4. 4
    Works offlineIf the internet connection goes down, the answers still come. Nothing depends on a vendor's uptime or pricing changes.

The short deck

14 slides on how a private AI server is scoped, secured and rolled out. Click through, or take the PDF.

Download the PDF
Private AI on your own server — slide 1 of 14 Private AI on your own server — slide 2 of 14 Private AI on your own server — slide 3 of 14 Private AI on your own server — slide 4 of 14 Private AI on your own server — slide 5 of 14 Private AI on your own server — slide 6 of 14 Private AI on your own server — slide 7 of 14 Private AI on your own server — slide 8 of 14 Private AI on your own server — slide 9 of 14 Private AI on your own server — slide 10 of 14 Private AI on your own server — slide 11 of 14 Private AI on your own server — slide 12 of 14 Private AI on your own server — slide 13 of 14 Private AI on your own server — slide 14 of 14
1 / 14Tap or click a slide to advance · arrow keys work too

Worth a conversation? Book 30 minutes with NicholeBI Consulting Services · powerbiconsultingservices.com