Skip to content
Curious Context Labs

case study · Healthcare · Automation

Coverage problems solved before the patient arrives

How electronic eligibility checks for every appointment can move insurance problems from check-in to days ahead.

business
Diagnostics and labs
build
Automation
timeline
6 weeks
read
3 min

01 the business

Pathology and lab collection network

25 collection sites, 2,000 patients a day

Front-desk staff check insurance by phone and portal, often on the day. Inactive coverage and missing authorisations are found at check-in, causing delays and later denials.

02 before

The problem

Front-desk staff check insurance by phone or portal, one patient at a time, often on the day. Inactive coverage or a missing referral is found at check-in, and visits are delayed or claims are denied later.

  • Checks happen on the day, one at a time.
  • Coverage problems cause queues at check-in.
  • Eligibility errors lead to denied claims.

03 the build

What the AI does

  1. Step 1: Reads upcoming appointments a few days ahead from your scheduling system.
  2. Step 2: Runs electronic eligibility checks with each payer for every patient.
  3. Step 3: Reads the response for coverage status, co-pays, deductibles and any referral or authorisation needed.
  4. Step 4: Flags problems, such as inactive coverage or a missing authorisation, for the front desk to resolve before the visit.
  5. Step 5: Saves the result to the patient's account so check-in and billing use the same information.

paused: waiting for a person to approve

How it was put together

  • Read appointments a few days ahead.
  • Ran electronic eligibility checks with each payer.
  • Read coverage, co-pays, deductibles and referral or authorisation needs.
  • Flagged problems for the front desk and saved results for billing.

04 human in the loop

Where a person stays in charge

Front-desk staff contact patients about any coverage problem and decide how to proceed. The tool never cancels or reschedules a visit on its own.

  • Front-desk staff contact patients about problems and decide next steps.
  • The tool never cancels or reschedules a visit.
  • Results are stored only in the patient's account.

05 rollout

From kickoff to live in 6 weeks

  1. Weeks 1–2Connect scheduling and the clearinghouse; agree problem rules.
  2. Weeks 3–4Run for three sites and compare with manual checks.
  3. Weeks 5–6Extend to all sites.

06 after

What changes

Coverage problems are solved before patients arrive, check-in is quicker, and fewer claims are denied for eligibility reasons.

worked example · your numbers will differ

Assume 2,000 patients a day, a quarter needing a manual check today at 12 minutes each.

2,000 × 25% × 12 minutes = 6,000 minutes, or 100 staff hours a day across the network.

What to measure

  • Appointments checked before the day.
  • Check-in delays for coverage reasons.
  • Eligibility-related denials.
  • Front-desk time on checks.

07 evidence

What the research says

  1. Moving US healthcare admin transactions from manual to automated could save $20 billion a year; a prior authorisation takes providers about 24 minutes by phone, fax or email and 16 minutes through a portal.

    CAQH, 2024 CAQH Index (opens in a new tab) · 2025

  2. HealthCare.gov insurers denied 20% of in-network claims in 2023, and fewer than 1% of denied claims were appealed.

    KFF, Claims denials and appeals in ACA Marketplace plans in 2023 (opens in a new tab) · 2025

08 lessons

Mistakes to avoid

  • Checking too late. Run checks days ahead.
  • Ignoring authorisation flags.
  • Not saving results for billing.

09 questions

Common questions

How much time does automation save?
The 2024 CAQH Index estimates electronic eligibility checks save medical providers about 12 minutes per transaction compared with manual methods.
Does it work outside the US?
Insurance checks are mostly a US need, but the same approach works for private insurers and funding checks elsewhere.

keep reading

All case studies ->

Tell us how your business runs. We'll tell you where AI fits.

A free 30-minute call. You talk, we ask questions, and you leave with a few concrete ideas — or an honest answer that AI isn't the right fix yet.

Working with teams around the world.