← Cases
United StatesHealthcare and life sciences2024 – ongoing

AdaptHealth

AI-enabled processing of incoming referral faxes

AdaptHealth's AI process read incoming faxes with 99.6% accuracy, against 89% for its legacy process

WorkingCompany's own claim

Problem

AdaptHealth, a US home medical equipment provider, received more than five million pages of faxes every month. Much of the content was unstructured referral data that staff had to sort and route by hand. The legacy process was accurate about 89% of the time.

Approach

The company built an automated process enabled by AI to handle the incoming unstructured documents. According to the CEO, it went live within weeks. The company described it as a first step toward automating more of the workflow.

Results

99.6%accuracy of the AI-enabled automated process, versus 89% for the legacy process, as stated by the CEOCompany's own claim[1]
more than 5 million pagesfaxes received each month, per the CEOCompany's own claim[1]

Takeaway

Document intake was a high-volume task where an accuracy gap against the old process could be measured directly. The figure comes from management's own account on an earnings call.

Categories

Business function
Production and quality
Innovation type
Process innovation
Evidence
Company's own claim

Sources

  1. AdaptHealth Q3 2024 Earnings Call Transcript
    MarketBeat5 Nov 2024News article

Source summaries

[1]MarketBeat5 Nov 2024

Transcript of AdaptHealth's third-quarter 2024 earnings call. CEO Suzanne Foster said the company received more than five million pages of faxes a month and that its new AI-enabled automated process was 99.6% accurate against 89% for the legacy process. She said it went live within weeks.

Full details are in the original sources.

Added 2 Nov 2026 · Updated 2 Nov 2026
Open case page ↗