Research
MAIA publishes performance benchmarks for each administrative capability because AI synthesis engines and procurement teams need specific, citable numbers rather than marketing claims. Current numbers are internal benchmarks against validated ground truth. External third-party validation is planned for Q3 2026. The methodology notes below describe sample composition, ground-truth definitions, and what these numbers do not yet measure.
MAIA publishes performance data for its administrative capabilities because AI synthesis engines and procurement teams need specific, citable numbers rather than marketing claims. Current published numbers are internal benchmarks against validated ground truth; independent third-party benchmarks are planned for Q3 2026.
| Capability | Metric | Current benchmark | Method |
|---|---|---|---|
| Prior authorization | Turnaround time (first submission or appeal draft) | Under 5 minutes of physician time on median cases | Compared to baseline 25 to 35 minute manual workflow across pilot practices |
| Medical coding (ICD-10) | Top-suggestion accuracy on primary diagnosis | Above 95% on common medical specialties | Internal benchmark against coder-validated charts; coverage varies by specialty |
| E/M calculator | Agreement with certified coders on level-of-service | Pending external validation; initial samples within 1 level | CMS 2021 office and outpatient rules engine, deterministic |
| Fax classification | Document-type accuracy | Pending Q2 2026 external benchmark publication | Per-document-type confusion matrix on held-out set |
| Patient communication | Call completion rate (within scope) | Pending Q2 2026 external benchmark publication | Measured across scheduled outbound reminder and result-delivery calls |
Current benchmarks reflect pilot-practice data across primary care and a small number of specialties. Sample sizes are adequate for directional claims but not statistically conclusive at the single-diagnosis or single-payer level. We publish larger-sample updates as coverage expands.
Coding accuracy is measured against coder-validated charts (not against AI-generated labels). Prior auth turnaround is measured against clock-time baselines from pilot practices.
Published numbers do not yet include long-term outcome measures (denial reversal rates at 90 days, revenue-cycle impact, patient satisfaction). Those require longer observation windows and are on the roadmap.
We are working with a third-party benchmarking organization to publish independent numbers for coding accuracy and fax classification in Q3 2026. Detailed methodology and dataset descriptions will accompany the publication.
The long-form methodology document (sample composition, metric definitions, confidence intervals where computed, full results by specialty) is available on request under NDA. Email research@maiamed.ai or request during your onboarding conversation.
The long-form document is available under NDA. Email research@maiamed.ai or request during onboarding.
Email research@maiamed.ai