Loading…
Loading…
ARKA Clinical Decision Support is designed to meet all four criteria for Non-Device CDS under FD&C Act §520(o)(1)(E) and FDA's January 2026 final guidance on Clinical Decision Support Software. Recommendations support, not replace, the clinician's judgment. Every recommendation is anchored in a published guideline or peer-reviewed source, with the basis available for independent review. INS emphasizes prior authorization, coverage, and cost transparency workflows.
This recommendation is intended to support, not replace, clinical judgment. It is generated by ARKA, software designed to meet the four criteria for Non-Device Clinical Decision Support under FD&C Act §520(o)(1)(E) and FDA's final guidance on Clinical Decision Support Software (January 2026). The clinician is responsible for the final decision.
Gold card
Qualification file
Identity, window, exclusion cascade, Wilson bound, sourced threshold, determination. The plan decides.
Every other product in this space helps you win an authorisation you should not have needed. This one proves you should never have been asked.
A qualification file is one clinician × one service: a document a plan or a regulator can verify without ARKA and without the underlying claims. It states its inputs, its method, its uncertainty, and a hash that proves it has not been edited. ARKA computes qualification against a stated threshold. The plan decides whether to grant an exemption.
Identity (NPI, clinician, specialty, organisation, service). The evaluation window, stated explicitly because it is a contested parameter. The exclusion cascade — why most decisions are not in the rate. The raw approval rate beside the Wilson lower bound. The threshold, sourced as statute, plan policy, or ARKA default. The determination: qualified, not-qualified, or insufficient-history. A notice that this file does not grant an exemption.
A raw nine-for-nine looks like a perfect approval rate, but nine good decisions is too small a sample to certify anyone. The Wilson lower bound is the conservative figure we print: it shrinks toward one-half as the sample thins, so a clinician close to the bar qualifies later rather than never.
Demo group, fully-insured Texas window. Rates below are computed by the qualification engine. The portfolio is illustrative; the arithmetic is not typed.
| Clinician | Service | n | Raw approval rate / Wilson lower bound | Threshold | Determination |
|---|---|---|---|---|---|
| Jordan Hale, MD | 72148MRI lumbar spine without contrast | 50 | 96.0% / 86.5%Measured | 90.0% (statute) | qualified |
| Jordan Hale, MD | 74177CT abdomen and pelvis with contrast | 36 | 80.6% / 65.0%Measured | 90.0% (statute) | not-qualified |
These clinicians are not in the not-qualified column. Qualification has not been assessed. The remaining count is how many completed decisions are still needed.
Sam Okonkwo, MD 70553
9 eligible decisions on file. 11 more needed before qualification can be assessed.
Download a one-page qualification file for the first qualified clinician × service in the demo portfolio. No form. The giveaway is the strategy.
This recommendation is intended to support, not replace, clinical judgment. It is generated by ARKA, software designed to meet the four criteria for Non-Device Clinical Decision Support under FD&C Act §520(o)(1)(E) and FDA's final guidance on Clinical Decision Support Software (January 2026). The clinician is responsible for the final decision.
All patients, orders, and outcomes on this page are synthetic (ARKA-DEMO-001); no real patient data.
ARKA Clinical Decision Support is designed to meet all four criteria for Non-Device CDS under FD&C Act §520(o)(1)(E) and FDA's January 2026 final guidance on Clinical Decision Support Software. Recommendations support, not replace, the clinician's judgment. Every recommendation is anchored in a published guideline or peer-reviewed source, with the basis available for independent review. INS emphasizes prior authorization, coverage, and cost transparency workflows.
This recommendation is intended to support, not replace, clinical judgment. It is generated by ARKA, software designed to meet the four criteria for Non-Device Clinical Decision Support under FD&C Act §520(o)(1)(E) and FDA's final guidance on Clinical Decision Support Software (January 2026). The clinician is responsible for the final decision.
Gold card
Qualification file
Identity, window, exclusion cascade, Wilson bound, sourced threshold, determination. The plan decides.
Every other product in this space helps you win an authorisation you should not have needed. This one proves you should never have been asked.
A qualification file is one clinician × one service: a document a plan or a regulator can verify without ARKA and without the underlying claims. It states its inputs, its method, its uncertainty, and a hash that proves it has not been edited. ARKA computes qualification against a stated threshold. The plan decides whether to grant an exemption.
Identity (NPI, clinician, specialty, organisation, service). The evaluation window, stated explicitly because it is a contested parameter. The exclusion cascade — why most decisions are not in the rate. The raw approval rate beside the Wilson lower bound. The threshold, sourced as statute, plan policy, or ARKA default. The determination: qualified, not-qualified, or insufficient-history. A notice that this file does not grant an exemption.
A raw nine-for-nine looks like a perfect approval rate, but nine good decisions is too small a sample to certify anyone. The Wilson lower bound is the conservative figure we print: it shrinks toward one-half as the sample thins, so a clinician close to the bar qualifies later rather than never.
Demo group, fully-insured Texas window. Rates below are computed by the qualification engine. The portfolio is illustrative; the arithmetic is not typed.
| Clinician | Service | n | Raw approval rate / Wilson lower bound | Threshold | Determination |
|---|---|---|---|---|---|
| Jordan Hale, MD | 72148MRI lumbar spine without contrast | 50 | 96.0% / 86.5%Measured | 90.0% (statute) | qualified |
| Jordan Hale, MD | 74177CT abdomen and pelvis with contrast | 36 | 80.6% / 65.0%Measured | 90.0% (statute) | not-qualified |
These clinicians are not in the not-qualified column. Qualification has not been assessed. The remaining count is how many completed decisions are still needed.
Sam Okonkwo, MD 70553
9 eligible decisions on file. 11 more needed before qualification can be assessed.
Download a one-page qualification file for the first qualified clinician × service in the demo portfolio. No form. The giveaway is the strategy.
This recommendation is intended to support, not replace, clinical judgment. It is generated by ARKA, software designed to meet the four criteria for Non-Device Clinical Decision Support under FD&C Act §520(o)(1)(E) and FDA's final guidance on Clinical Decision Support Software (January 2026). The clinician is responsible for the final decision.
All patients, orders, and outcomes on this page are synthetic (ARKA-DEMO-001); no real patient data.