Limitations & Guardrails in Consult
- What Consult Is Designed For
- Response Accuracy
- Real-World Data Caveats
- Patient Privacy Guardrails
- How to Flag an Inaccurate Response
- Important to Remember
- Related Articles
Know what Consult can and cannot do before you rely on a response in practice. This page covers its intended use, how to verify accuracy, the limits of real-world data, the privacy standards that apply, and how to flag a response that looks wrong.
What Consult Is Designed For
Consult answers clinical questions with evidence-grounded responses that inform your judgment. Use it as a reference tool to retrieve and synthesize peer-reviewed literature and real-world data relevant to a clinical question, during a patient encounter or clinical inquiry.
Consult is not designed to:
- Substitute for clinical judgment, formal diagnosis, or treatment decisions
- Serve as a source of legally binding clinical documentation
- Replace specialist consultation or collegial clinical discussion
- Provide current clinical information or current drug shortage data
- Answer queries about patient data and other PHI
Every Consult response supports your own assessment. It does not replace it.
Response Accuracy
This disclosure appears at the bottom of Consult responses: "By Jiro AI; there could be mistakes. Learn more." Select the underlined link to view the full disclosure.
Verify clinical details, including medication doses, diagnostic criteria, and evidence quality, against primary sources before applying them to patient care. Accuracy improvements are ongoing, and your feedback directly informs that process.
Real-World Data Caveats
When a response includes real-world data, such as prescribing rates, utilization patterns, or peer comparisons, three limitations can affect what you see.
- Data coverage. The depth of your personalization depends on the volume of claims associated with your NPI. When coverage is limited, Jiro uses specialty-level or location-level data instead of NPI-level data.
- Cohort suppression. In accordance with CMS policy, Jiro never displays patient cohort counts between 1 and 10. When suppression applies, the affected data point is left out of the response without an indication.
- Claims lag. Graphs reflect processed and attributed claims. Recent clinical activity may not yet appear in the data behind a response.
Patient Privacy Guardrails
Patient anonymity standards apply to all real-world data in Consult responses. Jiro does not use individual patient-level data in ways that could permit re-identification. These standards align with applicable HIPAA requirements for de-identification and small population reporting.
How to Flag an Inaccurate Response
Each Consult response includes thumbs-up and thumbs-down controls. To report a concern:
- Select the thumbs-down icon below the response.
- Select the category that best describes the issue: Poor literature selection, Inaccurate information, Misrepresents research, Response style, Did not understand question, Technical error, or Other.
- Add an optional written comment and submit.
The Jiro clinical team reviews feedback and uses it to improve response quality. For detailed guidance, see How Consult Works.
Important to Remember
- Verify clinical details, including medication doses and diagnostic criteria, against primary sources before applying them to patient care.
- Jiro never displays patient cohort counts between 1 and 10, and the affected data point is left out of the response without an indication.
- Recent clinical activity may not yet appear in the data behind a response, because graphs reflect only processed and attributed claims.