Industry field guide
Podiatry site diagram and follow-up linkage data for AI
A follow-up note can use a short location label that is easy to confuse across diagrams.
- 2022 NAICS
- 621391
- Practice pack
- Example and answer key (JSON)
- Updated
What this guide tests
Which annotation matches F1, and how should F2's side conflict and the E2 diagram be handled?
See the specimen and fields · Work through the fictional records
Task and source context
A follow-up note can use a short location label that is easy to confuse across diagrams. CMS publishes podiatry documentation resources for providers. A podiatry practice can use simple original drawings to test location matching without sharing clinical photographs. CMS podiatry care documentation guidance
Make two fictional foot outlines with numbered regions. Attach a mock follow-up to one side and add a second record with the same number and a conflicting side label. Ask which annotation matches and what a reviewer needs to check. Score region, laterality and encounter separately.
Exclude actual foot photographs, charts, patient identifiers and treatment instructions. Use independently authored materials and qualified review of the fictional evidence.
Industry research
The U.S. Census Bureau’s industry definitions establish which activities these codes cover. The workflow sources in this guide describe the task or record type. Fiund’s pilot below uses fictional material to test a specific decision within that scope.
621391 · Offices of Podiatrists
This U.S. industry comprises establishments of health practitioners having the degree of D.P.M. (Doctor of Podiatric Medicine) primarily engaged in the independent practice of podiatry. These practitioners diagnose and treat diseases and deformities of the foot and operate private or group practices in their own offices (e.g., centers, clinics) or in the facilities of others, such as hospitals or HMO medical centers.
Build a pilot sample
Set up this pilot
Make fictional foot diagrams with two encounter IDs and a conflicting side marker. Link one numbered region to the correct follow-up and route the other for correction.
Prepare the test packets
- Start with the worked case. Use the fictional record types below as a guide to the source files you need. Give each packet a stable ID and save its source versions with it.
- Change one fact. Make one packet with enough evidence to answer the question and one where the evidence points to a different answer. Keep the other fields fixed so a reviewer can tell what changed.
- Remove the decisive evidence. Give the reviewer a third packet with a plausible near-match in its place. Have them write what can still be established and what evidence would resolve the rest.
Fields the reviewer needs
- Encounter and diagram ID
- Defines the source.
- Side and numbered region
- Disambiguates repeated local labels.
- Follow-up target and conflict status
- Supports the exact association.
Use What health care and social services teams can contribute to AI to turn the specimen into a brief with a defined task, source and review owner.
Fictional exercise
A numbered region needs side and encounter before a follow-up can be matched
Two original generic foot outlines use numbered abstract regions. They contain no clinical photographs, real observations, patient information or treatment instructions.
| Record ID | Source | What it records |
|---|---|---|
| PD1 | Diagram map | Encounter E1: LEFT region 2 marked A; RIGHT region 2 marked B. Distinct original diagram references DL and DR. |
| PD2 | Mock follow-up F1 | Explicitly names E1/LEFT/region 2 and diagram DL. Administrative label REVIEWED, no medical finding. |
| PD3 | Conflicting F2 | Header says E1/RIGHT/region 2; attached diagram label says LEFT/region 2. No reviewed reconciliation; another E2 diagram also uses region 2. |
Question for the model. Which annotation matches F1, and how should F2's side conflict and the E2 diagram be handled?
Show the reference answer
PD1 and PD2 match F1 to E1's LEFT region two, annotation A on DL. PD3 conflicts between RIGHT in its header and LEFT on the attached diagram, so it needs source reconciliation rather than a forced match. E2's repeated region number belongs to another encounter and cannot resolve it. Preserve side, encounter and region together without interpreting a clinical condition from the invented labels.
How to check the result
Ask for the answer, the record IDs that support it and any fact the evidence leaves unresolved. Have a reviewer compare the response against the reference before deciding whether the sample is ready to expand.
Errors to flag in this case
- Matching region number while ignoring laterality or encounter.
- Choosing one conflicting side label without authorized evidence.
Change the inputs and run it again
Add a reviewed correction changing F2's header to LEFT but referencing E2. Require the remaining encounter mismatch to stay open.
Score the decision and the evidence separately
Save the reviewer’s expected answer, supporting record IDs and unresolved fields in a separate answer key. Score the model on the decision, its citations and its handling of the deliberate gap. A correct answer citing a different case counts as an evidence error.
Before expanding collection, have a second reviewer run the same checks on the held-out packet. Keep related versions, views and exports of the same case together so they stay on one side of the training and evaluation split.
Check permission and scope
Use independently drawn outlines and qualified review of the fictional key. Exclude real images, charts and patient identifiers.
Use no patient data or actual care footage in a practice package. Handle real clinical data through a separate authorized governance path.
Describe an authorized archive through Fiund’s existing-data assessment, or describe a new capture capability through the collection brief. The contributor agreement covers the terms for participation.
Sources and further reading
Resources for this workflow
Includes worksheet
What health care and social services teams can contribute to AI
Separate a staff training simulation from a governed clinical or care-data project.
Includes worksheet
Build an AI evaluation sample for service handoffs
Use fictional records to test whether a handoff reached a documented state.
Company and program reviews
Use these reviews to compare sourcing, capture or evaluation approaches. Confirm the applicable program, accepted sources and terms with the provider.
Compare the approach
Protege review for AI teams and data owners
Compare the company’s healthcare data-provider pathway separately from a fictional staff workflow.
Compare the approach
Sapien review: dataset quality review and expert checks
Compare an independent quality review process for an administrative or nonclinical evaluation.
Related industry examples
Industry guide · NAICS 621320
Optometry image laterality and exam linkage data for AI
An optometry exam can contain measurements and images from both eyes.
Industry guide · NAICS 621310
Chiropractic visit and exam documentation data for AI
A template can carry an observation from an earlier visit into a later draft.
Industry guide · NAICS 621399
Dietitian food log and serving-basis records for AI
A food log can list an amount per package while a label lists a value per serving.