Use Cases

Evidence-gating in practice.

Synthetic clinical vignettes showing what the Pocket Auditor does — and what it refuses to do.

Synthetic example — not real patient data

CKD Staging Gap

Synthetic example — not real patient data

Input

Paciente 67 años, masculino. Assessment: DM2, HTN, CKD. Lab: eGFR 38 mL/min.

What N28 does

Maps documented findings. Identifies CKD is present but staging is unspecified. eGFR of 38 suggests Stage 3b but the physician has not documented the stage in the A/P.

What N28 refuses to do

Does not assume CKD is diabetic without explicit linkage documentation. Does not assign a stage without physician documentation.

Output

“Flags the staging gap. Generates a non-leading physician query: 'The lab data suggests the patient's kidney function may correspond to a specific CKD stage. Would you be able to document the CKD stage in the assessment?'”

Why it matters

Coding unspecified CKD (N18.9) vs. Stage 3b (N18.32) has significant risk adjustment and care management implications. The evidence gate prevents the coder from assuming a stage that the physician has not documented.

Amputation Causality Trap

Synthetic example — not real patient data

Input

Patient 58F. BKA left leg. History of DM2. A/P: diabetes management, wound care.

What N28 does

Recognizes the below-knee amputation and the diabetes diagnosis.

What N28 refuses to do

Does not assume the amputation is diabetic. The documentation does not state the cause of amputation.

Output

“Amputation documented. Cause not specified. If the amputation is due to diabetes, this should be explicitly documented by the physician. Do not infer causality from co-existing conditions.”

Why it matters

A generic LLM would likely assume DM2 + BKA = diabetic amputation. Under audit, that assumption collapses without explicit causal documentation.

Heart Failure Acuity

Synthetic example — not real patient data

Input

Paciente 72F. HF en problem list. Paciente reporta disnea al caminar. No hay descompensación documentada en A/P.

What N28 does

Recognizes heart failure on the problem list and dyspnea symptom.

What N28 refuses to do

Does not infer acute/decompensated HF from dyspnea alone.

Output

“Heart failure is documented. Dyspnea is reported but decompensation is not documented in the A/P. To capture acute HF, the physician must document decompensation. Query: 'Is the patient's heart failure currently in an acute decompensated state?'”

Why it matters

Acute HF captures a higher-weighted HCC than chronic HF. Inferring acuity from symptoms without physician documentation is exactly the pattern federal auditors flag.

Morbid Obesity Documentation

Synthetic example — not real patient data

Input

BMI 42 in vitals. No obesity diagnosis in A/P. Plan says weight management counseling.

What N28 does

Notes the BMI value and the absence of a formal diagnosis.

What N28 refuses to do

Does not code morbid obesity based solely on BMI in vitals.

Output

“BMI of 42 is consistent with morbid obesity, but no diagnosis is documented in the assessment. A BMI value alone is not sufficient for HCC capture. Query: 'Patient's BMI is 42. Would you document a diagnosis of morbid obesity in the assessment if clinically appropriate?'”

Why it matters

Vitals data alone cannot establish a codeable diagnosis under ICD-10-CM guidelines. The physician must document the diagnosis in the assessment.

Depression Severity

Synthetic example — not real patient data

Input

Paciente 55M. Depression en problem list. Toma sertralina 100mg. No PHQ-9. No severity documented.

What N28 does

Identifies depression on problem list and active medication.

What N28 refuses to do

Does not infer major depressive disorder or severity from medication alone. Medication confirms treatment but not diagnosis specificity.

Output

“Depression is documented but severity is not specified. Sertraline confirms active treatment but does not establish whether this is mild, moderate, or major depression. Under V28, only major depressive disorder captures an HCC. Query: 'Can you document the severity of the patient's depression? Is this major depressive disorder?'”

Why it matters

Under V28, only major depressive disorder captures an HCC. The medication alone does not justify the assumption of a specific severity level.

Join the first cohort.

We are onboarding a select group of risk adjustment professionals in Puerto Rico. Request early access to be considered.

Evidence-gated — no guessed codes
V28-native from day one
Built for Puerto Rico's clinical workflow