Lumbar MRI · Borderline deny · Incomplete conservative trial

Concept demo data

Concept demo data — illustrates the audicta.pa.v1 schema. Live pipeline-generated records replace these as the authorized invocation queue produces them.

DENYmanual_concept_democeo_flag · human review

borderline deny

Lumbar MRI · Borderline deny · Incomplete conservative trial

What this proves: When criteria miss, the record cites why AND what to do instead — denial paired with a covered alternative pathway (LCD §D). The system flags its own borderline cases for human review via ceo_flag.

record_id: rec_2026-04-25T14-31-44Z_b8c5d22a
decided_at: 2026-04-25T14:31:44.708Z

Case

Patient ref: Patient/synthea-9b2f-771
Imaging request: MRI Lumbar Spine without contrast (CPT 72148)
Chief complaint: Low back pain, 3 weeks duration, post-lifting injury
Red flags documented: (none)
Exam findings: no_radicular_symptoms, slr_negative, no_motor_deficit, no_bladder_bowel_dysfunction

Agent chain

Clinical reviewer

confidence: 0.78

What

Identified absence of red flags and inadequately documented conservative trial; case fits LCD standard pathway, prerequisites not met.

Why

Patient presents with 3-week mechanical low back pain following a lifting injury — no radicular symptoms (no leg pain, SLR negative), no motor deficit, no bladder/bowel involvement, no constitutional symptoms. This is the prototypical uncomplicated acute LBP that ACR AC variant 1 covers. Conservative trial documentation is incomplete however — chart shows 1 week PT with 2 of 6 prescribed sessions attended, plus NSAIDs with subjective 'some improvement' but no quantified outcome metric. The combination of (a) no red flags and (b) inadequate conservative trial places this case in LCD L34220's standard pathway, where the 4-week-wait + adequate-management prerequisites must both be met before imaging is covered.

Tradeoff

Recommend complete trial: defensible per LCD / patient endures 3–4 more weeks symptomatic. Approve now: faster diagnostic certainty / contradicts coverage policy and incentivizes premature imaging.

Scope check

I am assessing red-flag presence and conservative-trial adequacy against documented criteria. I am NOT making treatment recommendations or judging the patient's pain experience.

Alternatives considered (3)

Trigger red-flag-bypass pathway despite no documented red flags

Pattern is uncomplicated mechanical LBP; no neuro deficit, no constitutional symptoms — bypass criteria definitionally not met

Treat 'some improvement' on NSAIDs as adequate response

LCD §B.1.a defines adequacy as 'no clinically meaningful improvement' — patient self-report of 'some' does not reach that bar, and PT compliance gap remains separately unaddressed

Defer all conclusions, request clarifying clinical note

Chart documentation is sufficient for adequacy assessment; further clarification does not change the core gap (compliance + duration)

Flagged uncertainties (2)

PT compliance at 2/6 sessions — chart doesn't document patient-reported reason for missed sessions; assumption that this represents inadequate adherence rather than clinically-justified avoidance

NSAIDs subjective 'some improvement' — not quantified by VAS, ODI, or similar; adequacy judgment relies on language interpretation of the chart note

Citations (2)

CMS_LCD_L34220 · Coverage Indications.B.1

sha256:kb-lcd-l34220-sec-b1-c3a82e

ACR_AC_Low_Back_Pain · variant_1 · MRI lumbar without contrast · rating 1/9

sha256:kb-acr-lbp-v1-row-mri-noctrt-7d2e91

Criteria mapper

confidence: 0.72

What: Mapped to LCD L34220 §B.1 standard pathway: prerequisites not met. Cited covered alternative service per LCD §D — supervised PT extension to 4–6 weeks, then re-evaluation.
Why: LCD L34220 §Coverage Indications.B.1 (standard pathway) requires both (1) >=4 weeks of documented conservative management AND (2) inadequate response to that management. Neither prerequisite is met: total documented conservative duration is 3 weeks, and PT compliance at 2/6 sessions does not reach the LCD §B.1.a 'adequate trial' definition; NSAIDs outcome 'some improvement' is positive directional, not 'failed' as the prerequisite specifies. The red-flag-bypass pathway (§B.2) is not applicable per the clinical_reviewer chain. The covered alternative service per LCD §Coverage Indications.D is supervised PT extension to 4–6 weeks with documented compliance, then re-evaluation — this is the pathway the record cites alongside the denial.
Tradeoff: Cite LCD §D alternative explicitly: defensible deny + constructive next step / requires patient to endure additional conservative trial. Bare deny without alternative: faster decision / fails LCD §D citation requirement and undermines audit defensibility.
Scope check: I am mapping documented findings to LCD criteria rows and citing the LCD-specified alternative pathway. I am NOT recommending specific PT protocols or making the final denial decision.
Alternatives considered (3): Map to LCD §B.2 red-flag bypass
Clinical_reviewer chain confirms no red flags — pathway prerequisite definitionally not met
Treat 5-week duration as meeting 4-week prerequisite standalone
LCD §B.1 requires duration AND adequate trial conjunctively, not disjunctively; partial fulfillment does not satisfy the conjunction
Map to LCD §B.4 EMG-correlation pathway
No neurologic findings documented; pathway prerequisites (positive EMG or persistent radicular sx) not present
Flagged uncertainties (1): LCD §B.1.a 'adequate trial' definition uses 'no clinically meaningful improvement' — applying this to 'some improvement' chart text is a textual-pattern judgment, not a quantitative match
Citations (2): CMS_LCD_L34220 · Coverage Indications.B.1
sha256:kb-lcd-l34220-sec-b1-c3a82e
CMS_LCD_L34220 · Coverage Indications.D
sha256:kb-lcd-l34220-sec-d-f8e2c4

Evidence retriever

confidence: 0.85

What: Retrieved ACR Appropriateness Criteria evidence: LBP variant 1 (uncomplicated, <6 weeks), MRI lumbar without contrast rated 1/9 (Usually Not Appropriate).
Why: ACR AC LBP variant 1 — 'acute or subacute, uncomplicated, less than 6 weeks duration, no red flags' — is the direct fit for this case. Variant 1 rates MRI lumbar without contrast at 1/9, the lowest 'Usually Not Appropriate' band. This rating reflects decades of evidence that early imaging in uncomplicated LBP increases utilization without changing clinical outcomes — the evidence base that justifies the LCD's wait-and-trial pathway. ACR AC also publishes variant 1's preferred pathway: structured conservative management with re-evaluation at 4–6 weeks, which is what the decision record recommends as the alternative covered service.
Tradeoff: Variant 1 evidence: directly applicable / negative recommendation may feel adversarial to patient. Multi-variant analysis: more robust / overstates evidence depth needed for this clear classification.
Scope check: I am retrieving and citing published evidence rows. I am NOT interpreting evidence ratings or recommending the alternative pathway specifics.
Alternatives considered (3): ACR AC LBP variant 2 (subacute >6 weeks)
Case is at 3 weeks, well under 6-week threshold defining variant 2
ACR AC LBP variant 4 (with red flags)
Clinical_reviewer chain confirms no red flags — variant prerequisite not met
ACR AC LBP variant 6 (post-trauma)
Lifting injury is mechanical strain, not trauma per ACR variant 6 definition (which requires >=6/10 force injury or fall)
Flagged uncertainties (1): ACR AC LBP variant 1 published 2018 (last revision); LCD L34220 references ACR AC generally — version-specificity of the citation linkage relies on LCD's own non-versioned reference, no explicit version pinning
Citations (1): ACR_AC_Low_Back_Pain · variant_1 · MRI lumbar without contrast · rating 1/9
sha256:kb-acr-lbp-v1-row-mri-noctrt-7d2e91

Decision

DENYby clinical_reviewer → criteria_mapper → evidence_retriever

LCD L34220 §B.1 prerequisites unmet (duration + adequate trial); ACR AC LBP variant 1 rating 1/9. Covered alternative cited: LCD §D supervised PT extension to 4–6 weeks with re-evaluation.

Covered alternative pathway

Supervised PT extension to 4–6 weeks with documented compliance, then re-evaluation

CMS_LCD_L34220 §Coverage Indications.D

Evaluation

Evaluator function received only this record; case data, agent code, and KB content are not in the evaluator's input scope (compile-time enforced — see /architecture).

Dimension	Local	Cloud	Final	Divergence
Scope awareness	3.0	3.0	3.0	0.0
Alternative evaluation	3.0	4.0	4.0	1.0
Tradeoff clarity	3.0	3.5	3.5	0.5
Goal alignment	3.5	3.0	3.5	0.5
Uncertainty flagging	3.5	4.0	4.0	0.5
Decision chain	3.0	3.0	3.0	0.0

Max divergence

1.00

Avg divergence

0.42

CEO flag — human review

Strict threshold exceeded

CEO flag reason

max_dimension_divergence (1.0 on alternative_evaluation) exceeds strict threshold (0.7); record routed to human review per Audicta evaluator protocol §7.1.

Borderline case — alternative_evaluation diverges by 1.0 between evaluators (local 3.0, cloud 4.0), passing the lenient ≤1.0 bound but exceeding the strict ≤0.7 threshold. The system flags itself for human review via ceo_flag while still emitting a convergent verdict. Both evaluators agree on the DENY outcome; the disagreement is on rigor grading of the alternative-pathway reasoning, not on the decision.

Local evaluator: qwen2.5-coder:7b · Cloud evaluator: claude-sonnet-4-20250514

Integrity

Content integrity

Compute the SHA-256 of this record (excluding content_hash itself) in your browser and compare to the stored hash.

Stored: sha256:1cdb7e3c9fc2c4ce3928d849e8703103a48b517adc9a470eb266e87c797ddcd3

Provenance

kb_snapshot_hash: sha256:kb-snap-2026-04-25-a1b2c3
agent_genome_hash: sha256:genome-healthcare-imaging-v0.4-91e3d7
audicta_version: 0.4.0-drydraft
reproducible_with: docker pull audicta/healthcare-imaging:0.4.0-drydraft