j& d Z ddlmZ ddlZddlZddlZddlmZ ddlZddl m
Z
ddl m Z ddl
m
Z
d Zd
Z G d d e Z G d
de ZddZddZd Zy)a Quick-read v3: two-pass approach + Anthropic extended thinking.
Pass 1: forced per-lead ST/T enumeration with thinking enabled. The model
builds an unbiased catalog of every visible finding before naming
any diagnosis.
Pass 2: synthesis. Sees the original image + pass-1 output, produces the
formal reading. Thinking enabled.
Total time ~60-150s. Designed to be invoked from a background worker, not
synchronously from an HTTP-edge-timeout-bounded request.
) annotationsN)Path)
HTTPException) BaseModel )configu You are an expert cardiac electrophysiologist examining a 12-lead ECG.
DO NOT yet attempt to diagnose. Your only job in this pass is to systematically catalog every visible finding so a synthesis step later can interpret them.
For EACH of the 13 leads visible (I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, V6, and the rhythm strip — typically lead II at the bottom), describe what you see in plain language:
1. **P wave** — present? visible morphology? upright/inverted?
2. **PR interval** — short/normal/long?
3. **QRS** — narrow/wide? notching? deep S? tall R? Q wave presence + width + depth (Q ≥40 ms wide or ≥25% R height = pathologic)?
4. **ST segment** — elevation (mm), depression (mm), morphology (concave/convex/flat/downsloping/upsloping), or isoelectric?
5. **T wave** — upright, flat, inverted, biphasic, hyperacute (tall + symmetric)?
6. **Rhythm strip features** — regularity, P-QRS relationship, any ectopy?
Also note overall:
- Heart rate (count R-R intervals in the rhythm strip)
- QRS axis (estimate quadrant from leads I and aVF)
- Image quality issues (rotation, low contrast, partial obstruction)
Format as a structured per-lead table or bulleted list. Be quantitative whenever possible (mm for ST shifts, ms for intervals).
Do NOT name a diagnosis. Do NOT use the words "STEMI", "NSTEMI", "MI", "ischemia" yet — those are interpretive labels for the synthesis pass.
Output plain markdown, no JSON, no code fences. End with: "---END PASS 1---" on its own line.u You are an expert cardiac electrophysiologist. You previously examined a 12-lead ECG and produced this objective per-lead catalog:
═══════════════════════════════════════════════════════════════════
PASS 1 OUTPUT (your prior cataloging step)
═══════════════════════════════════════════════════════════════════
{pass1_text}
═══════════════════════════════════════════════════════════════════
END PASS 1 OUTPUT
═══════════════════════════════════════════════════════════════════
Now look at the ECG image again WITH the pass-1 catalog in mind and produce the formal reading.
Required structure (plain markdown, no JSON, no code fences):
**Diagnosis** — ONE sentence. If STEMI/OMI criteria are met anywhere, lead with that explicitly and name the territory. Otherwise state the dominant clinical pattern.
**Rate** — bpm.
**Rhythm** — primary rhythm + regularity.
**Axis** — quadrant + estimated degrees.
**Intervals** — PR / QRS / QT(c) in ms.
**ST/T summary table** — Group by territory (inferior, lateral, anteroseptal, anterior, lateral precordial, posterior). For each: what was elevated, depressed, or otherwise abnormal, with mm where measurable.
**Reciprocal changes** — Explicitly check every ST elevation against its anatomical opposite. State yes/no per pairing.
**Q waves** — Pathologic? Which leads? Significance?
**Final synthesis** — 2-3 sentences integrating the findings into a clinical picture.
**Why — three teaching pearls** — each pearl must reference specific leads or features from your pass-1 catalog and explain the reasoning chain.
CRITICAL:
- Use the pass-1 catalog as your evidence base. Do not invent findings not present in pass 1.
- If ST elevation in any territory was noted in pass 1, you MUST address whether it meets STEMI/OMI criteria (and check for reciprocal changes).
- If pass 1 noted "no ST elevation anywhere", confidently call this non-ischemic.
- Do NOT default to "nonspecific ST-T changes" — name a pattern.c e Zd ZU ded< y)QuickReadRequeststr image_urlN__name__
__module__ __qualname____annotations__ B/var/www/adampowell.pro/apps/ekg-tutor/interpret/src/quick_read.pyr
r
_ s Nr r
c , e Zd ZU ded< ded< ded< y)QuickReadResponser markdownint
elapsed_msmodelNr
r r r r r c s MO Jr r c f | j d rt | dd }n+| j d r t | }nt d| |j st t | |j j }dddddj |d }|j |fS ) Nzfile:// /z unsupported image_url scheme: z image/pngz
image/jpegz
image/webp)z.pngz.jpgz.jpegz.webp)
startswithr
ValueErrorexistsFileNotFoundErrorr suffixlowerget
read_bytes)r pathext
media_types r _read_image_bytesr) i s I&IabM" c "I9)EFF ;;= D **
++
C
c#{ ?? j ((r c g }| j D ]. }t |dd dk( s|j |j 0 dj | j S )zMConcatenate text blocks from an Anthropic response, skipping thinking blocks.typeNtext )contentgetattrappendr, joinstrip)responsepartsblocks r
_extract_textr6 | sQ E!! 5&$ '6 1 LL $ " 775> !!r c @ | j dt dd }y )Nz/v1/quick-read)response_modelc t j s
t dd | j }|j d r:t
j j t j |t d d } t | \ }}t j | j! d }d d
||d d }t# j$ t j d
}t
j& j) dd }t+ t
j& j) dd } d| d}
t- j. } |j0 j3 |dd|
d|dt4 dgdg } t9 | }
|
s
t d d t: j= |
} |j0 j3 |d d|
d|d|dgdg }t9 | }|s
t d d" |d#z d$z |
j? d%d& jA z d'z }t+ t- j. | z
d(z }tC |||jD ) S # t $ r}t dd| d }~wt $ r}t dt | d }~ww xY w# t" j6 $ r}t d d | d }~ww xY w# t" j6 $ r}t d d!| d }~ww xY w)*Ni z ANTHROPIC_API_KEY not configured) status_codedetailz /uploads/i zimage not found: i asciiimagebase64)r+ r( data)r+ sourcei, )api_keytimeoutEKG_TUTOR_INTERPRET_MODELzclaude-sonnet-4-6#EKG_TUTOR_INTERPRET_THINKING_BUDGET4000enabled)r+
budget_tokensi g ?userr, )r+ r, )roler. )r
max_tokens temperaturethinkingmessagesi zanthropic pass-1 error: zempty pass-1 response)
pass1_texti zanthropic pass-2 error: zempty pass-2 responsez
---
zFShow per-lead analysis (pass 1)
z---END PASS 1---r- z