Case Study: Atrial Fibrillation Ablation Outcomes

This case study demonstrates how to use CDT to build a research cohort for studying stroke and TIA outcomes in patients with atrial fibrillation, comparing those who underwent catheter ablation versus medical management alone.

Research Question

"Is the incidence of stroke or transient ischemic attack (TIA) different between atrial fibrillation patients who underwent pulmonary vein isolation versus those managed medically?"

---

Extraction Strategy

To answer this question, we need to extract three concept types from clinical notes:

Step	Concept Type	Purpose
1. Cohort Selection	Atrial fibrillation	Identify eligible patients
2. Subcohort Assignment	Pulmonary vein isolation / catheter ablation	Divide into PVI vs no-PVI groups
3. Outcome Event	Stroke / TIA	Identify outcome events

---

SNOMED CT Codes

Atrial Fibrillation (Cohort Selection)

SNOMED CT Code	Term
49436004	Atrial fibrillation
282825002	Paroxysmal atrial fibrillation
440028005	Permanent atrial fibrillation
440059007	Persistent atrial fibrillation
706923002	Longstanding persistent atrial fibrillation

Note

This list may not be exhaustive.

Ablation Procedure (Subcohort Assignment)

SNOMED CT Code	Term
18286008	Catheter ablation of tissue of heart
431626004	Endocardial ablation of pulmonary vein using fluoroscopic guidance with contrast
1366473002	Thoracoscopic bilateral video-assisted pulmonary vein isolation with excision of left atrial appendage
1332525002	Cardiac ablation for atrial fibrillation
1363214008	Radiofrequency ablation operation on left atrium for arrhythmia

Note

This list may not be exhaustive.

Outcome Events (TIA / Stroke)

SNOMED CT Code	Term
266257000	Transient ischemic attack
230690007	Cerebrovascular accident
422504002	Ischemic stroke
432504007	Cerebral infarction

Note

This list may not be exhaustive.

---

Example Clinical Notes

Below are three example clinical letters from different patients. In a real study, you would process hundreds or thousands of such notes.

Patient A - AF with ablation, subsequent TIA

Cardiology Follow-up - 15 March 2025

67-year-old male with history of paroxysmal atrial fibrillation diagnosed in
2021, hypertension, and hyperlipidemia. Patient underwent pulmonary vein
isolation via catheter ablation in September 2023. Post-procedure, he remained
in sinus rhythm for 14 months on flecainide.

Presenting today after episode of right-sided weakness and slurred speech
lasting approximately 45 minutes yesterday, now fully resolved. MRI brain
shows no acute infarct. Assessment: Transient ischemic attack, likely
cardioembolic. Recommend resuming anticoagulation with apixaban.

Patient B - AF with ablation, no events

Electrophysiology Clinic - 20 March 2025

54-year-old female with persistent atrial fibrillation, status post catheter
ablation with pulmonary vein isolation in June 2024. She reports no
palpitations or symptoms of arrhythmia recurrence. Holter monitor shows
sinus rhythm throughout. No thromboembolic events.

Impression: Successful ablation outcome. Continue rate control medications.
Discontinue anticoagulation given CHA2DS2-VASc score of 1. Follow-up in
12 months.

Patient C - AF without ablation (medical management)

Cardiology Outpatient Letter - 10 March 2025

71-year-old female with long-standing persistent atrial fibrillation managed
with rate control strategy. Comorbidities include heart failure with preserved
ejection fraction, type 2 diabetes, and chronic kidney disease stage 3.
Patient declined catheter ablation due to procedural concerns.

Currently on metoprolol for rate control and rivaroxaban for stroke
prevention. Remains in atrial fibrillation with controlled ventricular rate.
No history of stroke or TIA. Continue current management.

---

Processing Notes with CDT

Submit each clinical note to the API:

curl -X POST "https://cdt-beta.healthsage.ai/generate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "note": "67-year-old male with history of paroxysmal atrial fibrillation...",
    "specialty": "Cardiology",
    "letter_date": "2025-03-15"
  }'

Response:

{
  "task_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "status": "PENDING"
}

Retrieve results once processing completes:

curl "https://cdt-beta.healthsage.ai/tasks/a1b2c3d4-e5f6-7890-abcd-ef1234567890" \
  -H "X-API-Key: YOUR_API_KEY"

---

Example API Response (Patient A)

{
  "task_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "status": "SUCCESS",
  "letter_date": "2025-03-15",
  "patient_dob": null,
  "json_data": {
    "extractions": [
      {
        "id": "f1a2b3c4-d5e6-7890-abcd-111111111111",
        "snomed_ct_code": "282825002",
        "snomed_ct_term": "Paroxysmal atrial fibrillation (disorder)",
        "concept_type": "disorder",
        "status": "confirmed",
        "date": "2021",
        "source": "paroxysmal atrial fibrillation diagnosed in 2021"
      },
      {
        "id": "f1a2b3c4-d5e6-7890-abcd-222222222222",
        "snomed_ct_code": "38341003",
        "snomed_ct_term": "Hypertensive disorder (disorder)",
        "concept_type": "disorder",
        "status": "confirmed",
        "source": "hypertension"
      },
      {
        "id": "f1a2b3c4-d5e6-7890-abcd-333333333333",
        "snomed_ct_code": "55822004",
        "snomed_ct_term": "Hyperlipidemia (disorder)",
        "concept_type": "disorder",
        "status": "confirmed",
        "source": "hyperlipidemia"
      },
      {
        "id": "f1a2b3c4-d5e6-7890-abcd-444444444444",
        "snomed_ct_code": "18286008",
        "snomed_ct_term": "Catheter ablation of heart (procedure)",
        "concept_type": "procedure",
        "status": "confirmed",
        "date": "2023-09",
        "source": "catheter ablation in September 2023"
      },
      {
        "id": "f1a2b3c4-d5e6-7890-abcd-555555555555",
        "snomed_ct_code": "266257000",
        "snomed_ct_term": "Transient ischemic attack (disorder)",
        "concept_type": "disorder",
        "status": "confirmed",
        "date": "2025-03",
        "source": "Transient ischemic attack"
      }
    ],
    "specialty": "Cardiology",
    "snomed_ct_version": "2026-01-01"
  }
}

---

Building the Research Dataset

After processing all clinical notes, aggregate the extracted concepts into a structured dataset:

Patient	Has AF	Subcohort	PVI Date	Has TIA/Stroke	Event Date	Time to Event
A	Yes	PVI	2023-09	Yes	2025-03	18 months
B	Yes	PVI	2024-06	No	-	-
C	Yes	No PVI	-	No	-	-

---

Processing API Responses

Extract relevant concepts from each API response:

# SNOMED CT codes for our study
AF_CODES = [
    "49436004",   # Atrial fibrillation
    "282825002",  # Paroxysmal atrial fibrillation
    "440028005",  # Permanent atrial fibrillation
    "440059007",  # Persistent atrial fibrillation
    "706923002",  # Longstanding persistent atrial fibrillation
]

ABLATION_CODES = [
    "18286008",    # Catheter ablation of tissue of heart
    "431626004",   # Endocardial ablation of pulmonary vein
    "1366473002",  # Thoracoscopic bilateral video-assisted PVI
    "1332525002",  # Cardiac ablation for atrial fibrillation
    "1363214008",  # Radiofrequency ablation on left atrium
]

OUTCOME_CODES = [
    "266257000",  # Transient ischemic attack
    "230690007",  # Cerebrovascular accident
    "422504002",  # Ischemic stroke
    "432504007",  # Cerebral infarction
]

def process_patient_response(response: dict) -> dict:
    """Extract study-relevant data from a CDT API response."""
    extractions = response["json_data"]["extractions"]

    # Check for AF diagnosis (cohort inclusion)
    has_af = any(
        e["snomed_ct_code"] in AF_CODES
        for e in extractions
    )

    # Find ablation procedure and date (subcohort assignment)
    ablation = next(
        (e for e in extractions if e["snomed_ct_code"] in ABLATION_CODES),
        None
    )

    # Check for TIA or stroke outcome
    outcome = next(
        (e for e in extractions if e["snomed_ct_code"] in OUTCOME_CODES),
        None
    )

    return {
        "has_af": has_af,
        "has_pvi": ablation is not None,
        "pvi_date": ablation["date"] if ablation else None,
        "has_outcome": outcome is not None,
        "outcome_date": outcome["date"] if outcome else None
    }

---

Filtering Logic

After aggregating all patient data, apply filters to identify study cohorts:

import pandas as pd

# Load aggregated results
df = pd.read_csv("cdt_extraction_results.csv")

# Filter 1: Include only patients with confirmed AF (study cohort)
af_cohort = df[df["has_af"] == True]

# Filter 2: Divide into PVI vs no-PVI subcohorts
pvi_group = af_cohort[af_cohort["has_pvi"] == True]
no_pvi_group = af_cohort[af_cohort["has_pvi"] == False]

# Filter 3: Identify outcome events in each subcohort
pvi_with_event = pvi_group[pvi_group["has_outcome"] == True]
no_pvi_with_event = no_pvi_group[no_pvi_group["has_outcome"] == True]

# Calculate and compare event rates
pvi_rate = len(pvi_with_event) / len(pvi_group) * 100 if len(pvi_group) > 0 else 0
no_pvi_rate = len(no_pvi_with_event) / len(no_pvi_group) * 100 if len(no_pvi_group) > 0 else 0

print(f"PVI Group: {len(pvi_group)} patients")
print(f"  - TIA/Stroke events: {len(pvi_with_event)} ({pvi_rate:.1f}%)")
print(f"No PVI Group: {len(no_pvi_group)} patients")
print(f"  - TIA/Stroke events: {len(no_pvi_with_event)} ({no_pvi_rate:.1f}%)")

---

Study Cohort Summary

Cohort	Description	Filter Criteria
AF Cohort	All patients with atrial fibrillation	has_af
PVI Subcohort	AF patients who underwent PVI/ablation	has_af AND has_pvi
No PVI Subcohort	AF patients without PVI (medical management)	has_af AND NOT has_pvi
PVI + Outcome	PVI patients with TIA/stroke	has_af AND has_pvi AND has_outcome
No PVI + Outcome	Medical management patients with TIA/stroke	has_af AND NOT has_pvi AND has_outcome

These cohorts can be used to calculate incidence rates, time-to-event analyses, and compare outcomes between treatment and control groups.