Leadless Pacemaker
End-of-Service (EOS)
6-Minute Walk Test

Question & Answer

Artificial Intelligence Doctor

Question

During a 6MWT performed at low battery status, what is the incidence of exertional non-capture or intermittent capture (verified by ambulatory ECG/EGM) and does the burden of capture failure correlate with shorter 6MWD, greater HR variability, higher NT-proBNP the next day, or post-test symptoms?

Answer (Prospective Monitoring Protocol & Analysis Plan)

TL;DR

Implement simultaneous 6MWT + ambulatory ECG/EGM logging near EOS to quantify exertional capture failure (ECF). Express ECF as % paced beats without capture and/or episodes per minute. Expect that higher ECF burden associates with shorter 6MWD, more erratic minute-to-minute HR, elevated next-day NT-proBNP, and more symptoms. Use adjusted models and event-level analyses to test these relationships.

1) Verification & Definitions

Non-capture (beat-level)

  • Pacing artifact present with no ensuing paced QRS (or morphology inconsistent with capture) within vendor-specific capture window.
  • EGM markers: pace delivered (Vp), no capture confirmation if available.

Intermittent capture (episode-level)

  • ≥3 consecutive non-captured paced beats or ≥5 non-captured beats within 10 s during walking.
  • Flag episodes with start/stop timestamps to align with HR/SpO2 traces.

ECF Burden

Beat-level: non-captured paced beats / total paced beats (%)
Episode-level: episodes per minute; total duration (s)

2) Data Collection (same day unless noted)

3) HR Variability (operationalized for 6MWT)

4) Primary Endpoints

Incidence

  • Proportion of patients with any ECF during 6MWT at EOS.
  • Median (IQR) ECF burden (% non-capture) among those with ECF.

Correlates

  • Association of ECF burden with 6MWD (m).
  • Association with HR variability indices (SD6×60s, RMSSDwalk, CV).
  • Association with ΔNT-proBNP (next day − baseline).
  • Association with post-test symptoms.

5) Statistical Plan

  1. Incidence: Exact binomial CI for any ECF; report episode rate (Poisson with exposure = walk time).
  2. Correlations: Linear/quantile regression for 6MWD and HRV; logistic regression for symptoms; linear model for ΔNT-proBNP.
  3. Adjustment set (pre-specified): age, sex, BMI, hemoglobin, eGFR, LVEF, pulmonary function, β‑blocker dose, chronic capture threshold, programmed output, RR slope/sensitivity.
  4. Nonlinearity: Restricted cubic splines for ECF burden and chronic threshold.
  5. Event-level analysis: Align ECF episodes with 10‑s windows of HR/SpO2; mixed models with random subject intercepts.
  6. Sensitivity: Exclude tests with corridor interruptions; repeat using %-predicted 6MWD.

6) Expected Patterns (Hypothesis)

7) Operational Safety

8) Sample Size (planning)

9) Reporting Template

Incidence any ECF: ____% (95% CI ____ to ____)
ECF burden (non-captured/total paced): median ____% (IQR ____–____)
6MWD vs ECF: β per 5% ECF = ____ m (95% CI ____ to ____), p = ____
HR variability vs ECF: ΔRMSSDwalk = ____ ms; ΔSD6×60s = ____ bpm
ΔNT-proBNP (ng/L): ____ (adjusted β per 5% ECF = ____)
Symptoms (OR per 5% ECF): ____ (95% CI ____ to ____)

Event-level: ECF windows associated with HR drop of ____ bpm and SpO₂ drop of ____ % (mixed-model p = ____)

10) Caveats

Prepared for clinical research/quality improvement; align with local policy and device vendor guidance.