# Fibricheck detection capabilities for atrial fibrillation (FDA–AF): a multicenter validation study

**Authors:** John Sollee, Baljash Cheema, David Slotwiner, Alexander Volodarskiy, Lien Desteghe, Christophe Buyck, Hein Heidbuchel, Stavros Stavrakis, Laurent Pison, Dieter Nuyens, Maximo Rivero-Ayerza, Hugo Van Herendael, James Thomas

PMC · DOI: 10.1038/s41746-025-02059-2 · NPJ Digital Medicine · 2025-11-20

## TL;DR

This study confirms that FibriCheck, a smartphone-based platform, accurately detects atrial fibrillation across various devices and health conditions.

## Contribution

The study validates FibriCheck's high accuracy for AF detection across multiple smartphones and clinical subgroups.

## Key findings

- FibriCheck achieved 98.5% accuracy, 96.3% sensitivity, and 99.3% specificity in detecting AF.
- Performance remained consistent across different smartphone models and comorbidities.
- Reduced sensitivity in individuals with darker skin tones and higher BMIs was mitigated by technician verification.

## Abstract

Atrial fibrillation (AF) is the most common arrhythmia worldwide and is associated with significant morbidity and mortality. FibriCheck is a medical analysis platform that uses an end-to-end algorithm to detect AF based on photoplethysmography signals recorded on consumer smartphones. The study aimed to validate FibriCheck in a multicenter, multinational cohort of 236 subjects across ten popular smartphone devices. The 12-lead electrocardiogram was used as the reference diagnosis. FibriCheck demonstrated high overall performance: accuracy 98.5% (95% CI: 98.0–99.0%); sensitivity 96.3% (95% CI: 94.4–97.7%); specificity 99.3% (95% CI: 98.8–99.7%). Performance was not affected by smartphone device or comorbid heart failure, vascular disease, hypertension, diabetes, or stroke. Sensitivity was reduced in individuals with darker skin tones and higher BMIs, but this was mitigated by technician verification. The study confirms the high accuracy, sensitivity, and specificity of the FibriCheck algorithm in detecting AF across various smartphone models and clinical subgroups.

## Linked entities

- **Diseases:** atrial fibrillation (MONDO:0004981), heart failure (MONDO:0005252), diabetes (MONDO:0005015), stroke (MONDO:0005098)

## Full-text entities

- **Diseases:** AF (MESH:D001281), arrhythmia (MESH:D001145), diabetes (MESH:D003920), vascular disease (MESH:D014652), heart failure (MESH:D006333), stroke (MESH:D020521), hypertension (MESH:D006973)

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12635274/full.md

## Figures

1 figure with captions in the complete paper: https://tomesphere.com/paper/PMC12635274/full.md

## References

17 references — full list in the complete paper: https://tomesphere.com/paper/PMC12635274/full.md

---
Source: https://tomesphere.com/paper/PMC12635274