PPG-based AF detection algorithm / Heart Failure / Atrial Fibrillation (AF) · Observational Study

A Photoplethysmography-Based Machine Learning Algorithm for Early Atrial Fibrillation Detection: A Prospective Validation Study

ClinicalTrials.gov · August 6, 2026

Preliminary Why this matters to you Expert discussion

Early or partial results. Treat as a signal, not a conclusion.

AI Summary

This is a clinical trial registry record for a prospective validation study of a photoplethysmography-based machine-learning algorithm for atrial fibrillation detection. The study is currently recruiting and has not yet reported results. The planned primary outcome is diagnostic accuracy (area under the ROC curve) compared to 12-lead ECG.

What was studied

Observational. Atrial Fibrillation (AF), Heart Failure; age from 18 Years. Intervention: Documented AF; Non-AF. Compared with: Gold-standard 12-lead ECG. n = 200. 1 site: Slovakia.

Key findings

Safety

Study is still recruiting; no efficacy or safety data are available

Who this may help

This algorithm is in early validation; it is not yet ready for clinical deployment. Clinicians should await published results before considering integration into practice.

Plain-language summary

This is a prospective validation study still recruiting participants with no results posted; it represents early clinical evaluation of a machine-learning algorithm in development.

Study design

As stated by the source record.

MethodsCohort model. Prospective time perspective. Primary outcome measure: Diagnostic accuracy (area under the ROC curve) of the PPG-based machine-learning algorithm for detecting clinically relevant AF (≥ 30s), compared with gold-standard 12-lead ECG (assessed at Through study completion (estimated November 2026))

DesignObservational

PopulationAtrial Fibrillation (AF), Heart Failure; age from 18 Years

Sample size200

InterventionDocumented AF; Non-AF

ComparatorGold-standard 12-lead ECG

Setting1 site: Slovakia

Reported figures

Quoted from the source exactly as published.

Planned enrollment200

Primary outcome measureDiagnostic accuracy (area under the ROC curve) of PPG-based machine-learning algorithm for detecting clinically relevant AF (≥30s) compared with 12-lead ECG

Estimated study completionNovember 2026

Clinical bottom line

This algorithm is in early validation; it is not yet ready for clinical deployment. Clinicians should await published results before considering integration into practice.

Caveats

This is a registry record only; no results are reported
Study is still recruiting; no efficacy or safety data are available
Methodology details (blinding, actual enrollment, cohort characteristics) not fully described in registry text
Validation will include internal cross-validation and external validation; relative weight and timing of each component not specified

Evidence assessment

Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.

Study design

moderate

Prospective observational study with planned internal and external validation cohorts

Directness

strong

Direct comparison to gold-standard 12-lead ECG for clinically relevant AF detection

Consistency

insufficient

No results posted; consistency cannot be assessed from registry record alone

Risk of bias

insufficient

Study ongoing; bias assessment not possible without methodology details or results

Sample adequacy

limited

Planned enrollment of 200 participants estimated; sample size determination not described

What is missing. This record has no key findings. That is a gap in the analysis, not a judgement about the study.

Source abstract

Registry record from ClinicalTrials.gov (NCT07749183). This is a study registration, not published results. Lead sponsor: Seerlinq s. r. o.. Recruitment status: RECRUITING. Study type: OBSERVATIONAL. Enrollment: 200 participants (ESTIMATED). Conditions: Atrial Fibrillation (AF), Heart Failure. Interventions: OTHER: PPG-based AF detection algorithm. Primary outcome measures: Diagnostic accuracy (area under the ROC curve) of the PPG-based machine-learning algorithm for detecting clinically relevant AF (≥ 30s), compared with gold-standard 12-lead ECG , Through study completion (estimated November 2026). Brief summary: This is a prospective study validating a new machine-learning algorithm that detects atrial fibrillation (AF) from photoplethysmography (PPG) signals, developed for integration into the Seerlinq remote monitoring platform. This algorithm builds on the same core PPG signal-processing technology as Seerlinq's HeartCore device, a CE-certified (Class IIb, MDR) device that monitors left ventricular filling pressures in heart failure patients. The algorithm will be validated through internal cross-validation, external validation against an independent cohort with paired PPG-ECG recordings, and validation in a cohort of patients with paroxysmal atrial fibrillation and frequent sinus-AF transitions.

Follow from this

Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.

PPG-based AF detection algorithmNCT07749183Heart FailureAtrial Fibrillation (AF)Seerlinq s. r. o.