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

Prospective Validation of a Machine-Learning Algorithm Using Photoplethysmography Signals for Early Detection of Atrial Fibrillation During Remote Telemonitoring

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.

Study Overview

• Status: Recruiting
• Conditions: Heart Failure; Atrial Fibrillation (AF)
• Intervention / Treatment: Other: PPG-based AF detection algorithm

Detailed Description

Atrial fibrillation (AF) and heart failure (HF) frequently coexist and share a bidirectional causal relationship; their concurrence is associated with worse clinical outcomes. Early detection of AF may enable timely intervention and improve outcomes. This study is prospectively validating a machine-learning algorithm for AF detection from PPG signals, intended 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 device under the EU MDR that monitors left ventricular filling pressures in heart failure patients). It is a stand-alone algorithm designed specifically to detect clinically relevant (≥ 30s) atrial fibrillation.

Validation of the algorithm will proceed in three stages: (1) internal cross-validation; (2) external validation against an independent cohort with paired PPG-ECG recordings, to confirm generalizability; and (3) validation in a cohort of patients with paroxysmal atrial fibrillation and frequent sinus-AF transitions, to assess performance during clinically challenging rhythm changes.

The study is enrolling toward an estimated 1,000 unique PPG recordings. A 12-lead ECG is used to confirm cardiac rhythm classification (gold standard) as the reference for evaluating algorithm performance.

• Study Type: Observational
• Enrollment (Estimated): 200

Contacts and Locations

• Study Contact: Name: Marta Kollárová, MSc., PhD.; Phone Number: +421 950 896 026; Email: marta.kollarova@premedix.org

Study Locations

• Slovakia
  • Bratislava, Slovakia
    • Recruiting
    • PreMedix
    • Contact: Allan Bohm, M.D., MSc. PhD.; Phone Number: +421 907 411 499; Email: allan.bohm@premedix.org
    • Principal Investigator: Allan Bohm, M.D., MSc., PhD.

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Adults ≥18 years with a diagnosis of heart failure (HFrEF, HFmrEF, or HFpEF) from Slovakia

Description

Inclusion Criteria:

• Adults ≥18 years with a diagnosis of heart failure (HFrEF, HFmrEF, or HFpEF)
• 12-lead ECG performed to confirm cardiac rhythm classification (AF vs. non-AF)

Exclusion Criteria:

• Missing a valid PPG recording

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Documented AF; HF patients with a history of permanent/paroxysmal AF and AF documented on 12-lead ECG at enrollment	Other: PPG-based AF detection algorithm; The PPG-based atrial fibrillation detection algorithm is a non-invasive signal processing approach that analyzes photoplethysmographic waveforms obtained during remote monitoring. The algorithm evaluates pulse-to-pulse variability, waveform characteristics, and signal quality parameters to identify irregular rhythm patterns associated with atrial fibrillation and provide early detection of potential arrhythmic events.
Non-AF; HF patients in sinus rhythm on the index 12-lead ECG with no prior documented AF episodes	Other: PPG-based AF detection algorithm; The PPG-based atrial fibrillation detection algorithm is a non-invasive signal processing approach that analyzes photoplethysmographic waveforms obtained during remote monitoring. The algorithm evaluates pulse-to-pulse variability, waveform characteristics, and signal quality parameters to identify irregular rhythm patterns associated with atrial fibrillation and provide early detection of potential arrhythmic events.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
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)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity and specificity of the algorithm at the Youden-optimal threshold		Through study completion (estimated November 2026)
Positive predictive value and negative predictive value		Through study completion (estimated November 2026)
Average precision	area under the precision-recall curve	Through study completion (estimated November 2026)
Model calibration	e.g., calibration curve / Brier score	Through study completion (estimated November 2026)
Matthews correlation coefficient		Through study completion (estimated November 2026)
Overall classification accuracy		Through study completion (estimated November 2026)
Specificity and false-positive rate in the subgroup with frequent atrial/ventricular extrasystoles		Through study completion (estimated November 2026)
Accuracy of AF detection during sinus-AF transitions at the individual patient level		Through study completion (estimated November 2026)

Collaborators and Investigators

• Sponsor: Seerlinq s. r. o.
• Collaborators: Premedix Academy; ACADEMY - občianske združenie

Study record dates

Study Major Dates

• Study Start (Actual): October 1, 2025
• Primary Completion (Estimated): August 1, 2026
• Study Completion (Estimated): November 1, 2026

Study Registration Dates

• First Submitted: July 31, 2026
• First Submitted That Met QC Criteria: July 31, 2026
• First Posted (Actual): August 6, 2026

Study Record Updates

• Last Update Posted (Actual): August 6, 2026
• Last Update Submitted That Met QC Criteria: July 31, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: Photoplethysmography; Machine learning; Wearable device; Digital biomarker; Remote telemonitoring; Arrhythmia detection
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Pathologic Processes; Heart Diseases; Arrhythmias, Cardiac; Pathological Conditions, Signs and Symptoms; Heart Failure; Atrial Fibrillation
• Other Study ID Numbers: HeartCoreAF01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: The data will not be shared publicly, but anonymized data can be shared upon reasonable request to the corresponding author.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No