ECG-AI Pulmonary Hypertension (PH) 12-Lead algorithm (1020)

The ECG-AI Pulmonary Hypertension 12-Lead algorithm is machine learning software that analyzes standard 12-lead ECG data to aid in earlier detection of elevated mean pulmonary arterial pressure (mPAP), an indicator of pulmonary hypertension, in adults presenting with dyspnea. It is not intended as a standalone diagnostic device but rather as an adjunct to clinical judgment, requiring further clinical evaluation for diagnosis confirmation.

The device uses a machine learning-based algorithm that processes 10-second or longer duration 12-lead ECG voltage-time series data and outputs a binary result (Detected, Not Detected, or Error) through integration with third-party clinical software such as EMR or ECG Management Systems. It includes automated quality checks to ensure appropriate signal characteristics and excludes poor-quality signals, and is compliant with FDA Guidance on Cybersecurity.

Software verification and validation per IEC 62304; cybersecurity compliance with FDA Guidance; quality assessment for signal processing including filter, resolution, duration, and noise/artifact detection per compatible ECG device specifications.

The subject device is substantially equivalent to the predicate ECG-AI LEF 12-Lead algorithm (K250652) because both employ identical machine learning-based principles, use 12-lead ECG data acquisition with binary output formats, target adult populations with cardiovascular symptoms, are intended for use by clinicians as adjuncts to clinical judgment, and incorporate equivalent cybersecurity compliance. Although the diagnostic applications differ (pulmonary hypertension vs. low ejection fraction), clinical validation demonstrates comparable performance characteristics (sensitivity 73.0%, specificity 74.4%) that do not raise new safety or effectiveness questions.