On July 16, HoneyNaps announced that Somnum v3.0, its artificial intelligence-based software for polysomnography analysis, received U.S. Food and Drug Administration 510(k) clearance under clearance number K253390. The FDA clearance expands the software’s capabilities for automated analysis of sleep-disordered breathing.

About Somnum v3.0

Somnum is an AI-enabled stand-alone software application that analyzes previously recorded physiological data from adult level 1 sleep studies. The software automatically detects events and displays scoring results using AI-based algorithms across its functional modules. According to the FDA 510(k) summary, physicians can review, edit, or delete auto-scored events and generate a sleep summary report that includes tables and graphs for clinical assessment of sleep disorders.

The cleared version includes AI/ML-based algorithms for sleep stage classification, arousal detection, respiratory event detection, and leg movement detection. It automatically detects apnea and hypopnea events and classifies apnea as obstructive, central, or mixed. According to HoneyNaps, Somnum v3.0 is “designed to distinguish different apnea subtypes that may be challenging to differentiate through manual scoring alone.”

Category SOMNUM 3.0 Clinical Value
Analysis Capability Automated detection and
individual analysis of
Hypopnea, Obstructive Apnea,
Central Apnea, and Mixed Apnea
Supports detailed
respiratory event analysis
Performance
Evaluation
AI performance validated
at the individual event level
Improved analytical
precision and broader
AI capabilities
AI Features Automatic detection and
classification of respiratory
event subtypes
Advanced
AI algorithms
Overall Percent
Agreement (OPA)
Hypopnea 98.58%
Obstructive Apnea 97.42%
Central Apnea 99.83%
Mixed Apnea 99.94%
High agreement
across respiratory
event categories

Figure 1: Key Enhancements in SOMNUM V3.0; source

The device is intended for use as an aid in the diagnosis of sleep and respiratory-related sleep disorders. It is intended for analysis, manual scoring or rescoring, display, retrieval, summarization, and report generation of digital data collected by monitoring devices typically used to evaluate sleep and respiratory-related sleep disorders. The device is to be used under the supervision of a physician in adults age 22 and older.

Read more industry news from the AASM.