FDA Radiology AI Devices

NEAT 001 is a software medical device that automatically analyzes EEG data obtained during sleep studies to detect different stages of sleep according to established sleep medicine guidelines. It helps clinicians by providing automated scoring and visualization of sleep stages, improving the efficiency and consistency of sleep evaluations in adult patients.

The EyeBOX EBX-4.1 is an eye-tracking device designed to help diagnose concussions by measuring eye movements. It uses a high-speed infrared camera to record gaze while the patient watches a video stimulus. The device automatically analyzes the data and produces a BOX score indicating the likelihood of concussion, comparing the eye tracking metrics to a normative database of uninjured individuals. This helps clinicians assess brain injury more objectively and quickly.

The Nurochek-Pro System is a portable EEG-based device that generates visual evoked potentials to help healthcare professionals diagnose mild traumatic brain injury (mTBI) in patients aged 12 to 44. Worn on the patient's head, it records brain electrical activity and provides an analytic aid to detect mTBI within 5 days after a potential head injury, improving diagnostic accuracy in clinical settings.

DeepRESP is a cloud-based AI software tool that analyzes sleep study recordings, with or without EEG signals, to assist clinicians in diagnosing sleep disorders. It automatically marks events, calculates parameters like the Apnea-Hypopnea Index, and infers sleep stages. This helps medical professionals to efficiently assess sleep health and tailor treatments.

Noxturnal Web is a web-based software designed to display, analyze, and manually score pre-recorded physiological data collected during sleep studies. It assists clinicians in diagnosing sleep and respiratory-related disorders by enabling detailed review and reporting of sleep stages and breathing events such as obstructive apneas, all under clinical supervision.

The HomeSleepTest (HST, HST REM+) by Somnomedics GMBH is a non-invasive, prescription device designed for home use to aid in the diagnosis of sleep disorders, including sleep-related breathing disorders. It records multiple physiological signals such as brain electrical activity (EEG), eye movements (EOG), muscle activity (EMG), oxygen saturation, heart rate, and snoring. The data is collected via frontal and mastoid electrodes and other sensors, then uploaded to a cloud platform for analysis by clinicians using specialized software. This helps physicians assess sleep quality and breathing disorders outside of hospital settings, improving patient comfort and accessibility to diagnostic testing.

The Dreem 3S is a wearable headband device that records brain electrical activity (EEG) and movement data during sleep. It uses AI algorithms based on neural networks to automatically analyze this data and produce detailed sleep stage reports for adults. This helps clinicians assess sleep patterns and disturbances remotely in home or healthcare environments.

The Cerebral Autoregulation Index (CAI) Algorithm is a software tool designed to help clinicians monitor whether cerebral autoregulation—the brain's ability to maintain stable blood flow—is intact or impaired. It analyzes signals from cerebral oximetry and blood pressure monitors to provide an index value indicating the level of coherence between these parameters. This helps guide advanced hemodynamic monitoring in critical care patients without making direct therapeutic decisions.

SleepStageML is a software-only medical device that uses AI to automatically analyze EEG signals from sleep studies (PSG recordings) to identify different sleep stages. It assists qualified clinicians in diagnosing sleep quality and sleep disorders in adult patients by providing automated, software-generated sleep stage annotations that clinicians can review and verify.

BrainSee is software that helps clinicians predict whether patients aged 55 to 95 with amnestic mild cognitive impairment (aMCI) will progress to clinical Alzheimer's disease dementia within 5 years. It uses standard brain MRI scans along with patient demographics and cognitive test scores to generate a similarity score indicating the likelihood of progression. This tool provides supplemental prognostic information to aid clinical decision-making but is not a standalone diagnostic device.