Search Results

NeoBeat and NeoBeat Mini are indicated to continuously measure and display the heart rate of neonates using dry electrodes on the torso during transition, stabilization and/or resuscitation. The devices are intended to be used in healthcare facilities. NeoBeat is intended for use on newborns approximately 1.5-5 kg. NeoBeat Mini is intended for newborns approximately 0.5-2 kg.

The NeoBeat Newborn Heart Rate Meter is a battery-powered device placed on the torso of a newborn, indicated to measure the heart rate. NeoBeat does not store, display or output an ECG signal. The device is placed around the torso of the neonate such that the ECG dry electrodes contact the neonate's skin. It can be oriented caudally or cranially. In normal operation, the LED display presents the heart rate in large numerals. The display can also present other information, such as signal quality and error codes. The device comes with a charging stand.

Here's a breakdown of the acceptance criteria and study information for the NeoBeat/NeoBeat Mini device based on the provided text:

Acceptance Criteria and Device Performance

Study Information

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: 19 clinical cases representing over 4 hours of ECG data.
   • Data Provenance: The 19 cases were randomly selected from a large database containing newborn ECGs from four countries outside the United States.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: 2
   • Qualifications: An ICU physician and a scientific expert in ECG signal processing and analysis.

3. Adjudication method for the test set:

   • Not explicitly stated, but it implies a consensus given "Heart rate based on expert annotation was considered 'ground truth'." This suggests the two experts either agreed directly or their combined annotation formed the ground truth.

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study was done. This study focused on the algorithm's standalone performance compared to expert-annotated ground truth, not on human reader improvement with or without AI assistance.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Yes, a standalone performance study was done. The study compared "Heart rate based on NeoBeat's algorithm" to the "ground truth" heart rate established by experts.

6. The type of ground truth used:

   • Expert consensus (specifically, expert annotation of QRS complexes).

7. The sample size for the training set:

   • Not explicitly stated. The document mentions a "large database containing newborn ECGs from four countries outside the United States" with "over 1000 cases of ECGs" collected from researchers. While this database was used to select the test cases, it is strongly implied that this database would have been used for training/development, but the exact size of the training set is not specified separately from the total database.

8. How the ground truth for the training set was established:

   • Not explicitly stated for the training set. For the test set, it was established by expert annotation of QRS complexes by an ICU physician and a scientific expert. It is reasonable to infer a similar method for the training set, given the nature of the data and the use of expert annotation for the test set.

Ask a specific question about this device