Search Results

The ALGO Pro Newborn Hearing Screener is a mobile, noninvasive instrument used to screen infants for hearing loss. The screener uses Automated Auditory Brainstem Response (AABR®) for automated analysis of Auditory Brainstem Response (ABR) signals recorded from the patient. The screener is intended for babies between the ages of 34 weeks (gestation age) and 6 months. Babies should be well enough to be ready for discharge from the hospital, and should be asleep or in a quiet state at the time of screener is simple to operate. It does not require special technical skills or interpretation of results. Basic training with the equipment is sufficient to learn how to screen infants who are in good health and about to be discharged from the hospital. A typical screening process can be completed in 15 minutes or less. Sites appropriate for screening include the well-baby nursery, NICU, mother's bedside, audiology suite, outpatient clinic, or doctor's office.

The ALGO® Pro is a fully automated hearing screening device used to screen infants for hearing loss. It provides consistent, objective pass/refer results. The ALGO Pro device utilizes Auditory Brainstem Response (ABR) as the hearing screening technology, which allows the screening of the entire hearing pathway from outer ear to the brainstem. The ABR signal is evoked by a series of acoustic broadband transient stimulus (clicks) presented to a subject's ears using acoustic transducers and recorded by sensors placed on the skin of the patient. The ALGO Pro generates each click stimulus and presents to the patient's ear using acoustic transducers attached to disposable acoustic earphones. The click stimulus elicits a sequence of distinguishable electrophysiological signals produced as a result of signal transmission and neural responses within the auditory nerve and brainstem of the infant. Disposable sensors applied to the infant's skin pick up this evoked response, and the signal is transmitted to the screener via the patient electrode leads. The device employs advanced signal processing technology such as amplification, digital filtering, artifact rejection, noise monitoring and noise-weighted averaging, to separate the ABR from background noise and from other brain activity. The ALGO Pro uses a statistical algorithm based on binomial statistics to determine if there is a response to the stimulus that matches to the ABR template of a normal hearing newborn. If a response is detected that is consistent with the ABR template derived from normal hearing infants (automated auditory brainstem response technology, AABR), the device provides an automated 'Pass' result. A 'Refer' result is automatically generated if the device cannot detect an ABR response with sufficient statistical confidence or one that is consistent with the template.

Here's a breakdown of the acceptance criteria and study information for the ALGO Pro Newborn Hearing Screener, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA submission primarily focuses on demonstrating substantial equivalence to a predicate device (ALGO 5) rather than setting specific, numerical acceptance criteria for a new clinical performance study. The "acceptance criteria" here are implied through the comparison with the predicate device's established performance and the demonstration that the ALGO Pro performs comparably.

2. Sample Size Used for the Test Set and Data Provenance

No new clinical "test set" was used for the ALGO Pro in the context of a prospective clinical trial. The performance data for the AABR algorithm (sensitivity and specificity) are derived from previously published, peer-reviewed clinical studies that validated the underlying ALGO AABR technology.

• Sample Size for AABR Algorithm Development: The ABR template, which forms the basis of the ALGO Pro's algorithm, was determined by superimposing responses from 35 neonates to 35 dB nHL click stimuli.
• Data Provenance for ABR Template: The data for the ABR template was collected at Massachusetts Eye and Ear Infirmary during the design and development of the original automated infant hearing screener.
• Data Provenance for Clinical Performance (Sensitivity/Specificity): The studies cited (Peters, J. G. (1986) and Herrmann, Barbara S., Aaron R. Thornton, and Janet M. Joseph (1995)) are generally long-standing research from various institutions. The document doesn't specify the exact country of origin for the studies cited beyond the development of the template in the US. These studies would be retrospective relative to the ALGO Pro submission, as they describe the development and validation of the original ALGO technology.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

This information is not provided in the document for the studies that established the ground truth for the ABR template or the clinical performance of the ALGO AABR algorithm. The template was derived from "normal hearing" neonates, implying a clinical assessment of their hearing status, but the specifics of how that ground truth was established (e.g., specific experts, their qualifications, or methods other than the ABR itself) are not detailed within this submission summary.

4. Adjudication Method for the Test Set

Not applicable, as no new clinical "test set" requiring adjudication for the ALGO Pro itself was conducted or reported in this submission. The historical studies developing the AABR algorithm would have defined their own ground truth and validation methods, but these are not detailed here.

5. 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

Not applicable. The ALGO Pro is an automated hearing screener that provides a "Pass" or "Refer" result without requiring human interpretation of the ABR signals themselves. It is not an AI-assisted human reading device, but rather a standalone diagnostic aid.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, a standalone performance assessment of the AABR algorithm (which is essentially the "algorithm only" component) was done indirectly through historical studies and directly through bench testing.

• The core AABR algorithm has a 99.9% algorithmic sensitivity (based on binomial statistics).
• Historically, independent clinical studies (cited) showed an overall clinical sensitivity of 98.4% and specificity of 96% to 98% for the ALGO AABR technology when used in clinical settings.
• For the ALGO Pro specifically, bench testing was performed to confirm the equivalence of the acoustical stimuli, recording of evoked potentials, and proper implementation of the ABR template and algorithm between the ALGO Pro and its predicate device (ALGO 5). This bench testing effectively confirmed the standalone performance of the ALGO Pro's algorithm against the established performance of the predicate.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

• For ABR Template Development: The ABR template was based on the morphology of ABR waveforms from normal hearing neonates. This implies a ground truth established by clinical assessment of "normal hearing" status.
• For Clinical Performance (Sensitivity/Specificity): The clinical studies cited (Peters, Herrmann et al.) would have established ground truth for hearing status through follow-up diagnostic audiologic evaluations, which could include behavioral audiometry, auditory steady-state response (ASSR) testing, or other objective measures (likely expert consensus based on these diagnostic tests). The document does not specify the exact ground truth methodology of these historical studies.

8. The Sample Size for the Training Set

The document states that the ABR template, which underpins the algorithm, was derived by superimposing responses from 35 neonates. This set of 35 neonates effectively served as the "training set" or foundational data for the ABR template.

9. How the Ground Truth for the Training Set Was Established

The ground truth for the "training set" (the 35 neonates used to derive the ABR template) was established based on their status as "normal hearing" infants. This implies a determination of their hearing status through established clinical methods for neonates at the time (e.g., standard audiologic evaluation to confirm normal hearing), though the specific details of these diagnostic methods are not provided in this summary.

Ask a specific question about this device