Search Results

The Steth IO Spot is an electronic stethoscope that enables amplification, filtering, and transmission of auscultation sound data, whereby a clinician at one location on network can listen to the auscultation sounds of a patient on site or at a different location on the network. Steth IO Spot is intended for use on individuals undergoing physical examination. The Steth IO Spot is intended to be used by professional users in a clinical environment or by lay users in a nonclinical environment. The device is not intended for self-diagnosis or emergency use.

OTC use: Steth IO Spot can be used by a patient to be examined during a video call and to submit a non-emergent-examination for review by their healthcare provider.

Rx-only use: Steth IO Spot may be prescribed by a licensed medical provider to monitor medical conditions that require the use of a stethoscope.

The Steth IO Spot is an acoustic device with an integrated microphone that collects biological sounds. Steth IO Spot attaches to the lightning port/USB-Type C (Universal Serial Bus Type C) port of the smartphone and can be utilized to auscultate patients during physical examination. The sound is then analyzed by the Steth IO Spot software telemedicine application (app) installed on the smartphone. This analysis enables a healthcare provider to identify sounds and from targeted areas of interest that may be present. A web portal (i.e., the Steth IO Portal) may also be used to access recorded patient data and to hold telemedicine calls.

The Steth IO Spot device has two main components:

• Steth IO Spot device: The Steth IO Spot device is capable of transmitting your heart, lung or other biological sounds to the mobile device. This device needs to be connected to the smartphone's lightning port/USB-Type C port.
• Steth IO Spot Software (Telemedicine App): The Steth IO smartphone application software performs real-time analysis to hear the sounds using headphones. The app is available for download from a designated software repository.

A chest piece, consisting of a bell and diaphragm, and an integrated microphone is placed on the patient and the sound is transmitted to a smartphone via lightning port/USB-C port. The device is capable of recording sound data, allowing the patient-user at one location to share audio data with their healthcare provider on site or at a different location on the network.

The provided document describes the Steth IO Spot, an electronic stethoscope. While it details various performance tests (functional, biocompatibility, electrical safety, EMC, software verification and validation), it focuses on demonstrating substantial equivalence to a predicate device (Eko CORE) rather than proving the device meets specific acceptance criteria based on clinical efficacy or diagnostic accuracy.

Therefore, the information required to construct the comprehensive table of acceptance criteria and a study proving those criteria (especially regarding diagnostic performance, human reader improvement with AI, standalone AI performance, and detailed ground truth establishment), as typically seen for AI-driven diagnostic devices, is not fully available in this regulatory submission document. This document is for a medical device that amplifies, filters, and transmits sounds, which is different from an AI-driven diagnostic tool that analyzes sounds for specific medical conditions.

However, I can extract the available information and highlight what is missing based on your request.

Based on the provided document, here's what can be extracted regarding acceptance criteria and performance studies for the Steth IO Spot:

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Eko CORE) by comparing technological characteristics and showing that the device performs comparably or better in functional aspects relevant to its core purpose (amplifying, filtering, and transmitting sounds). It does not describe a study that validates a diagnostic AI model's performance.

1. Table of Acceptance Criteria and Reported Device Performance

Given the nature of this device as an electronic stethoscope for sound data acquisition and transmission, the "acceptance criteria" presented are primarily functional and safety-related, rather than diagnostic performance metrics (e.g., sensitivity, specificity for disease detection).

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

• Heart Rate Accuracy Test: Not explicitly stated, but "side-by-side comparison test" implies a test set was used. The provenance (country, retrospective/prospective) is not mentioned.
• Frequency Audio Response Test: Not explicitly stated.
• Human Factors Usability Testing: "Two separate studies were conducted." Sample size (number of participants) is not explicitly stated. Provenance (country, retrospective/prospective) is not mentioned beyond the "intended use environment (e.g., hospital setting, office setting, etc.)" for professionals and "home setting" for lay users.

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

• Heart Rate Accuracy Test: The ground truth was established using an "EKG (gold standard)." This implies an objective measurement rather than expert interpretation of the device's output. The expertise for establishing the EKG ground truth itself is not detailed.
• Frequency Audio Response Test: No mention of experts; this is an engineering performance test against specifications and a predicate device.
• Human Factors Usability Testing: Evaluated "intended users" (healthcare professionals and patient-users/lay-users), but it's about usability, not a diagnostic ground truth established by experts.

4. Adjudication Method for the Test Set

• Not applicable for the described tests, as they are primarily technical performance or usability assessments rather than diagnostic accuracy studies requiring adjudication of discrepancies.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, an MRMC comparative effectiveness study was not done according to the provided text. This document describes a device for sound acquisition and transmission, not an AI that interprets or aids in diagnosis. Therefore, there's no discussion of human readers improving with or without AI assistance.

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

• Not explicitly applicable in the context of diagnostic AI. The "Steth IO Spot Software (Telemedicine App)" performs "real-time analysis to hear the sounds," but the document does not state that this analysis includes automated diagnostic interpretations. Its role is primarily for amplification, filtering, transmission, and recording of sounds for human clinicians to interpret. The "analysis enables a healthcare provider to identify sounds and from targeted areas of interest that may be present," implying it's an aid for the human, not a standalone diagnostic algorithm being evaluated for accuracy.

7. The Type of Ground Truth Used

• Heart Rate Accuracy Test: "EKG (gold standard)" for heart rate.
• Frequency Audio Response Test: Objective measurements against a predicate device and engineering specifications.
• Human Factors Usability Testing: User task completion and satisfaction (functional ground truth).

8. The Sample Size for the Training Set

• Not applicable. The document describes a medical device, not an AI model trained on sound data for diagnostic purposes. The software mentioned (Steth IO Spot Software) primarily handles real-time audio processing for listening and transmission, not deep learning for diagnosis.

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

• Not applicable. See point 8.

Ask a specific question about this device

The VoqX Electronic Stethoscope is intended for medical diagnostic purposes only. It may be used for the detection and amplification of sounds from the heart, lungs, arteries, veins, and other internal organs with the use of a selective frequency and with an integrated graphics display to show amplified heart sounds as phonocardiograms. It can be used on any person undergoing a physical assessment.

The VoqX Electronic Stethoscope is intended for medical diagnostic purposes. It may be used for the detection and amplification of sounds from the heart, lungs, arteries, veins, and other internal organs with the use of a selective frequency and with an integrated graphics display to show amplified heart sounds as phonocardiograms.

The VoqX Electronic Stethoscope is comprised of two parts: Back Unit (head piece) and Front Unit (chest piece).

The device has 3 modes of operation: General - emphasizes sounds from 20 to 2000Hz, Heart emphasizes sounds from 20 to 200Hz and Lungs - emphasizes sounds from 100 to 500Hz. In addition, the VoqX Electronic Stethoscope incorporates a software feature that displays sounds as a "Sound Signature". The "Sound Signature" algorithm generates intensity image based on the spectrogram of the output audio data. The device is supplied with an AC/DC power supply adapter and a charging cable.

Here's a breakdown of the acceptance criteria and study information for the VoqX Electronic Stethoscope, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The document states that a "Performance Testing" study was conducted to compare the VoqX Electronic Stethoscope to its predicate device (3M Littmann Electronic Stethoscope, Model 3200). The main purpose was to verify that the VoqX's performance is similar to that of its predicate device in terms of frequency response.

Note: The document does not provide specific numerical values for the frequency response acceptance criteria or the actual measured performance of the VoqX. It only states that the tests "passed and met the predefined acceptance criteria" and that the performance is "similar to that of its predicate device."

2. Sample Size and Data Provenance

The document does not specify the sample size used for the performance testing related to "frequency response."

The data provenance is not explicitly stated in terms of country of origin of the data or whether it was retrospective or prospective. Given that this is a premarket notification, the performance testing would typically be prospective, conducted by the manufacturer, Sanolla Ltd., which is based in Israel.

3. Number of Experts and Qualifications for Ground Truth

For the performance testing focused on frequency response, there's no mention of "experts" being used to establish a ground truth. This type of testing often relies on instrumental measurements and comparisons to a validated standard (the predicate device) rather than human expert interpretation of an outcome.

4. Adjudication Method

Not applicable for frequency response testing, as it's an objective measurement.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or implied in the provided document. The performance testing described is focused on the inherent technical performance (frequency response) of the device itself compared to a predicate, not on how human readers' diagnostic accuracy is affected by using the device.

6. Standalone Performance Study

Yes, the "Performance Testing" described appears to be a standalone (algorithm only without human-in-the-loop performance) study in the sense that it evaluates the technical characteristics of the device (frequency response) objectively, rather than assessing a human user's performance with the device.

7. Type of Ground Truth Used

For the "Performance Testing" related to frequency response, the ground truth appears to be based on instrumental measurements and comparison to the technical specifications/performance of the legally marketed predicate device (3M Littmann Electronic Stethoscope, Model 3200).

8. Sample Size for the Training Set

The document does not mention a training set, as the device's main function is the detection and amplification of sounds, and the "Sound Signature" algorithm generates an intensity image based on the spectrogram of output audio data. This typically implies signal processing rather than a deep learning model that requires a large labeled training set for classification or detection.

9. How Ground Truth for Training Set Was Established

Not applicable, as a training set for a machine learning model is not explicitly mentioned for the described "Sound Signature" feature. The "Sound Signature" algorithm's output is described as an "intensity image based on the spectrogram of the output audio data," which suggests a deterministic signal processing method rather than a data-driven machine learning approach requiring a training set with established ground truth.

Ask a specific question about this device