Search Results

Stethophone Pro is an electronic stethoscope that enables detection, amplification, filtering, and transmission of auscultation sound data (heart and lungs), whereby a clinician at one location can listen to the auscultation sounds of a patient acquired on site or at a different location. Stethophone Pro is intended for use on adult patients. Stethophone Pro is not intended for self-diagnosis and not intended to be used as a sole means of diagnosis. Stethophone Pro can be used in clinical and nonclinical environments.

For Rx-only: Stethophone Pro is intended to provide decision support to clinicians in their evaluation of patients' heart sounds. The software analyzes heart sounds and phonocardiograms and can automatically detect murmurs that may be present, sound timing and character, including S1, S2, and the absence of a heart murmur. The interpretations of heart sounds offered by the software are not diagnoses and are meant only to provide decision support to the clinician, who may use the result in conjunction with their own evaluation and clinical judgment.

For OTC: When used without access to the automatic analysis feature or under supervision of healthcare professional, Stethophone Pro is also intended to be used by lay users.

Stethophone Pro is an electronic stethoscope software application that operates on smartphones. Stethophone enables the capture and amplification of chest sounds for real-time or recorded listening. Cloud storage with sound record sending capabilities, filtering for selected frequency ranges, and visualization all assist with sound analysis.

Stethophone is designed to assist healthcare professionals in both hearing and visualizing heart and lung sounds during a physical examination of a patient and in storing recorded sounds in the cloud for later analysis. It also enables home users to record and send chest sounds to their physicians.

Stethophone can be used for the assessment of chest sounds of adult patients in clinical and non-clinical environments. Assessment should be performed by healthcare professionals, while sound capturing can be performed by both healthcare professionals and home users.

While all functions described above are available to both prescription and OTC users, the following analysis features and the associated report are accessible exclusively with a prescription: Stethophone Pro performs basic analysis of heart sounds, including detection of murmurs, identification of S1 and S2 heartbeats on the timeline, and calculation of timing intervals between them.

Key Product Features Available for both prescription and OTC users

• Capturing chest sounds using the smartphone microphone:
  • Real-time listening to chest sounds
  • Recording of chest sounds
• Sending examinations to specialists for assessment
• Two modes of sound visualization: oscillogram and spectrogram
• Selecting from three audio filters for listening:
  • Bell Traditional filter used in stethoscopes for low frequency sounds
  • Diaphragm Traditional filter used for higher frequency sounds of heart and lungs
  • Starling Filter for listening to the full frequency of chest sounds

All of these features are present in both the primary predicate, Stethophone Pro (K240901), and the reference device, Stethophone (K231551), and are now available for OTC use.

Product Features For prescription users only

• Detecting murmurs, timing for S1 and S2 sounds, and calculating heart rate

These features are derived from the Stethophone Pro (K240901, Rx-only).

Collectively, these features enable home users to acquire their own sounds, share them with healthcare professionals, and control their health, as well as allow healthcare professionals to examine and monitor patients on site and remotely, seek out second opinions from specialists, and use the device in a telemedicine context.

Based on the provided FDA 510(k) clearance letter for Stethophone Pro (K252595), here's an analysis of the acceptance criteria and study information:

The document explicitly states that no new performance data was required for this submission. This is because the device is a modified version of previously cleared devices (Stethophone Pro K240901 and Stethophone K231551), and the modifications were solely to the indications for use, not to the underlying acoustics algorithms or automated sound analysis capabilities.

Therefore, the following information is not available in the provided document, as no new studies were conducted for this specific clearance (K252595):

• A table of acceptance criteria and the reported device performance
• Sample sizes used for the test set
• Data provenance for the test set
• Number of experts used to establish ground truth for the test set
• Qualifications of experts
• Adjudication method for the test set
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done
• Effect size of human reader improvement with AI vs. without AI assistance
• If a standalone performance (algorithm only without human-in-the-loop performance) was done
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.)
• Sample size for the training set
• How the ground truth for the training set was established

However, we can infer that acceptance criteria and performance data were established and met in the previous clearances (K240901 and K231551) for the functionalities that remain unchanged.

Summary of Device Performance and Acceptance Criteria (Based on Previous Clearances - Not explicitly detailed in this document):

The document states:

• "The acoustics algorithms for sound filtering (that are used for both OTC and Rx parts of the software) capabilities remain entirely unchanged from those validated and cleared in both K240901 and K231551."
• "Automated sound analysis capabilities (that are available for Rx use only) remain entirely unchanged from those validated and cleared in K240901."

This implies that for the features that do have performance claims (specifically, automated sound analysis for murmur detection and heart sound timing in the Rx-only version), acceptance criteria were met during the clearance of K240901. Similarly, for the basic functions of sound capture, amplification, filtering, and transmission, acceptance criteria were met during the clearance of K231551 and K240901.

To obtain the specific details regarding the acceptance criteria, study designs, sample sizes, and ground truth methodologies for these functionalities, one would need to refer to the original 510(k) submissions for K240901 and K231551. This current document (K252595) serves as a modification that leverages the previously established substantial equivalence and performance data.

Ask a specific question about this device

The Eko Foundation Analysis Software with Transformers (EFAST) is intended to support healthcare professionals in the evaluation of patients' heart sounds and electrocardiograms (ECGs). The software calculates heart rate, detects the presence of murmurs associated with Structural Heart Disease, and determines murmur timing including the timing of S1, S2 heart sounds. When ECG is available, the software detects the presence of atrial fibrillation and normal sinus rhythm.

The software is intended for use by or under the supervision of a healthcare professional and is not to be used as a sole means of diagnosis. The interpretations of heart sounds and ECG offered by the software are designed to support and not replace the healthcare professional's clinical judgment. The murmur detection is intended for use on both pediatric and adult patients, while the detection of atrial fibrillation is intended for use on adults (> 18 years).

Eko Foundation Analysis Software with Transformers (EFAST) is a cloud-based Software as a Medical Device (SaMD) intended to provide clinical decision support to healthcare professionals (HCP) in the evaluation of patients' heart sounds (phonocardiogram, PCG) and electrocardiograms (ECGs). The software employs signal processing techniques and machine learning (Deep Neural Networks) to perform simultaneous analysis of recorded heart sounds and ECG data (when available), and identify the presence of murmurs associated with Structural Heart Disease, and determine murmur timing including the timing of S1, S2 heart sounds. When ECG is available, the software also detects the presence of atrial fibrillation and sinus rhythm.
The software does not identify other arrhythmias. In addition, it calculates the heart rate of the patient.

The EFAST Software accepts input consisting of heart sounds and ECG waveforms recorded using Eko Digital Stethoscopes that are saved in .WAV file format and stored in the Eko Cloud, which utilizes the Amazon Web Services (AWS) Simple Storage Service (S3) for data storage and for easy communication with the EFAST analysis server. When an API Request is sent to the EFAST API, the corresponding recordings (PCG and/or ECG) are accessed by the EFAST software and they are analyzed by the EFAST software components. After analysis, the EFAST software returns a JSON format data structure with the algorithm results, which is saved back to the Eko Cloud and can be displayed on EFAST API integrated target software or devices (e.g. user-facing apps).

The EFAST Software consists of the following algorithm components:

• Heart Sound Signal Quality Classifier: Evaluates whether an audio recording contains heart sounds of sufficient quality for further clinical analysis
• Structural Murmur Classifier: Determines whether a good-quality heart sound recording contains a structural murmur or not
• Heart Sound Timing & Murmur Timing: Determines the timing of S1 and S2 heart sounds and determines whether a structural murmur occurs during the systolic or diastolic phase
• ECG Rhythm Classifier: Analyzes ECG signals and categorizes them into one of four classifications: Sinus Rhythm, Atrial Fibrillation, Unspecified Rhythm, and Poor ECG Signal
• Heart Rate Calculation: Signal processing algorithm that utilizes ECG and PCG to calculate heart rate value in beats per minute

Here's a detailed breakdown of the acceptance criteria and the studies proving the device's performance, based on the provided FDA 510(k) clearance letter:

Acceptance Criteria and Reported Device Performance

Note on Acceptance Criteria: The document does not explicitly state numerical "acceptance criteria" but rather presents the device's performance results in comparison to a predicate device, implying that the demonstrated performance is considered acceptable for substantial equivalence. The predicate device's performance often sets an implicit benchmark.

Study Details: Structural Murmur Classification

2. Sample size used for the test set and the data provenance:

• Test set sample size: 2,460 unique heart sound recordings (from 615 unique subjects). 259 recordings were excluded due to lack of cardiologist agreement.
• Data provenance: Retrospective study of de-identified data. Three sites within the US (2 sites) and Canada (1 site).

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

• Number of experts: "Multiple cardiologists" annotated the recordings.
• Qualifications: "Cardiologists." No further specific qualifications (e.g., years of experience) are provided in this document.

4. Adjudication method for the test set:

• For 2,460 initial recordings, "multiple cardiologists" annotated them.
• For 259 of these recordings, the cardiologists "could not come to agreement," leading to their exclusion from the analysis. This implies some form of consensus or agreement-based adjudication, where a lack of agreement led to exclusion rather than a specific tie-breaking rule (e.g., 2+1, 3+1).

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:

• No MRMC comparative effectiveness study involving human readers with vs. without AI assistance is described in this section for structural murmur classification. The comparison is between the EFAST algorithm's standalone performance and the predicate device's standalone performance ("Algorithm Performance Comparison to Predicate").

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

• Yes, the presented performance metrics (Sensitivity, Specificity) are for the EFAST algorithm operating in a standalone capacity ("EFAST Structural Murmur Classification Performance" and "Algorithm Performance Comparison to Predicate").

7. The type of ground truth used:

• Ground truth was established by "pairing the cardiologist annotations with gold standard echocardiogram." This indicates a hybrid ground truth, combining expert interpretation with objective clinical imaging (echocardiogram).

8. The sample size for the training set:

• Not specified in this document. The document only mentions validation on "proprietary datasets."

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

• Not specified in this document.

Study Details: Heart Sound Timing (S1/S2 Detection)

2. Sample size used for the test set and the data provenance:

• Test set sample size: 96 heart sound recordings.
• Data provenance: Retrospective study. Data collected using Eko CORE or Eko CORE 500 Digital Stethoscopes. Country of origin not explicitly stated for this subset, but the broader structural murmur study involved US and Canada.

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

• Number of experts: "Expert cardiologists."
• Qualifications: "Cardiologists." No further specific qualifications are provided.

4. Adjudication method for the test set:

• Not explicitly stated, but "annotated by expert cardiologists" implies expert consensus for these 96 recordings, as no exclusions due to disagreement are mentioned. "Cardiologists were blinded to all subject demographic data and echocardiogram findings during annotation."

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:

• No MRMC comparative effectiveness study described.

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

• Yes, the presented performance is for the EFAST algorithm in a standalone capacity ("EFAST Heart Sound Timing Performance").

7. The type of ground truth used:

• Expert cardiologist annotations of "timing of the S1 and S2 sounds."

8. The sample size for the training set:

• Not specified.

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

• Not specified.

Study Details: ECG Rhythm Classification (Atrial Fibrillation Detection)

2. Sample size used for the test set and the data provenance:

• Test set sample size: 1,256 ECG recordings (from 314 unique subjects). 97 recordings were excluded due to lack of expert agreement.
• Data provenance: Retrospective study of de-identified data. Two sites within the US.

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

• Number of experts: "Multiple experts."
• Qualifications: "Electrophysiologists, certified cardiographic technicians." No further specific qualifications (e.g., years of experience) are provided.

4. Adjudication method for the test set:

• "Multiple experts" annotated the recordings.
• For 97 recordings, "the experts did not come to an agreement," leading to their exclusion. Similar to the structural murmur study, this indicates an agreement-based adjudication where disagreement led to exclusion.

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:

• No MRMC comparative effectiveness study involving human readers with vs. without AI assistance is described. The comparison is between the EFAST algorithm's standalone performance and the predicate device's standalone performance ("Algorithm Performance Comparison to Predicate").

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

• Yes, the presented performance metrics (Overall Sensitivity, Overall Specificity) are for the EFAST algorithm operating in a standalone capacity ("EFAST Atrial Fibrillation Detection Performance" and "Algorithm Performance Comparison to Predicate").

7. The type of ground truth used:

• Expert annotations related to "quality and the presence of atrial fibrillation."

8. The sample size for the training set:

• Not specified.

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

• Not specified.

Study Details: Heart Rate Calculation

2. Sample size used for the test set and the data provenance:

• Not explicitly stated, but the performance is presented as a summary ("found to be less than 5%").

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

• Ground truth method not explicitly detailed in the summary, but typically for heart rate, it involves reference devices or manual counting from a known good signal.

4. Adjudication method for the test set:

• Not explicitly stated.

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:

• No MRMC comparative effectiveness study described.

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

• Yes, the performance is for the algorithm itself.

7. The type of ground truth used:

• Implied to be a reference standard for heart rate measurement.

8. The sample size for the training set:

• Not specified.

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

• Not specified.

Ask a specific question about this device

The RTM Vital Signs RTMsense is indicated for use by healthcare professionals in healthcare facilities, such as post-operative care and general wards, to monitor breathing in adult (at least 22 years old) patients.

RTMsense is a non-invasive system that graphically displays respiratory function against time and reports respiratory rate.

RTMsense measurements are used as an adjunct to other clinical information sources.

The RTMsense Respiratory Monitoring System is a single use wearable device consisting of a wearable trachea sound sensor (TSS) and software that continuously measures a patient's respiratory rate by analyzing the sounds of air flow within the proximal trachea during inhalation and exhalation. The acoustic signal is transmitted wirelessly to a Lenovo Tablet, and the respiratory measurement values are displayed on the tablet after analysis of the acoustic data by a proprietary software algorithm.

The RTMsense software application has three parts: firmware on the TSS, a web-based application on the Lenovo tablet, and a cloud-based proprietary software algorithm. The TSS securely transmits acoustic data wirelessly to the local, Bluetooth low energy enabled Lenovo tablet. The tablet uses a web-based application to securely transmit the acoustic data to the cloud for analysis in RTM's proprietary cloud-based algorithm. The web application retrieves the processed data from the algorithm to display respiratory rate on the tablet.

The device will be used by healthcare professionals in healthcare facilities such as post-operative care or general wards. The RTMsense respiratory measurements are used as an adjunct to other clinical information sources.

The TSS is held in place by a flexible wearable carrier adhered to the patient's proximal trachea with commercially available medical grade adhesive. The TSS contains the audio sensor, onboard processing, wireless communications technology, and Lithium-ion coin cell rechargeable battery. A custom charger is provided to charge the battery.

The provided FDA 510(k) clearance letter and summary for the RTM Sense (A-0001) device details several aspects of its performance and validation. However, it does not explicitly provide a table of acceptance criteria for specific metrics, instead focusing on overall "passing" of predefined performance criteria. The information regarding ground truth establishment for the training set, number and qualifications of experts, and adjudication methods is also limited.

Based on the provided text, here's an attempt to reconstruct the information:

Overview of RTM Sense (A-0001) Performance Study

The RTM Sense (A-0001) is a non-invasive respiratory monitoring system that continuously measures a patient's respiratory rate by analyzing tracheal sounds. The device, intended for use by healthcare professionals in healthcare facilities, underwent non-clinical and clinical performance testing to demonstrate its safety and effectiveness and establish substantial equivalence to predicate devices.

1. Acceptance Criteria and Reported Device Performance

While explicit acceptance criteria are not presented in a table format within the document, the "Clinical Performance Testing" section describes primary endpoints that serve as de facto acceptance criteria. The results indicate that the device met these criteria.

Note: The acceptance criteria are inferred from the "Primary endpoints assessed were accuracy ≤ 1 BPM and mean accuracy error < 5%."

2. Sample Size and Data Provenance for Test Set

• Total Sample Size: Combined, the studies included 44 subjects and over 150 breath samples.
  • Study #1: 31 subjects and 124 breath samples.
  • Study #2: 13 subjects and 65 breath samples.
• Data Provenance: The document does not explicitly state the country of origin. It indicates that the studies were prospective comparative studies.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method for the test set. Ground truth was established by "Manually scored End-Tidal CO2 breath counts from the capnometer." This suggests a direct technical measurement rather than expert consensus requiring adjudication.

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

No MRMC study was conducted or reported. The study design focused on comparing the device's measurements directly against a gold standard (capnometer), not on how AI assistance improves human reader performance. Therefore, no effect size for human reader improvement with AI assistance is provided.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was conducted. The "Clinical Performance Testing" directly evaluates the RTMsense device's (which includes its proprietary software algorithm) accuracy against a gold standard respiratory measurement (Hamilton C-1 Ventilator with integrated Capnostat 5 capnometer). The reported results (accuracy, bias, % error) are based on the algorithm's performance in calculating respiratory rate from acoustic signals.

7. Type of Ground Truth Used

The ground truth used for the clinical performance testing was technical measurement/outcomes data. Specifically, "Manually scored End-Tidal CO2 breath counts from the capnometer" from a Hamilton C-1 Ventilator with integrated Capnostat 5 capnometer were used as the gold standard reference.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set. It only describes the clinical validation (test set) data.

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

The document does not describe how the ground truth for the training set was established. It only refers to "RTM's proprietary cloud-based algorithm" that processes acoustic data and "Software Verification / Validation Testing" which states "Integration and algorithm testing was conducted to verify the software meets its requirements and accurately reports respiration rate." This implies internal validation of the algorithm, but details about the training data and its ground truth establishment are absent.

Ask a specific question about this device

The AeviceMD is a non-invasive battery-operated device, including a wearable component, intended to longitudinally acquire, record and store lung sounds from pediatric patients (aged 3 years and above) in a clinical or non-clinical setting. The device stores the data for later playback, review, and analysis by a clinician and comparison with earlier data from the same patient.

The AeviceMD is designed as an electronic stethoscope to acquire and record lung sounds from users for healthcare professionals (HCP) to playback and interpret the sounds recorded. AeviceMD does not contain any alarm feature and it is not intended for emergency use. It is also not a sleep apnea device. The device is not intended for self-diagnosis.
The AeviceMD consists of hardware and embedded software. It is a five-part system that includes the following components:

1. AeviceMD Sensor – an embedded electronic wearable device that detects and records lung sounds and transmits data to an electronic gateway via Bluetooth.
2. AeviceMD Silicone Patch – silicone patch that houses and attaches the Sensor to the user's body (i.e., chest). This silicone patch undergoes biocompatibility testings which allow AeviceMD Sensor to be worn on the skin.
3. AeviceMD Docking Station – gateway device that serves as a computational hub and linkage from the Sensor to the Cloud Platform, and as a charger for the Sensor.
4. AeviceMD App (for patients) / AeviceMD HCP Web App (for healthcare professionals) - The AeviceMD App is a mobile app that downloads the post-processed information from the Cloud Platform and presents users with their recorded lung sounds at the auscultation locations which they can share with their HCP during their next consultation. A separate app, AeviceMD HCP Web App is tailored for HCP to review their patient's data in a clinical setting.
5. AeviceMD Cloud Platform – secure cloud server that receives data from gateway units and analyzes user's data using meaningful output information.

I'm sorry, but the provided FDA 510(k) Clearance Letter for AeviceMD (K243603) does not contain the detailed information necessary to fully answer your request.

Specifically, the document does not include any acceptance criteria or a study demonstrating that the device meets such criteria. It primarily focuses on:

• Substantial Equivalence: Comparing the AeviceMD to a predicate device (AeviceMD K223382) and a reference device (Eko CORE K200776) to establish similar intended use and technological characteristics.
• Non-Clinical Performance Data: Listing the standards and additional testing performed (e.g., biocompatibility, electrical safety, usability, shipping validation, cleaning validation, frequency response test, stethoscope performance test). However, it does not provide the results of these tests or specific performance metrics that could be construed as acceptance criteria.
• Indications for Use: Defining what the device is intended for.

Therefore, I cannot extract the following information from the provided text:

1. A table of acceptance criteria and the reported device performance: This information is not present.
2. Sample size used for the test set and the data provenance: While a "Stethoscope Performance Test against a 510(k) cleared reference stethoscope" is mentioned, no details about the sample size, data provenance, or the results are provided. The statement "The reference device was used to demonstrate effective performance in a pediatric population aged 3 years and above" suggests a study was done, but no details are given.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method: Not mentioned.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size: Not mentioned. The device is for recording and analysis by a clinician, but no study on AI assistance is detailed.
6. If a standalone performance (i.e., algorithm only without human-in-the-loop performance) was done: The document describes the device as recording sounds for later "playback, review, and analysis by a clinician," implying human-in-the-loop. However, it also mentions the "AeviceMD Cloud Platform" analyzes user data using "meaningful output information," which could hint at an algorithm, but no standalone performance data for such an algorithm is provided.
7. The type of ground truth used: Not mentioned.
8. The sample size for the training set: Not mentioned.
9. How the ground truth for the training set was established: Not mentioned.

In summary, the provided document from the FDA clearance process primarily focuses on demonstrating substantial equivalence through comparison with existing devices and compliance with safety and performance standards, rather than detailing a specific clinical performance study with acceptance criteria and results.

Ask a specific question about this device

The AS-101 is an electronic stethoscope intended for the detection and amplification of sounds associated with the heart, lungs, arteries, veins, and other internal organs. It can be used on any person undergoing a physical assessment. The device is intended to be operated only by healthcare professionals for diagnostic decision support in clinical settings.

This submission is for device "The AccurSound Electronic Stethoscope AS-101 ("AS-101")". This submission expands upon a previously 510(k)-cleared device(K221805) by introducing two new reusable sensors, whereas the original device only included disposable sensors..

The AccurSound Electronic Stethoscope AS-101 ("AS-101") in this submission is a device designed for healthcare professionals used in clinical settings. The AS-101 can detect and amplify the sounds of the heart, lungs, arteries, veins, and other internal organs.

The microphone-equipped sensor detects and amplifies the sounds from the patient's body. The auscultation sound is digitally processed and filtered, electronically amplified in the hub unit. The anti-noise function reduces ambient noise and echoes, then transferred to the earpiece.

The multi-channel design allows healthcare professionals to attach disposable sensors or reusable sensors onto patient's body, by switching modes from handheld single-channel recording to four-channel stationery and continuously auscultation based on different requirements of clinical applications or physical assessments.

The provided text is a 510(k) Premarket Notification for the AccurSound Electronic Stethoscope (AS101), which is a modification of a previously cleared device (K221805). The modification involves the introduction of two new reusable sensors, whereas the original device only included disposable sensors. Based on the document, here's an analysis of the acceptance criteria and supporting studies:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly present a table of acceptance criteria with corresponding performance results for specific clinical metrics. Instead, it relies on non-clinical testing and the substantial equivalence to the predicate device. The performance tests mentioned are general and not detailed with specific quantitative acceptance criteria in this document.

However, based on the information provided, the following non-clinical tests were conducted to ensure safety and performance:

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

The document explicitly states: "This submission does NOT include animal or clinical performance testing." Therefore, there is no clinical test set, sample size, or data provenance (country of origin, retrospective/prospective) to report for the primary evaluation of this device (the modified AS-101 with reusable sensors). The assessment relies on non-clinical bench testing and the substantial equivalence to the predicate device.

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

As there was no clinical study conducted for this submission (specifically for the modified device), there is no information on experts used to establish ground truth.

4. Adjudication Method for the Test Set

Not applicable as there was no clinical test set.

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

No MRMC comparative effectiveness study was done. The document states: "This submission does NOT include animal or clinical performance testing."

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Not applicable. This device is an electronic stethoscope intended for use by healthcare professionals for direct patient assessment, not an AI algorithm acting in a standalone capacity. The "diagnosis decision support" refers to the device aiding the human professional, not replacing them or offering an automated diagnosis.

7. Type of Ground Truth Used

For the non-clinical tests conducted, the "ground truth" would be established by the industry standards and regulatory requirements themselves (e.g., passing specific electrical safety thresholds, demonstrating biocompatibility as per ISO standards, software functioning as specified). There is no "ground truth" in the sense of clinical reference diagnoses (e.g., pathology, outcomes data, expert consensus) because no clinical performance testing was performed for this submission.

8. Sample Size for the Training Set

Not applicable. The AccurSound Electronic Stethoscope is a hardware device for sound amplification and filtering. It does not appear to incorporate machine learning or AI that would require a "training set" in the conventional sense of AI/ML algorithms. The software mentioned is for device control and processing, verified through standard software validation, not through learning from data.

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

Not applicable, as there is no training set mentioned or implied.

Ask a specific question about this device

Stethophone Pro is an electronic stethoscope that enables detection, filtering, and transmission of auscultation sound data (heart and lungs).

Stethophone Pro is intended to provide decision support to clinicians in their evaluation of patients heart sounds. The software analyzes heart sounds and phonocardiograms and can automatically detect murmurs that may be present, sound timing and character, including S1, S2, and the absence of a heart murmur.

Stethophone Pro is not intended to be used as a sole means of diagnosis and is for use in environments where health care is provided by clinicians. The interpretations offered by the software are meant only to provide decision support to the clinician, who may use the result in conjunction with their own evaluation and clinical judgment. The interpretations are not diagnoses. Stethophone Pro is intended for use on adult patients.

Stethophone Pro is an electronic stethoscope software application that operates on smartphones. Stethophone Pro is designed for use by healthcare professionals or on the order of healthcare professionals.
Stethophone Pro enables the capture and amplification of chest sounds for real-time or recorded listening. Cloud storage with sound record sending capabilities, filtering for selected frequency ranges, and visualization all assist with sound analysis.

Stethophone Pro is designed to assist healthcare professionals in both hearing and visualizing heart and lung sounds during a physical examination of a patient and in storing recorded sounds in the cloud for later analysis. It also enables home users to record and send chest sounds to their physicians.

Stethophone Pro can be used for the assessment of chest sounds of adult patients in clinical and non-clinical environments. Assessment is performed by healthcare professionals, while sound capturing can be performed by both healthcare professionals and home users.

Stethophone Pro performs basic analysis of heart sounds allowing to detect the presence of murmurs, locate heartbeats on the timeline (S1/S2), and calculate timing between them.

Key product features:

• Capturing chest sounds using the smartphone microphone:
  • Real-time listening to chest sounds,
  • Recording of chest sounds,
• Sending examinations to specialists for assessment,
• Two modes of sound visualization: oscillogram and spectrogram,
• Detecting murmurs, timing for S1 and S2 sounds, and calculating heart rate,
• Selecting from three audio filters for listening:
  • Bell: Traditional filter used in stethoscopes for low frequency sounds,
  • Diaphragm: Traditional filter used for higher frequency sounds of heart and lungs, and
  • Starling: Filter for listening to the full frequency of chest sounds.

Collectively, these features enable users to acquire heart sounds and receive basic reporting, so as enable healthcare professionals to examine and monitor patients on site and remotely, seek out second opinions from specialists, and use the device in a telemedicine context.

Here's a breakdown of the acceptance criteria and study details for the Stethophone Pro, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a pass/fail form (e.g., "must achieve >X% sensitivity"). Instead, it presents the reported performance metrics. For this response, I will list the reported performance metrics as the de facto "met performance" from the validation study.

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

• Sample Size (Test Set): 7,304 heart sound recordings from 2,277 adult subjects.
• Data Provenance: The data consisted of both proprietary and public clinical data. 4,396 recordings were from a proprietary dataset, recorded using various devices including smartphones and commercially available stethoscopes. Data appears to be from adult subjects ranging from 18 to 91 years old. Ethnicity representation: 86.1% white, 6.1% Latino, 5.0% Asian, and 2.7% African American. The country of origin for the "America" dataset or "Multi-Device" dataset is not explicitly stated but implies a broad representation. The study was retrospective.

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

• Number of Experts: "Multiple expert cardiologists." The exact number is not specified beyond "multiple".
• Qualifications: "Expert cardiologists." Specific experience levels (e.g., "10 years of experience") are not provided.

4. Adjudication Method for the Test Set

The document states that "Each recording in a testing dataset was annotated by multiple expert cardiologists." It does not explicitly describe an adjudication method (such as 2+1 or 3+1 consensus). It simply states they were annotated by multiple experts, implying that their annotations formed the ground truth, likely through consensus or independent review that established the final label.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

• No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not explicitly stated or described. The performance data presented is for the standalone algorithm.

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

• Yes, a standalone performance study was done. The results presented in the tables (S1 precision, S2 sensitivity, Murmur detection, etc.) are for the "Stethophone Pro algorithms for heart sound analysis," without mentioning human-in-the-loop performance. The preamble to the performance data states: "Stethophone Pro underwent a thorough testing process to ensure its safety, reliability and effectiveness. Testing included both software verification and validation, as well as clinical validation." And "Stethophone Pro algorithms for heart sound analysis have been validated in both retrospective and clinical performance testing..." This confirms standalone algorithm performance.

7. The Type of Ground Truth Used

• Expert Consensus: The ground truth for heart sound analysis (presence of murmur, S1/S2 timings) was established by "multiple expert cardiologists" who annotated each recording.

8. The Sample Size for the Training Set

• The sample size for the training set is not provided in the document. It only states that there was "no overlap between subjects and recordings included in the testing and training data."

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

• The document does not specify how the ground truth for the training set was established. It only mentions that the "validation was performed after the algorithm development and training was finalized."

Ask a specific question about this device

The Tyto Insights for Crackles Detection is an over-the-counter artificial intelligence (AI) enabled decision support software system used in the evaluation of lung sounds in adults and pediatrics (2 years and older). It automatically analyzes the acoustic signal of the lung as recorded by the FDA 510k cleared compatible Tyto Stethoscope and identifies recordings where a specific abnormal lung sound suggestive of "Crackle" is suspected. It is not intended to detect other abnormal or normal lung sounds. A licensed health care professional’s advice is required to understand the meaning of the Tyto Insights for Crackles Detection result. Healthcare providers should consider the device result in conjunction with recording and other relevant patient data.

The Tyto Insights for Crackles Detection is a web-based (AI) enabled software system designed to aid in the clinical assessment of lungs auscultation sound data by analyzing recorded lung sounds to determine whether a Crackle is detected within the recorded sound data. The Tyto Insights for Crackles Detection Software is intended to process recordings from the FDA-cleared compatible Tyto Stethoscope (Tyto Stethoscope, K181612). The acquisition of the acoustic data (recordings) is carried out by a professional user in a clinical environment or by a lay- user in a non-medical environment, in compliance with the labeling of the Tyto Stethoscope. The system is composed of the following sub-systems:

• The Tyto Insights for Crackles Detection Application Server (APS) communicates with 1. the Tyto Insights for Crackles Detection Algorithm Server (ALS) and implements an application programming interface (API) for communication with the telehealth server.
• The Tyto Insights for Crackles Detection Algorithm Server (ALS) receives an audio file 2. as input and returns an analysis result of positive or negative regarding whether a Crackles was detected as output.
• The Tyto Insights for Crackles Detection Web Server (WBS) provides a graphic 3. indication whether a Crackles is detected in the recording. It can be utilized both in patient and clinician side.
  All the software subsystems (servers and storage) are hosted in the cloud and communicate through IP network.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for "Tyto Insights for Crackles Detection":

Product Information:

• Trade/Device Name: Tyto Insights for Crackles Detection
• Regulation Number: 21 CFR 868.1900
• Regulation Name: Diagnostic Pulmonary-Function Interpretation Calculator
• Regulatory Class: Class II
• Product Code: PHZ
• Intended Use/Indications for Use: An over-the-counter AI-enabled decision support software system for evaluating lung sounds (adults and pediatrics 2+ years) recorded by the compatible Tyto Stethoscope. It identifies recordings where "Crackle" is suspected. It is not intended to detect other abnormal/normal lung sounds. Requires a licensed healthcare professional's advice to interpret results, which should be considered with other patient data.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The acceptance criteria for Sensitivity and Specificity (LCI > 0.6279 and LCI > 0.9668, respectively) are specifically laid out in the "Predetermined Change Control Plan (PCCP)" section for modifications to the device. For the initial submission, the primary endpoint focused on the non-inferiority of the device's AUC compared to clinical readers. The reported standalone sensitivity and specificity are actual performance metrics from the validation study.

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

• Test Set Sample Size: 446 recordings (120 Crackles positive, 326 Crackles negative). This corresponded to a total of 445 patients.
• Data Provenance: Retrospective validation dataset. Recordings were obtained from the real-world use of the Tyto Care FDA-cleared compatible Tyto Stethoscope (K181612). The document does not specify the country of origin for the data.

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

• Number of Experts: Three (3) blinded experienced Pulmonologists.
• Qualifications: "Experienced Pulmonologists" are specified. Further details on years of experience or specific board certifications are not provided in the summary.

4. Adjudication Method for the Test Set

• Adjudication Method: Binary ground truth was determined by a majority vote of the three blinded Pulmonologists. This is a form of 3+ Consensus.

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

• MRMC Study Done?: A comparative effectiveness study was done comparing the device (AI) performance to "clinical readers" (Physicians non-Pulmonologists). However, this was an AI-only vs. human-only comparison, not a "human reading with AI assistance vs. human reading without AI assistance" MRMC study.
• Effect Size of Human Improvement with AI: This study did not assess how much human readers improve with AI assistance. It directly compared the AI algorithm's performance to human clinical readers.
  • Device AUC: 0.97 (0.95–0.98)
  • Clinical Readers AUC: 0.77 (0.73–0.8)
  • Difference in AUC (Device - Clinical Readers): 0.2 (0.17–0.23). This indicates the AI algorithm significantly outperformed the clinical readers in this specific comparison, establishing non-inferiority (and superiority) based on the defined margin.

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

• Standalone Study Done?: Yes.
• Performance Metrics:
  • Sensitivity: 0.72 (0.63-0.79)
  • Specificity: 0.99 (0.97–1.00)
  • Positive Predictive Value (PPV): 0.63 (0.4-0.87)
  • Negative Predictive Value (NPV): 0.99 (0.98-0.99)

7. The Type of Ground Truth Used

• Type of Ground Truth: Expert Consensus. Specifically, a majority vote of three blinded experienced Pulmonologists on the presence or absence of "Crackle" in the lung sound recordings.

8. The Sample Size for the Training Set

• The document does not specify the exact sample size for the training set. It mentions that the device utilizes a CRNN (Convolutional Recurrent Neural Network) model and that "Each network is trained based on the target clinical class." However, it only provides details for the retrospective validation dataset.

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

• The document does not explicitly describe how the ground truth for the training set was established. It primarily focuses on the ground truth establishment for the validation set used for performance evaluation. It's generally assumed that similar expert-driven annotation methods would be used for training data, but this is not detailed in the provided summary.

Ask a specific question about this device

The Keikku is an electronic stethoscope that enables amplification, filtering, and transmission of auscultation data of the patient (heart, lungs, bowel, arteries, and veins), whereby a clinician at one location on a network can listen to the auscultation data of a patient on site or at a different location on the network. The Keikku is intended for use on pediatric and adult patients. The Keikku 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.

The Keikku (Rx) is a digital stethoscope device designed for use by health care professionals in clinical settings and by lay users in non-clinical environments under healthcare provider supervision. The Keikku electronically amplifies, filters and transfers body sounds through the accompanying mobile application and is used for storage, sharing and transmitting the data for telemedicine use. It also enables lay users, under supervision from a healthcare provider, to listen to their body sounds (lungs, heart, arteries, veins, gastrointestinal tract, etc.), record and share it with their physicians during telehealth sessions. The Keikku consists of two primary components: 1. The Keikku device is an electronic stethoscope. The Keikku device is used for recording audio, converting it to digital data, and transmitting the data to a mobile device via Bluetooth®. It includes volume adjustment via rotation, tap feature for starting and ending the recording, and an LED light indicator for indicating the status of the device. 2. The Keikku App. The app captures audio data from the Keikku device and provides data visualization and annotation, secure data storage, audio playback, and sharing features. These features enable a healthcare professional to monitor patients, seek second opinions from a specialist or use the device for telemedicine use.

The provided text describes the Keikku Electronic Stethoscope and its substantial equivalence determination to predicate devices. However, it does not contain specific acceptance criteria or a detailed study that proves the device meets such criteria in the format explicitly requested.

The document states that "The test passed and met the predefined acceptance criteria" for performance testing related to audio frequency and NSR response, but it does not specify what those acceptance criteria were or present the reported device performance in a table. It also refers to usability evaluation as having "passing results" without detailing the study or its criteria.

Therefore, I cannot fully complete the requested table and answer all questions due to the lack of explicit information in the provided text.

Based on the available information, here is what can be extracted and what is missing:

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not specified in the provided text for any of the performance studies.
• Data Provenance: Not specified in the provided text.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

• Not specified. The document repeatedly refers to "tests" and "evaluations" but does not mention expert involvement in establishing ground truth for any test sets beyond general usability studies.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not specified.

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

• No MRMC comparative effectiveness study is mentioned. The device's primary function is as an electronic stethoscope for amplification, filtering, and transmission of auscultation data, not an AI-assisted diagnostic tool for human readers.

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

• This question is not directly applicable in the context of an electronic stethoscope as described. The device itself (Keikku Electronic Stethoscope) performs sound capture, amplification, and filtering. It is inherently a "standalone" device in its primary functionality. However, it works with an accompanying mobile application for data visualization, storage, and sharing, and facilitates human practitioners' listening. There's no separate "algorithm only" performance reported that would be distinct from the device's inherent operation.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• The document primarily describes engineering and validation testing (biocompatibility, cleaning/disinfection, electrical safety, EMC, software). For the "Performance Testing," it states the purpose was "to verify the Keikku's performance is similar to that of its predicate and reference devices, Eko Core and 3M Littmann electronic stethoscope, in terms of audio frequency and NSR response." This implies the "ground truth" for performance was defined by the established performance characteristics of the predicate and reference devices, rather than a clinical ground truth like pathology or expert consensus on clinical diagnoses.

8. The sample size for the training set

• Not applicable as the document does not describe any machine learning models that would require a "training set." The Keikku device provides amplification, filtering, and transmission, but it's not described as having an AI component that is "trained" in the typical sense.

9. How the ground truth for the training set was established

• Not applicable (see point 8).

Ask a specific question about this device

The CORE 500 Digital Stethoscope is intended to be used by clinicians or lay users to electronically amplify, filter, and transfer body sounds and three lead electrocardiogram (ECG) waveforms. The CORE 500 Digital Stethoscope also displays ECG waveforms and heart rate on the display and accompanying mobile application (when prescribed or used under the care of a clinician or by lay users).

A lay user is not intended to interpret or take clinical action based on the device output without consulting with a qualified healthcare professional.

CORE 500 Digital Stethoscope (CORE 500) is an electronic stethoscope with integrated electrodes for electrocardiogram (ECG). The device consists of a chestpiece, detachable earpiece (Eko Earpiece) and a mobile application (Eko App) and is intended as a digital auscultation tool on patients requiring physical assessment by the clinicians or lay users. CORE 500 provides the ability to amplify, filter, and transfer body sounds with the chestpiece diaphragm, and three lead ECG through electrodes integrated around the chestpiece. The device can be used in a professional healthcare facility and for home use.

CORE 500 features three auscultation modes for a better auscultation experience by filtering acoustic data and enhancing the primary frequency range of particular body sounds: Cardiac Mode for heart sounds, Pulmonary Mode for lung sounds, and Wide Band Mode for general auscultation. CORE 500 also detects and computes the heart rate in real time based on the phonocardiogram (PCG) data.

This FDA 510(k) summary for the Eko Health, Inc. CORE 500 Digital Stethoscope (K233609) describes the device's technical specifications and how it compares to a predicate device. Regarding acceptance criteria and detailed study results, the document provides a general overview rather than specific performance metrics.

Here's an analysis of the provided information concerning acceptance criteria and study details:

1. A table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria with corresponding reported device performance values for the CORE 500 Digital Stethoscope in the way one might expect for a clinical performance study. Instead, it lists the types of nonclinical testing performed and asserts that the device complies with standards or demonstrates performance.

Here's a summary of the reported performance without specific numerical acceptance criteria from the document:

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

The document does not provide specific sample sizes for test sets, data provenance, or whether studies were retrospective or prospective. The performance data section focuses on nonclinical testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

This information is not provided in the document. The performance data is described as "nonclinical testing" and does not appear to involve expert-adjudicated ground truth as typically found in clinical studies assessing diagnostic accuracy.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

This information is not provided. As the document focuses on nonclinical performance, an adjudication method on a clinical test set is not described.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The device, the CORE 500 Digital Stethoscope, is primarily an electronic stethoscope for amplifying, filtering, and transferring body sounds and ECG waveforms, and displaying ECG and heart rate. It is not described as having an AI diagnostic interpretation component that would typically be evaluated in an MRMC study with human readers.

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

The document does not explicitly state that a standalone (algorithm only) performance study was done for any specific AI functionality. The device displays ECG waveforms and heart rate, but the document does not describe it as having an autonomous diagnostic algorithm for complex conditions.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

Given that the performance data described is "nonclinical testing" (bench testing, biocompatibility, electrical safety, software V&V, usability), the concept of "ground truth" as it applies to clinical diagnostic accuracy (e.g., expert consensus, pathology) is not applicable or described in this section. The testing would have focused on meeting technical specifications and regulatory standards.

8. The sample size for the training set

The document does not mention a training set or its sample size. This type of information would typically be provided for devices involving machine learning or AI algorithms with extensive training phases, which is not the primary focus of the performance data in this submission.

9. How the ground truth for the training set was established

Since no training set is mentioned (see point 8), there is no information on how ground truth for a training set was established.

Summary of Device and Performance Context:

The K233609 submission for the CORE 500 Digital Stethoscope primarily focuses on demonstrating substantial equivalence to its predicate device (K230111) and a reference device (K200776), particularly for its expanded "Over-The-Counter Use" and inclusion of "lay users." The performance data provided are centered on foundational nonclinical tests to ensure safety, efficacy, and compliance with general device regulations and standards. It's not a submission for a novel diagnostic AI algorithm requiring extensive clinical performance studies with ground truth establishment by experts. The "nonclinical testing" confirms the device's technical functionality, biocompatibility, electrical safety, software validation, and usability for its intended purpose of amplifying, filtering, and transferring body sounds and ECG waveforms, and displaying basic heart rate and ECG.

Ask a specific question about this device

The Tyto Insights for Wheeze Detection is an over the-counter artificial intelligence (Al) enabled decision support software system used in the evaluation of lung sounds in adults and pediatrics (2 years and older). It automatically analyzes the acoustic signal of the lung as recorded by the FDA cleared compatible Tyto Stethoscope and identifies recordings where a specific abnormal lung sound suggestive of "Wheeze" is suspected. It is not intended to detect other abnormal or normal lung sounds. A licensed health care professional's advice is required to understand the meaning of the Tyto Insights for Wheeze Detection result. Healthcare providers should consider the device result in conjunction with recording and other relevant patient data.

The Tyto Insights for Wheeze Detection is a web-based (AI) enabled software system designed to aid in the clinical assessment of lungs auscultation sound data by analyzing recorded lung sounds to determine whether a Wheeze is detected within the recorded sound data.

The Tyto Insights for Wheeze Detection Software is intended to process recordings from the FDA-cleared compatible Tyto Stethoscope (Tyto Stethoscope, K181612). The acquisition of the acoustic data (recordings) is carried out by a professional user in a clinical environment or by a lay- user in a non-medical environment, in compliance with the labeling of the Tyto Stethoscope. The system is composed of the following sub-systems:

• 1. The Tyto Insights for Wheeze Detection Application Server (APS) communicates with the Tyto Insights for Wheeze Detection Algorithm Server (ALS) and implements an application programming interface (API) for communication with the telehealth server.
• 2. The Tyto Insights for Wheeze Detection Algorithm Server (ALS) receives an audio file as input and returns an analysis result of positive or negative regarding whether a wheeze was detected as output.
• The Tyto Insights for Wheeze Detection Web Server (WBS) provides a graphic 3. indication whether a wheeze is detected in the recording. It can be utilized both in patient and clinician side.

All the software subsystems (servers and storage) are hosted in the cloud and communicate through IP network.

Here's a breakdown of the acceptance criteria and study details for the "Tyto Insights for Wheeze Detection" device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" as a pass/fail threshold, but rather focuses on comparing the device's performance to its predicate and demonstrating non-inferiority. The key performance metrics are sensitivity, specificity, and Area Under the Curve (AUC).

Conclusion regarding acceptance criteria: The device met the primary endpoint of non-inferiority to the predicate device based on AUC, as the lower bound of the 95% CI for the difference in AUCs (0.0289) was well above the non-inferiority margin of -0.05.

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

• Sample Size for Test Set: 371 recordings, corresponding to 359 patients. (86 recordings were Wheeze positive and 285 negative).
• Data Provenance: Retrospective validation dataset sourced from real-world use of the FDA cleared compatible Tyto Stethoscope. The country of origin is not explicitly stated, but Tyto Care Ltd. is based in Israel.

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

• Number of Experts: Three blinded experienced Pulmonologists.
• Qualifications of Experts: Described as "experienced Pulmonologists." Specific details like years of experience are not provided.

4. Adjudication Method for the Test Set

• Adjudication Method: Binary ground truth was determined by a majority vote of the three blinded Pulmonologists. This implies a "3+1" approach where if at least two out of three experts agreed on the presence or absence of wheeze, that was considered the ground truth.

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

• There is no indication of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being performed with human readers with and without AI assistance. The study focused on the stand-alone performance of the AI algorithm and its non-inferiority to a predicate device's algorithm, not on the improvement of human readers with AI assistance.

6. If a Standalone Study (Algorithm Only Without Human-in-the-Loop Performance) was Done

• Yes, a standalone study was done. The performance evaluation section explicitly states: "For the characterization of the stand-alone accuracy, the automated binary result of the software has been compared to ground truth and specificity and sensitivity were calculated." and "The primary end point was area under the Curve (AUC) for the detection of wheezes by the proposed device compared to the TytoCare Lung Sounds Analyzer (K221614)".

7. The Type of Ground Truth Used

• Type of Ground Truth: Expert consensus. Specifically, the binary ground truth was determined by a majority vote of three blinded experienced Pulmonologists.

8. The Sample Size for the Training Set

• The sample size for the training set is not explicitly provided in the document. The text states: "The AI Algorithm was trained with recordings acquired by the real-world use of the compatible Tyto Stethoscope."

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

• The document states that the AI algorithm was "trained with recordings acquired by the real-world use of the compatible Tyto Stethoscope." However, it does not explicitly detail how the ground truth for this training set was established. It can be inferred that a similar expert labeling process might have been used, but this is not confirmed in the provided text.

Ask a specific question about this device