(170 days)
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.
| Metric (Heart Sound Analysis) | Dataset | Reported Performance (95% CI) |
|---|---|---|
| S1 Precision | America | 97.1 (96.7 to 97.5) |
| Multi-Device | 96.9 (96.6 to 97.3) | |
| S1 Sensitivity (Recall) | America | 97.3 (97.0 to 97.7) |
| Multi-Device | 97.9 (97.7 to 98.1) | |
| S2 Precision | America | 97.5 (97.2 to 97.9) |
| Multi-Device | 97.1 (96.7 to 97.4) | |
| S2 Sensitivity (Recall) | America | 96.5 (96.1 to 97.0) |
| Multi-Device | 97.7 (97.5 to 97.9) | |
| Murmur Detection Sensitivity | America | 88.7 (87.2 to 89.8) |
| Multi-Device | 93.0 (91.9 to 94.2) | |
| Murmur Detection Specificity | America | 89.2 (87.2 to 91.3) |
| Multi-Device | 94.4 (93.7 to 95.4) | |
| Murmur Detection Accuracy | America | 88.8 (87.6 to 89.8) |
| Multi-Device | 93.8 (93.2 to 94.6) | |
| Murmur Detection ROC AUC | America | 96.9 (96.1 to 97.3) |
| Multi-Device | 97.9 (97.5 to 98.3) | |
| Heart Rate MAE (bpm) | America | 0.482 (0.418 to 0.557) |
| Multi-Device | 0.389 (0.346 to 0.430) |
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."
§ 870.1875 Stethoscope.
(a)
Manual stethoscope —(1)Identification. A manual stethoscope is a mechanical device used to project the sounds associated with the heart, arteries, and veins and other internal organs.(2)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 870.9.(b)
Electronic stethoscope —(1)Identification. An electronic stethoscope is an electrically amplified device used to project the sounds associated with the heart, arteries, and veins and other internal organs.(2)
Classification. Class II (special controls). The device, when it is a lung sound monitor, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 870.9.