(123 days)
The Stethographics Heart STG is software intended to provide support to the physician in the evaluation of heart sounds in patients.
The product will acquire and record the acoustic signals of the heart and analyze these signals. The analysis procedure will identify specific heart sounds that may be present. Identified sounds include S1, S2, and suspected systolic murmurs.
The device is indicated for use in the clinical setting, by a physician or by trained personnel who are acting on the orders of a licensed physician. It in not intended as a sole means of diagnosis.
The interpretations of heart sounds offered by the Heart STG System are only significant when used in conjunction with physician over-read as well as consideration of all relevant patient data.
The Heart STG is software intended to provide support to medical personnel in the evaluation of heart sounds. The software records and analyzes an acoustic signal of the heart and aids the healthcare provider by marking S1, S2, and suspected systolic murmurs on the waveform.
As a complete system the Heart STG system consists of an electronic stethoscope and software running on a computer with Windows operating system. The user must provide a compatible electronic stethoscope and a computer.
The Stethographics Heart STG System is designed to provide support to physicians in evaluating heart sounds, specifically identifying S1, S2, and suspected systolic murmurs.
Here's a breakdown of its acceptance criteria and the study proving it meets them:
1. Table of Acceptance Criteria (Implicit) and Reported Device Performance
| Performance Metric | Acceptance Criteria (Stated Goal: Comparability to Expert Cardiologists) | Reported Device Performance (STG Data Set) | Reported Device Performance (Proctor Harvey Data Set) |
|---|---|---|---|
| Overall Percent Agreement with Experts | Comparable to inter-cardiologist agreement | 83% | 82% |
| Agreement with Murmur-Positive (Recall) | Comparable to inter-cardiologist agreement | 70% | 91% |
| Agreement with Murmur-Negative (Specificity) | Comparable to inter-cardiologist agreement | 93% | 62% |
| Heart Rate (HR) Correlation with Experts | High correlation (e.g., >0.90) | 0.96 | 0.91 |
2. Sample Sizes Used for the Test Set and Data Provenance
The device was evaluated using two test sets:
- STG Data Set:
- Sample Size: 91 sounds from 91 patients.
- Data Provenance: Prospective collection. The sounds were obtained from patients scheduled for echocardiography assessment. Specific country of origin is not explicitly stated, but the company is located in Boston, MA, suggesting a US origin for this data.
- Proctor Harvey Data Set:
- Sample Size: 363 sounds from 232 patients (63 from children, 300 from adults).
- Data Provenance: This is a retrospective, pre-existing dataset. It's described as "provided in the Clinical Auscultation of the Cardiovascular System, by Proctor Harvey and David C. Canfield," which is considered a "gold standard for teaching and covers a broad range of heart disorders." Its origin is likely academic/educational.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Three experienced cardiologists.
- Qualifications: "Experienced cardiologists." No specific years of experience are provided.
4. Adjudication Method for the Test Set
- Adjudication Method: 2+1 (two out of three cardiologists agreeing on the presence or absence of a murmur).
- "All sounds were graded by three experienced cardiologists. Ground truth was considered to be positive when 2 out of 3 cardiologists agreed on the presence of murmur." (This implies a similar rule for negative cases, though not explicitly stated for negative cases, the performance tables show agreement with 2/3 cardiologists positive and negative).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, an MRMC comparative effectiveness study was not done. The study design focuses on comparing the device's performance against expert consensus ground truth. While inter-cardiologist agreement is reported, there's no comparison of human readers with and without AI assistance to determine an effect size for improvement.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone performance study was done. The reported "Heart STG +" and "Heart STG -" values represent the algorithm's performance in identifying murmurs without human intervention, compared against the adjudicated ground truth.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (three experienced cardiologists, with a 2-out-of-3 agreement rule).
8. Sample Size for the Training Set
- Not explicitly stated. The document describes the "test sets" (STG data set and Proctor Harvey data set) but does not provide details on the training data used for the algorithm.
9. How the Ground Truth for the Training Set Was Established
- Not explicitly stated for the training set. Given the approach for the test sets, it is highly probable that the training data ground truth was also established by expert cardiologists. However, the document focuses exclusively on the ground truth establishment for the test (evaluation) datasets.
§ 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.