(49 days)
The CardioSleeve System consisting of the CardioSleeve Front-End stethoscope with integrated ECG device. mobile heart sound and ECG recording application and the remote diagnostic heart murmur software is a decision support device intended to be used on a single patient to assist the qualified clinician in analyzing cardiac sounds and electrical signals for the identification and classification including of suspected murmurs. It is used to distinguish between normal/physiological and pathological heart murmurs by recording the acoustic signal of the heart and the ECG signal simultaneously and analyzing these signals. The acoustic heart signal is analyzed to identify specific heart sounds that may be present. Identified sounds include S1, S2, and suspected murmurs.
CardioSleeve indicates whether or not a recorded heart sound contains a suspected heart murmur. The device must be used in a clinical setting by trained personnel with the prescribed accessories and all relevant patient information must be taken into consideration before a diagnosis is made.
The interpretations of heart sounds offered by the CardioSleeve device are only significant when used in conjunction with physician over-read as well as consideration of all other relevant patient data.
CardioSleeve is not intended to be a diagnostic device. It does not supersede the judgment of the clinician. The device is intended to aid the physician in the evaluation of heart sounds. The clinicians are responsible for reviewing and interpreting the results, along with the auscultatory findings and medical history, when making a referral decision.
Caution: Federal (USA) law restricts this device to sale by or on the order of a clinician
The CardioSleeve with Diagnostic Heart Murmur Application, (application identical to the FDA cleared Sensi with Diagnostic Heart Murmur Software-K110704), is a decision support device intended to acquire, record, and analyze heart sounds. It is used to distinguish between normal and pathological heart murmurs by recording the acoustic signal of the heart and the ECG signal simultaneously and analyzing these signals, and to acquire, record and display 3 Lead ECG signals for diagnostic support.
The complete system comprises of: a) Diagnostic Heart Murmur Algorithm (algorithm identical to the FDA cleared Diagnostic Heart Murmur Algorithm in K110704), that runs on a hosted server environment with Linux operating system, b) a mobile device software application that captures patient data, displays patient data and instructions for use and c) a stethoscope front-end recorder device with integrated ECG to acquire the acoustic and electrical heart signals. The CardioSleeve Front-end recorder device will interface via Bluetooth with the clinician's hand held mobile device.
Here's a breakdown of the acceptance criteria and the study information based on the provided 510(k) summary:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Biocompatibility | CardioSleeve material presented no issues of biocompatibility |
| Electrical Safety | Meets the requirements of IEC 60601-1: 2005 + CORR. 1 (2006) + CORR. 2 (2007) |
| Feasibility & Usability | On average, all users scored the usability of the CardioSleeve Software more than 4 out of 5 |
| Comparative accuracy (vs. Sensi system) | CardioSleeve and Sensi achieve comparable accuracy of 70.8% |
| Diagnostic Heart Murmur Algorithm Specificity | 94% |
| Diagnostic Heart Murmur Algorithm Sensitivity | 91% |
| Acoustic Performance (frequency response) | Responds to heart sound frequency of 20hz to 500hz |
Study Details
1. Sample sized used for the test set and the data provenance:
- Test Set Size: 1568 heart sounds (for the algorithm validation study to distinguish between functional and pathological heart murmurs in the pediatric population).
- Data Provenance: Not explicitly stated regarding country of origin or whether it was retrospective/prospective. The description mentions "pediatric population," implying clinical data, but no further specifics are given.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not explicitly stated. The document mentions that the 1568 heart sounds "were accepted to meet the criteria of good quality and match the recorded pathological conditions," which implies an expert assessment, but the number and qualifications of those experts are not provided.
3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not explicitly stated.
4. 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, a multi-reader, multi-case (MRMC) comparative effectiveness study with human readers assisted by AI was not explicitly described for this device. The documentation focuses on the device's performance in distinguishing murmurs and its equivalence to a predicate device. The device is described as a "decision support device" that should be used "in conjunction with physician over-read," but no specific study evaluating human performance improvement with or without AI assistance is detailed.
5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance evaluation of the algorithm was conducted. The "Design verification of a CAA algorithm" (Clinical Audit Algorithm, presumably related to the diagnostic heart murmur algorithm) reported a Specificity of 94% and Sensitivity of 91%. Additionally, the study validating algorithms for distinguishing functional/pathological murmurs in the pediatric population (which used 1568 heart sounds) appears to be a standalone evaluation of the algorithm's performance against established ground truth.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the algorithm validating the distinction between functional and pathological heart murmurs, the ground truth was based on "recorded pathological conditions" and "criteria of good quality." This implies a clinical diagnosis established by experts, likely based on a combination of auscultatory findings, medical history, and potentially other diagnostic tests, leading to a categorization of the heart sound as normal/physiological or pathological. It is most likely expert diagnosis/consensus, although not explicitly named.
7. The sample size for the training set:
- Not explicitly stated in the provided document. The 1568 heart sounds are referred to as being "accepted to meet the criteria... and match the recorded pathological conditions," which sounds more like a test/validation set. The training set size for the underlying algorithm is not disclosed.
8. How the ground truth for the training set was established:
- Not explicitly stated, as the training set details are not provided. However, given that the algorithm is "identical to the FDA cleared Diagnostic Heart Murmur Algorithm in K110704" (the predicate device), it can be inferred that the ground truth for the training set would have been established similarly to the test set, likely through expert clinical assessment of heart sounds against "recorded pathological conditions" by qualified medical professionals.
§ 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.