Search Results

The intended use of the CADScor System is to record heart sounds, murmurs and vibration for calculation of a patient specific score, indicating the risk of presence of coronary stenosis, as an aid in cardiac analysis and diagnosis.

Device Description

The CADScor System is a digital stethoscope for recording and quantifying acoustic noise from micro-turbulence originating from stenosis of the coronary arteries. Computational processing of a recording obtained from the chest surface of a patient is used to determine a coronary artery disease (CAD) risk score and associated risk classification.

Three components make up the CADScor System: the Docking station, the Acoustic Recording Sensor and the Patch. The docking station is responsible for charging and qualifying the sensor. These functionalities only happen when the Acoustic Recording Sensor is in direct contact with the docking station. An LED light indicates the status of the sensor. The Acoustic Recording Sensor contains a display, a microphone and an on/off button. The heart sound is recorded through a microphone and once the CAD risk score is calculated, it appears on the display screen. The patch is directly in contact with the patient's chest at the fourth left inter costal space (IC4-L) region. The patch provides a tight seal between the chest surface and the microphone to reduce the external noise that is picked up by the sensor. The patch is for single use only and is discarded after a CAD-score is calculated. A radiofrequency identification (RFID) tag in the patch is used to prevent the patch from being used more than once.

An algorithm is used to calculate a coronary artery disease (CAD) risk score. The algorithm analyzes 8 features of the acoustic recording and three clinical features that are manually inputted into the device by the clinician. The clinical inputs are age, gender and presence of hypertension. The eight acoustic features are put through a linear discriminate analysis and then put through a logistic regression with the clinical features. The risk score and associated categorization color are displayed on the acoustic sensor screen. There are two risk categories: low risk and elevated risk (Figure 2). Clinicians can use the score and categorization to aid in a clinician's determination of whether further testing is needed for a CAD diagnosis.

AI/ML Overview

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

CADScor System: Acceptance Criteria and Study Details

1. Table of Acceptance Criteria and Reported Device Performance

Test Type	Purpose	Acceptance Criteria	Reported Device Performance
Biocompatibility
Cytotoxicity	To identify any cytotoxic effects to the patient	No evidence of toxicity or cell lysis	PASS
Sensitization	To identify tissue reactions from the patch	No evidence of tissue reaction	PASS
Irritation	To identify tissue irritation	No evidence of tissue irritation	PASS
EMC & Electrical Safety	To conform to FDA-recognized standards for basic safety and essential performance of Medical Electrical Equipment	Adherence to IEC 60601-1-2:2014 and IEC 60601-1:2006 + A1:2013	Conforms to IEC 60601-1-2:2014 and IEC 60601-1:2006 + A1:2013
Software	To demonstrate that the device software met the software requirements (Moderate Level of Concern)	Software verification and validation testing performed; Algorithm unit testing to demonstrate software requirements met	Verification and validation testing performed; Algorithm unit testing performed using privately collected patient data.
Acoustic Performance
Free Field Acoustic Testing	Ensure the manufactured parts of the CADScor systems are performing according to test specifications	Heart and ambient microphone sensitive within 5dB throughout the range of frequencies tested	PASS
Microphone Sensitivity	Test microphone sensitivity before and after production	Sensitivity of the heart and ambient microphones are stable at 5, 10, 20, 140 Hz before and after the plotting process	PASS
Acoustic Verification	Ensure the manufactured CADScor Sensor functionality and performance	The sensor and ambient noise detectors respond uniformly to all seven frequencies (b)(4) and (b)(4) Hz, and broad band white noise.	PASS
Mechanical Testing	Verify the specified geometric proportions and mechanical lifetime	Manufactured to correct dimension specifications; Force to remove sensor from docking station is 5N; Qualification successful before and after 1000 insertions of the sensor onto the docking station.	PASS (Specific dimensions and force tests confirmed to be met. Qualification successful before and after 1000 insertions of sensor onto docking station.)
Usability Testing	To demonstrate that the user can correctly use the device, including device placement, based solely on reading the directions for use.	Successful completion of tasks in a simulated-use environment (e.g., correct patch positioning, entering clinical features, reading display).	Usability testing performed with medical doctors/physicians, registered nurses, and service technicians. Tasks included correct patch positioning, entering clinical features, and reading the display. (Outcome generally implied as successful to meet guidance requirements).
Clinical Performance	To determine the specificity and sensitivity of the CAD-score in patients with low-intermediate risk for ischemic heart disease. The device should aid clinicians in determining whether further testing is needed for a CAD diagnosis, particularly as a "rule-out" device for patients with suspected ischemic heart disease.	Primary Objective: Determine specificity and sensitivity in patients with low-intermediate risk for ischemic heart disease.
Effectiveness as a rule-out device: High Negative Predictive Value (NPV).	Sensitivity: 87.5% (for CAD-score threshold of 20)
Specificity: 37.5% (for CAD-score threshold of 20)
Area Under the Curve (AUC): 71.5%
Positive Predictive Value (PPV): 14.4%
Negative Predictive Value (NPV): 96.2%

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

Sample Size: 100 patients
Data Provenance: Prospective, multicenter, randomized clinical study. The country of origin of the data is not explicitly stated in the provided text, but the sponsor is based in Denmark.

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

The text 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 text does not explicitly state an adjudication method. It indicates that the patient's diagnosis (ground truth) was determined by Coronary Computed Tomography Angiography (CCTA).

CAD diagnosis: At least one significant stenosis (minimum 11% diameter reduction) of a coronary vessel.
Non-CAD diagnosis: CT calcium score of zero and no CT stenosis.

This suggests CCTA served as the definitive diagnostic reference, rather than a multi-expert consensus on the CADScor results themselves.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described. The clinical study focused on the standalone performance of the CADScor system against CCTA as ground truth, not on how human readers' performance improved with AI assistance.

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

Yes, a standalone performance study was done. The clinical study reported the sensitivity, specificity, AUC, PPV, and NPV of the CADScor system (algorithm output) for predicting CAD, which is a standalone assessment of the algorithm's performance. The results (87.5% sensitivity, 37.5% specificity, 96.2% NPV) are for the device's output itself, not for human interpretation aided by the device.

7. The Type of Ground Truth Used

The type of ground truth used for the clinical study was Coronary Computed Tomography Angiography (CCTA), with specific criteria for CAD (≥11% diameter reduction stenosis) and Non-CAD (CT calcium score of zero and no CT stenosis). This is a definitive diagnostic imaging modality.

8. The Sample Size for the Training Set

The sample size for the training set is not explicitly stated. The text only mentions that the 100 patients in the test set "were independent from the algorithm training set" and that algorithm unit testing used "privately collected patient data," but no specific number is given for the training set.

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

The text does not explicitly describe how the ground truth for the training set was established, other than mentioning that "privately collected patient data" was used for algorithm unit testing. Given the context of the clinical study, it is highly probable that similar diagnostic criteria (like CCTA) were used for establishing training set ground truth, but this is not confirmed in the provided document.

Ask a Question

Ask a specific question about this device

Page 1 of 1