Search Results

The SensiCardiac Mobi is an electronic auscultatory device, intended to provide support to the physician in the evaluation of patients' heart sounds.

The product acquires and records the acoustic signals of the heart and analyzes these signals. The analysis procedure will identify specific heart sounds that may be present. Identified sounds include S1, S2, and suspected murmurs. The device is indicated for use in a clinical setting, by a physician or by trained personnel who are acting on the orders of a licensed physician. It is not intended as a sole means of diagnosis.

The interpretations of heart sounds offered by the SensiCardiac Mobi are only significant when used in conjunction with physician over-read as well as consideration of all other relevant patient data.

The SensiCardiac Mobi Diagnostic Heart Murmur Application is a decision support device intended to acquire, record, and anlyze heart sounds. It is used to distinguish between normal/ physiological and pathological heart murmurs by recording the acoustic signal of the heart by means of an electronic stethoscope.

The complete system is a software application comprising Sensi Diagnostic Heart Murmur Algorithm that runs on a hosted server environment with Linux operating system, a hand held device to capture patient data, instructions for use and the electronic stethoscope that captures the acoustic heart signals. The user must provide a compatible electronic stethoscope.

SensiCardiac Mobi is a decision support software package intended to assist medical examiners in heart auscultation.

The SensiCardiac Mobi system consists of the following components:

• 1. The Sensi Diagnostic Heart Murmur Algorithm running within a hosted environment with TCP/IP interfaces to:
  • o a hand held mobile device (iPhone 4S or later)
  • o A database with patient and health worker information
• 2. A hand held mobile device (iPhone 4S or later) with the following uses:
  • o electronic transfer of the medical device data (TCP/IP interface)
  • o the electronic interfacing and conversion of the electronic stethoscope audio signal.
  • o The electronic display of medical device data.
  • o Capturing of basic patient information.
• 3. A compatible electronic stethoscope with characteristics
  • o Recording Frequency Range: 20 Hz to 10,000 Hz
  • o Sampling Frequency: > 4.000 Hz
  • o Data Recording: Standard .wav files at resolution of 16bit, mono
  • Recording Time: o minimum 10 sec, maximum 30 sec
  • o Electronic stethoscope: compatible model: ThinkLabs Medical ds32a+
  • Number of Sensors: o 1

The Sensi Diagnostic Heart Murmur Algorithm distinguishes between normal/ physiological and pathological heart murmurs by analyzing the acoustic heart signals captured with an electronic stethoscope. The device will record the acoustic sound of the hear at the four main auscultation positions. The acoustic heart signal is analyzed to identify heart sounds that may be present, identified sounds include S1, S2 and suspected murmurs.

The Sensi Diagnostic Heart Murmur Algorithm or the application running on the hand held mobile device does not control the medical device (electronic stethoscope) or actively monitoring the patient.

Acceptance Criteria and Device Performance

Study Details:

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

   • Test set sample size: 1568 heart sounds.
   • Data provenance: Not explicitly stated but the "APCA Clinical Report" suggests a clinical setting. It's unclear if the data is retrospective or prospective, or the country of origin.

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

   • Not specified. The document only mentions "golden standard - echo" and "all patients were echoed," indicating that echocardiography results were used as the ground truth, but not the number or qualifications of experts interpreting these echoes.

3. Adjudication method for the test set:

   • Not specified. The ground truth was established by echocardiography, but the method for resolving discrepancies among echo interpretations (if multiple were involved) or for correlating echo findings with heart sounds is not detailed.

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 MRMC comparative effectiveness study involving human readers with and without AI assistance was reported in the provided text. The studies focused on the standalone performance of the device and its usability.

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

   • Yes, a standalone study was done. The "Development of a Pediatric Cardiac Computer Aided Auscultation Decision Support System" reports on the specificity and sensitivity of the algorithm itself, comparing its output to the "golden standard - echo."

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

   • Echocardiography (echo) was used as the "golden standard" for establishing ground truth, as mentioned in the "Development of a Pediatric Cardiac Computer Aided Auscultation Decision Support System" and the "APCA Clinical Report."

7. The sample size for the training set:

   • Not specified in the provided text. The document refers to validation and verification studies but does not detail the training set size for the algorithm's development.

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

   • Not specified. The document mentions the use of echocardiography as a "golden standard" for ground truth in evaluation studies, but it does not describe how ground truth was established specifically for the training data used to develop the Sensi Diagnostic Heart Murmur Algorithm.

Ask a specific question about this device

The SensiCardiac is an electronic auscultatory device, intended to provide support to the physician in the evaluation of patients' heart sounds. The product acquires and records the acoustic signals of the heart and analyzes these signals. The analysis procedure will identify specific heart sounds that may be present. Identified sounds include S1, S2, and suspected murmurs. The device is indicated for use in a clinical setting, by a physician or by trained personnel who are acting on the orders of a licensed physician. It is not intended as a sole means of diagnosis.

The interpretations of heart sounds offered by the SensiCardiac are only significant when used in conjunction with physician over-read as well as consideration of all other relevant patient data.

The Sensi Diagnostic Heart Murmur Software is a decision support device intended to acquire, record, and anlyze heart sounds. It is used to distinguish between normal/ physiological and pathological heart murmurs by recording the acoustic signal of the heart by means of an electronic stethoscope.

The complete system is a software package comprising Sensi Diagnostic Heart Murmur Software that runs on a computer with Windows operating system, instructions for use and the electronic stethoscope that captures the acoustic heart signals. The user must provide a compatible electronic stethoscope.

The Sensi system consists of the following components:

1. The Sensi Diagnostic Heart Murmur Software program running on a personal computer (PC) with interfaces to:
   o a compatible electronic stethoscope
   o A database with patient and health worker information
   o Functions to record, display, analyze, save and playback heart sounds.
2. A compatible electronic stethoscope with characteristics
   o Recording Frequency Range: 20 Hz to 10,000 Hz
   o Sampling Frequency: > 4,000 Hz
   o Data Recording: Standard .wav files at resolution of 16bit, mono
   o Recording Time: minimum 10 sec, maximum 30 sec
   o Acoustic Sensors: Electronic stethoscope; compatible models include: ThinkLabs Medical ds32a+, Meditron Master Elite, RNK PCP/PC Stethoscope.
   Number of Sensors: 0

The Sensi Diagnostic Heart Murmur Software distinguishes between normal/ physiological and pathological heart murmurs by analyzing the acoustic heart signals captured with an electronic stethoscope. The device will record the acoustic sound of the heart at the four main auscultation positions. The acoustic heart signal is analyzed to identify heart sounds that may be present, identified sounds include S1, S2 and suspected murmurs.

Here's a breakdown of the acceptance criteria and study information for the Sensi Diagnostic Heart Murmur Software:

1. Table of Acceptance Criteria and Reported Device Performance

Notes on Acceptance Criteria: The document primarily lists study results rather than explicit, quantified acceptance criteria for all studies. The acceptance criteria in the table are inferred from the positive framing of the results (e.g., scoring "more than 4 out of 5" implies an acceptance threshold). For accuracy, the acceptance criterion is implicitly "not worse than" the predicate devices.

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

• Comparative Study (Accuracy) - Sensi V2 Validation:
  • No specific sample size is provided for the test set used to determine Sensi V2's 69.7% accuracy. The document mentions "Sensi V1 achieves overall accuracy of 70.8%. Cardioscan achieves an accuracy of 67.9% Sensi V2 achieves overall accuracy 69.7%." This implies a comparison was made, likely on a common dataset or comparable datasets. Without further detail, it's impossible to determine the Sensi V2 specific test set size for this accuracy calculation.
  • Data Provenance: Not specified.
• Validation of Algorithms (Pediatric Population):
  • Sample Size: 1568 heart sounds.
  • Data Provenance: Not specified.
• Comparing Sensi V1 and Sensi V2 in a clinical screening environment:
  • Sample Size: 43 patients with cleft lips and palates.
  • Data Provenance: Not specified, but involved "a clinical screening environment." The data for Sensi V2 validation in this study was derived from a database recorded using Sensi V1.

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

This information is not explicitly provided in the document for any of the studies mentioned. The document refers to "pathological condition" and "normal/physiological and pathological heart murmurs," implying expert assessment, but the number and qualifications of those experts are not detailed.

4. Adjudication Method for the Test Set

This information is not explicitly provided in the document.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Its Effect Size

• Was it done?: No, a traditional MRMC comparative effectiveness study, evaluating human readers with and without AI assistance, is not described in this document. The "Comparative Study" mentioned only compares algorithmic accuracies (Sensi V1, Cardioscan, Sensi V2) directly. There is no mention of human reader performance improvement with AI assistance.

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

• Yes, the document presents results for the standalone algorithmic performance. The "Comparative Study" (Sensi V1: 70.8% accuracy, Cardioscan: 67.9% accuracy, Sensi V2: 69.7% accuracy) and the "Design verification of a CAA algorithm" (Specificity of 95% and sensitivity of 84%) are examples of standalone algorithm performance. The device is a "decision support software package," and its core function is to analyze heart sounds to "distinguish between normal/physiological and pathological heart murmurs," which are algorithmic functions without direct human intervention in the classification process itself.

7. The Type of Ground Truth Used

• The document refers to establishing "pathological condition" and distinguishing "normal/physiological and pathological heart murmurs." This strongly implies expert consensus or clinical diagnosis as the ground truth. For the pediatric study, it mentions "match the recorded pathological condition," which further supports this. There is no mention of pathology reports or direct outcomes data being used as ground truth.

8. The Sample Size for the Training Set

This information is not explicitly provided anywhere in the document. The document describes tests and validations but does not detail the training process or the size of any training datasets used to develop the algorithms.

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

This information is not explicitly provided in the document, as the training set details are absent.

Ask a specific question about this device