Search Results

The SignalHF System is intended for use by qualified healthcare professionals (HCP) managing patients over 18 years old who are receiving physiological monitoring for Heart Failure surveillance and implanted with a compatible Cardiac Implantable Electronic Devices (CIED) (i.e., compatible pacemakers, ICDs, and CRTs).

The SignalHF System provides additive information to use in conjunction with standard clinical evaluation.

The SignalHF HF Score is intended to calculate the risk of HF for a patient in the next 30 days.

This System is intended for adjunctive use with other physiological vital signs and patient symptoms and is not intended to independently direct therapy.

SignalHF is a software as medical device (SaMD) that uses a proprietary and validated algorithm, the SignalHF HF Score, to calculate the risk of a future worsening condition related to Heart Failure (HF). The algorithm computes this HF score using data obtained from (i) a diverse set of physiologic measures generated in the patient's remotely accessible pre-existing cardiac implant (activity, atrial burden, heart rate variability, heart rate, heart rate at rest, thoracic impedance (for fluid retention), and premature ventricular contractions per hour), and (ii) his/her available Personal Health Records (demographics). SignalHF provides information regarding the patient's health status (like a patient's stable HF condition) and also provides alerts based on the SignalHF HF evaluation. Based on an alert and a recovery threshold on the SignalHF score established during the learning phase of the algorithm and fixed for all patients, our monitoring system is expected to raise an alert 30 days (on median) before a predicted HF hospitalization event.

SignalHF does not provide a real-time alert. Rather, it is designed to detect chronic worsening of HF status. SignalHF is designed to provide a score linked to the probability of a future decompensated heart failure event specific to each patient. Using this adjunctive information, healthcare professionals can make adjustments for the patient based on their clinical judgement and expertise.

The score and score-based alerts provided through SignalHF can be displayed on any compatible HF monitoring platform, including the Implicity platform. The healthcare professional (HCP) can utilize the SignalHF HF score as adjunct information when monitoring CIED patients with remote monitoring capabilities.

The HCP's decision is not based solely on the device data which serves as adjunct information, but rather on the full clinical and medical picture and record of the patient.

Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for SignalHF:

Acceptance Criteria and Device Performance for SignalHF

The SignalHF device was evaluated through the FORESEE-HF Study, a non-interventional clinical retrospective study.

1. Table of Acceptance Criteria and Reported Device Performance

For ICD/CRT-D Devices:

For Pacemaker/CRT-P Devices:

2. Sample Size and Data Provenance for the Test Set

• Test Set (Clinical Cohort) Sample Size: 6,740 patients (comprising PM 7,360, ICD 5,642, CRT-D 4,116 and CRT-P 856 - Note: there appears to be a discrepancy in the total sum provided, however, "6,740" is explicitly stated as the 'Clinical cohort' which is the test set).
• Data Provenance: Retrospective study using data from the French national health database "SNDS" (SYSTÈME NATIONAL DES DONNÉES DE SANTÉ) and Implicity proprietary databases. The follow-up period was 2017-2021.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications (e.g., radiologist with 10 years of experience). However, the ground truth was "hospitalizations with HF as primary diagnosis" as recorded in the national health database, implying that these diagnoses were made by qualified healthcare professionals as part of routine clinical care documented within the SNDS.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method like 2+1 or 3+1 for establishing the ground truth diagnoses. The study relies on “hospitalizations with HF as primary diagnosis” from the national health database, suggesting that these are established clinical diagnoses within the healthcare system.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

There is no indication that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to evaluate human reader improvement with AI assistance. The study focuses solely on the standalone performance of the SignalHF algorithm.

6. Standalone Performance

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done. The FORESEE-HF study evaluated the SignalHF algorithm's performance in predicting heart failure hospitalizations based on CIED data and personal health records.

7. Type of Ground Truth Used

The ground truth used was outcomes data, specifically "hospitalizations with HF as primary diagnosis" recorded in the French national health database (SNDS).

8. Sample Size for the Training Set

• Training Cohort Sample Size: 7,556 patients

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

The document states that the algorithm computes the HF score using physiological measures from compatible CIEDs and available Personal Health Records (demographics). It also mentions that the "recovery threshold on the SignalHF score established during the learning phase of the algorithm and fixed for all patients". This implies that the ground truth for the training set, similar to the test set, was derived from the same data sources: "hospitalizations with HF as primary diagnosis" documented within the SNDS database. The training process would have used these documented HF hospitalizations as the target outcome for the algorithm to learn from.

Ask a specific question about this device

IM007 is intended for use by qualified healthcare professionals for the assessment of arrhythmias in Insertable Cardiac Monitor (ICM) ECG data.

IM007 supports downloading and analyzing data recorded in compatible formats from ICMs. This version of the IM007 only supports ECG data from Medtronic ICMs.

IM007 is intended to be electronically interfaced with other computer systems (remote monitoring platform) that supply the ECG data to IM007, and receive the output of IM007 (analysis) for viewing by the healthcare professionals. IM007 provides ECG signal processing and analysis, to detect asystole, bradycardia, atrial tachycardia or atrial fibrillation, ventricular tachycardia, normal rhythm and artifact.

IM007 is not for use in life supporting or sustaining systems or ECG monitor and Alarm devices.

IM007 interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

IM007 is a software medical device for the analysis of ECG signals from Insertable Cardiac Monitor (ICM) devices and confirms the presence or absence of arrhythmias. When it is interfaced with a compatible remote monitoring platform, IM007 provides additional data to healthcare professionals to support the analysis of abnormal episodes detected by ICM devices.

IM007 receives as input an ECG data signal via the Implicity remote monitoring platform, then processes the signal with a proprietary algorithm designed to detect arrhythmias and generates as output the result of the analysis to a remote monitoring platform.

IM007 comprises:

• . An algorithm (the Algorithm) that analyzes ECG files in order to detect cardiac rhythm abnormalities.
• A communication interface to external applications with the Algorithm and processing of ECG files. The API consists of 2 messaging queues (an input and an output).

IM007 works as follows:

• . IM007 receives input data (an ECG file and device parameters) from the remote monitoring platform using the input queue.
• . The file is processed by the Algorithm which delineates zones with abnormal waveforms (ECG signals not defined as normal sinus rhythm). The output format is a sequence of waveform labels/start time/end time.
• . IM007 sends a response to the Remote Monitoring Platform using the output queue.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Important Note: The provided text is a 510(k) summary and FDA clearance letter, which focuses on demonstrating substantial equivalence to a predicate device. It typically does not contain detailed descriptions of clinical studies, raw data, or specific statistical results as would be found in a full clinical trial report or scientific publication. Therefore, some information requested might be incomplete or inferred from the high-level descriptions.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with numerical targets. Instead, it refers to "specifications" and "intended use" being met by the device. The reported device performance is described as meeting these specifications and operating as intended. The "Non-clinical Performance" section states: "The results of the testing demonstrate that IM007 performs to its specifications and meets its intended use, which is substantially equivalent to that of the predicate device."

However, we can infer the types of performance criteria from the device's function: detecting specific arrhythmias. The comparison tables (Table 3) list the output classifications, implying that accurate detection of these events is the core performance metric.

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

• Sample Size for Test Set: The document simply states "ECG databases from the ANSI/AAMI EC57:2012 standard as well as Implicity proprietary databases." It does not specify the exact number of ECGs or patients in the test set.
• Data Provenance:
  • Country of Origin: Not specified in the text.
  • Retrospective or Prospective: Not specified, but generally, tests against established databases (like ANSI/AAMI EC57:2012) are retrospective in nature.

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

The document does not provide details on the number or qualifications of experts used to establish ground truth for the test sets. It mentions "qualified healthcare professionals" and "physicians and clinicians" in the context of the device's intended use and advisory nature, but not for the ground truth creation within the non-clinical performance study.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) used for establishing ground truth classifications within the test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was a MRMC study done? No, the document does not mention any MRMC comparative effectiveness study involving human readers with and without AI assistance. The non-clinical performance section describes algorithm-only testing ("algorithm performance") against databases.
• Effect size of human improvement with AI vs. without AI: Not applicable, as no MRMC study was described.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• Was a standalone study done? Yes. The "Non-clinical Performance" section explicitly states that "Algorithm performance testing was assessed using ECG databases from the ANSI/AAMI EC57:2012 standard as well as Implicity proprietary databases." This indicates testing of the algorithm itself, without human intervention during the assessment, to ensure it "performs to its specifications and meets its intended use."

7. Type of Ground Truth Used

The type of ground truth used is implied to be expert consensus or established annotations from standard databases. The reference to "ECG databases from the ANSI/AAMI EC57:2012 standard" suggests a comparison to pre-annotated data, often derived from expert review. For the "Implicity proprietary databases," it would likely also involve expert adjudication, but this is not explicitly detailed.

8. Sample Size for the Training Set

The document does not provide the sample size used for the training set. It only mentions that the algorithm is "based on Machine Learning technology" and was tested on "ECG databases from the ANSI/AAMI EC57:2012 standard as well as Implicity proprietary databases." It's common for these databases to serve dual purposes (training and testing, with appropriate splitting), but specific numbers are not given for either.

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. Given the mention of "Machine Learning technology" and "ECG databases from the ANSI/AAMI EC57:2012 standard," it is highly probable that the training data and its ground truth were derived from:

• Expert Consensus: Cardiologists or electrophysiologists reviewed and annotated ECG waveforms.
• Established Annotations: Standard, publicly or privately curated databases often come pre-annotated by clinical experts.

However, the specific methods for ground truth establishment for the training set are not detailed in this 510(k) summary.

Ask a specific question about this device