Search Results

The Confirm Rx™ ICM is indicated for the monitoring and diagnostic evaluation of patients who experience unexplained symptoms such as the following: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atrial fibrillation or who are susceptible to developing atrial fibrillation.

The Confirm Rx™ ICM System consists of the following key features and components: Confirm Rx™ ICM Model DM3500 Implantable Device, Implant Tools (Incision tool model DM3520 and Insertion tool model DM3510), Confirm Rx ICM Accessory Kit DM3500A, Magnet, Clinician Programmer (Merlin PCS Programmer Model 3650), myMerlin™ Mobile Application (Model APP1000 (Android) and APP1001 (iOS)), and Remote Care/Clinician Portal (Merlin.net MN5000 Report Generator). The ICM is a minimally invasive, implantable diagnostic monitoring device with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability.

The provided text does not contain information about acceptance criteria for device performance or a study proving that the device meets specific performance criteria. Instead, it details a 510(k) premarket notification for an Abbott (St. Jude Medical) Confirm Rx™ Insertable Cardiac Monitor system (K202876).

This submission is for an Accessory Kit DM3500A and an updated incision tool DM3520 blade design for an already cleared device (predicate K193310). The document asserts substantial equivalence to the predicate device, meaning it argues that the new components do not raise new questions of safety or effectiveness and perform as well as the predicate.

The document states:

• "Completion of all verification and validation activities demonstrated that the Confirm Rx ICM accessory kit meets its predetermined design and performance specifications and that the product is substantially equivalent to the current device (Model DM3500, K193310)." (Page 9)
• "The results of the verification and validation tests and the risk analysis have demonstrated the candidate Confirm Rx ICM system with Accessory Kit DM3500A and updated incision tool DM3520 blade design functions in accordance with product specifications." (Page 9)
• "Product verification and validation testing demonstrate that the candidate Confirm Rx ICM system is as safe and as effective and performs as well as the predicate system (K193310)." (Page 9)

However, it does not provide a table of acceptance criteria and reported device performance for the new components or the system as a whole. It also does not describe a specific study with a test set, training set, expert ground truth, or adjudication methods in the context of device performance metrics (e.g., sensitivity, specificity for arrhythmia detection). The non-clinical test summary mentions a "risk analysis method... a Failure Mode and Effects Analysis (FMEA/FMECA)," but this is for assessing hazards and mitigating risks, not for evaluating performance against clinical acceptance criteria.

Therefore, I cannot fulfill your request for the detailed information as it is not present in the provided FDA document.

Ask a specific question about this device

The Confirm Rx™ ICM is indicated for the monitoring and diagnostic evaluation of patients who experience unexplained symptoms such as: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atrial fibrillation or who are susceptible to developing atrial fibrillation.

The Confirm RxTM ICM System consists of the following key features and components:

• Confirm RxTM ICM Model DM3500 Implantable Device: The ICM is intended as a minimally invasive, implantable diagnostic monitoring device, with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability, which help physicians monitor, diagnose, and document patients who are susceptible to cardiac arrhythmias.
• Implant Tools: Model DM3520 incision tool and Model DM3510 insertion tool are used to implant the device subcutaneously.
• Magnet: The magnet facilitates faster startup of Bluetooth connection and provides user authentication (required for programmer sessions).
• Clinician Programmer (Merlin PCS Programmer Model 3650): The Merlin PCS Programmer 3650 operates using Merlin PCS Model 3330 software and provides the means for the physician to program device parameters and retrieve diagnostic information from the device, including electrograms, heart rate history, episode duration and trend information.
• myMerlin™ Mobile Application (Model APP1000 (Android) and APP1001 (iOS)): The mobile application provides the means for the patient to activate EGM recording in the Confirm Rx™ device, with data pass-through functionality to enable physician follow-up via the Merlin.net Patient Care Network.
• Remote Care/Clinician Portal (Merlin.net MN5000 Report Generator): The Merlin.net system allows physicians to remotely monitor and diagnose patients' cardiac events.

This document is a 510(k) summary for the Abbott Confirm Rx Insertable Cardiac Monitor (ICM) with updated MR Conditional labeling. It focuses on demonstrating substantial equivalence to a previously cleared version of the device, specifically for MR Conditional labeling for 3T MRI environments. The acceptance criteria and study described primarily relate to this MR Conditional aspect, not the core cardiac monitoring functionality.

Here's the information extracted from the provided text, addressing your specific points:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the testing performed supports additional 3T MR Conditional labeling. It explicitly mentions that the "3T testing meets the same clinical acceptance criteria that was previously evaluated for predicate 1.5T MR Conditional labeling demonstration of safety."

While the specific clinical acceptance criteria for MR Conditional labeling (e.g., maximum temperature rise, induced voltage, artifact size, device malfunction rates) are not detailed within this summary, the outcome is reported as:

The document concludes that: "The results of the MRI verification testing have demonstrated the candidate Confirm Rx™ ICM DM3500 with updated MR Conditional labeling functions in accordance with product specifications." and "The results of the testing show that the candidate Confirm Rx™ ICM performs as intended and is safe for its intended use."

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

The document does not specify the sample size for the test set used for the MR Conditional testing. It generically refers to "all necessary device and system verification testing."

The provenance of the data (e.g., country of origin, retrospective/prospective) is not mentioned. Given the nature of MR Conditional testing, it would typically be conducted in a controlled lab environment.

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

This information is not provided in the document. For MR Conditional testing, ground truth typically relates to engineering measurements against pre-defined safety limits (e.g., temperature probes, E-field/H-field sensors, functional checks), rather than expert medical interpretation of diagnostic outputs.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method. For MR Conditional testing, results are typically objective measurements against engineering standards.

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

An MRMC study was not done as this submission focuses on updated MR Conditional labeling for a device, not the interpretation of its diagnostic output by human readers. Therefore, there is no effect size of human readers improving with AI vs. without AI assistance.

6. Standalone Performance Study

The document implies a standalone (algorithm only) performance study related to MR Conditional labeling, as it focuses on the device itself and its interaction with MRI fields. The "results of the MRI verification testing" demonstrate the device's functional integrity and safety. This testing is conducted on the device without human interpretation of its outputs during the test itself, only checking if the device continues to function correctly after the MRI exposure.

7. Type of Ground Truth Used

The ground truth used for the MR Conditional testing is based on engineering standards and design specifications for safe performance in an MRI environment. This includes, but is not limited to, parameters like temperature rise, induced voltage, and device functionality post-exposure, which are objectively measurable and compared against established safety thresholds.

8. Sample Size for the Training Set

The document describes pre-market notification for an updated label for an existing device. It does not mention any "training set" in the context of an AI/ML algorithm. This device is an implantable cardiac monitor, and the current submission is for an updated MR Conditional label, not for a new or updated AI algorithm.

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

As there is no mention of a training set related to an AI/ML algorithm in this document, this information is not applicable.

Ask a specific question about this device

The Confirm RxIM ICM is indicated for the monitoring and diagnostic evaluation of patients who experience unexplained symptoms such as: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atial fibrillation or who are susceptible to developing atrial fibrillation.

The Confirm Rx™ ICM Model DM3500 Implantable Device is intended as a minimally invasive, implantable diagnostic monitoring device, with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability, which help physicians monitor, diagnose, and document patients who are susceptible to cardiac arrhythmias. It has a two-year longevity, MR conditional labeling, sensing and detection algorithms, and Bluetooth communication. Specific features include: Patient-initiated triggering of EGM storage using the myMerlin™ Patient App for mobile devices, Automated triggering of EGM storage when tachycardia, bradycardia, or pauses are detected, Automated triggering of EGM storage when atrial fibrillation (AF) is detected, The ability to identify EGM anomalies as a consequence of noise or vigorous activity and inhibit EGM storage as applicable, Remote care monitoring. The system also includes Implant Tools (incision and insertion tools), a Magnet, a Clinician Programmer (Merlin PCS Programmer Model 3650) with Merlin PCS Model 3330 software, myMerlin™ Patient App (Model APP1000 Android), and Remote Care/Clinician Portal (Merlin.net MN5000 Report Generator).

This document is a 510(k) premarket notification for a minor design change to an existing device, the Confirm Rx Insertable Cardiac Monitor (ICM) Model DM3500. Therefore, the "study" referred to is primarily verification and validation testing to ensure the modified device still meets its specifications and is substantially equivalent to the predicate device, rather than a clinical effectiveness study.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't provide a direct table of specific acceptance criteria or quantitative performance metrics in the format requested, as it's a submission for a minor design change (adding a "peel and stick moisture getter"). Instead, it focuses on demonstrating that the modified device continues to meet the established design and performance specifications of the predicate device.

The study referenced is the Non-Clinical Test Summary, which involved:

• Risk Analysis (FMEA/FMECA): To assess the impact of the minor design change on hazards and associated risks.
• Verification and Validation Activities: To demonstrate that the device with the new moisture getter material meets its predetermined design and performance specifications.

The reported performance is that the device (with the modification) "functions in accordance with product specifications" and "is as safe and as effective and performs as well as the predicate device."

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

The document does not specify a distinct "test set" sample size for evaluating the algorithm's performance or device efficacy in a clinical sense. Given this is a 510(k) for a minor design change, the "test set" likely refers to engineering units used for verification and validation tests. The text indicates that these were non-clinical tests.

• Sample Size: Not specified quantitatively for testing the "peel and stick moisture getter." This would typically involve a specific number of devices or components undergoing various environmental, mechanical, and functional tests.
• Data Provenance: Non-clinical (laboratory/engineering tests). No country of origin is explicitly stated for these specific tests, but the company is based in the USA (Sylmar, CA). The tests are described as part of the "verification and validation activities" for the design change.

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

Not applicable in the context of this submission. The "ground truth" for non-clinical verification and validation tests is typically established by engineering specifications, regulatory standards, and comparison to the predicate device's performance, not by expert medical review of patient data in this specific context.

4. Adjudication Method for the Test Set

Not applicable. This is not a study involving human interpretation of medical data (like ECGs for arrhythmia detection) where adjudication methods (e.g., 2+1, 3+1) would be relevant. The verification and validation activities are engineering-focused.

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

No, an MRMC comparative effectiveness study was not done. This submission is for a minor design change to an existing device and does not involve assessing the impact of AI on human readers. The clinical effectiveness of the Confirm Rx ICM itself would have been established in previous 510(k) or PMA submissions (e.g., K190295 for the predicate device).

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

The document states that the fundamental technological characteristics and operating rules of the Confirm Rx ICM (which includes sensing and detection algorithms for arrhythmias) are not changing. Therefore, standalone performance of the algorithms was established with the predicate device (K190295) and is considered unchanged. This submission does not describe a new standalone performance study for the algorithms.

7. Type of Ground Truth Used

For the specific tests related to the "peel and stick moisture getter" modification:

• Ground Truth: Engineering specifications, performance criteria established for the predicate device, and regulatory standards. The goal was to demonstrate that these were still met after the modification.

For the underlying Confirm Rx™ ICM's arrhythmia detection algorithms, the "ground truth" for previous clearances would have likely involved:

• Expert Consensus: Cardiologists or electrophysiologists manually reviewing ECGs/EGMs to identify and classify arrhythmias.
• Clinical Outcomes: Correlating device detections with actual patient events or diagnoses.

However, these details are not provided in this specific document because the algorithms themselves are not being changed or re-evaluated for efficacy here.

8. Sample Size for the Training Set

Not applicable. The document describes a non-clinical modification to a hardware component (moisture getter) and explicitly states that the device's operating rules and functionality (which would include its algorithms) remain the same. This submission does not involve training new algorithms or a training set of data.

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

Not applicable, as there is no mention of a training set or new algorithm development/training in this submission.

Ask a specific question about this device

The Confirm Rx™ ICM is indicated for the monitoring and diagnostic evaluation of patients who experience unexplained symptoms such as: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atrial fibrillation or who are susceptible to developing atrial fibrillation.

The Confirm RxTM ICM has not been specifically tested for pediatric use.

The Confirm Rx™ Insertable Cardiac Monitor (ICM) Model DM3500 is intended as a minimally invasive, implantable diagnostic monitoring device, with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability, which help physicians monitor, diagnose, and document patients who are susceptible to cardiac arrhythmias. It has a two-year longevity, MR conditional labeling, sensing and detection algorithms, and Bluetooth communication. Specific features include:

• Patient-initiated triggering of EGM storage using the myMerlin™™ Patient App for mobile devices. This includes capability for the patient to identify symptoms, which are stored with the EGM for physician review.
• Automated triggering of EGM storage when tachycardia, bradycardia, or pauses are detected; with physician-programmable values for pause duration, bradycardia rate, tachycardia rate, and number of tachycardia intervals.
• Automated triggering of EGM storage when atrial fibrillation (AF) is detected, with physician programmable values for AF duration.
• The ability to identify EGM anomalies as a consequence of noise or vigorous activity and inhibit EGM storage as applicable.
• Remote care monitoring.

The provided document is a 510(k) premarket notification for the Abbott Confirm Rx™ Insertable Cardiac Monitor (ICM) System, Model DM3500, with updated firmware. The purpose of this submission is to demonstrate substantial equivalence to a predicate device (K182981).

The document details the device description, technological characteristics, and the testing conducted to support the substantial equivalence claim. However, it does NOT contain a detailed study proving the device meets specific acceptance criteria for AI/algorithm performance as would be typically found for new AI-driven diagnostic devices. Instead, the focus is on demonstrating that the updated firmware, particularly its detection algorithms, functions as intended without raising new issues of safety and effectiveness compared to the predicate device.

Specifically, the acceptance criteria and performance data are described in terms of verification and validation activities showing the device meets its "predetermined design and performance specifications" and "functions in accordance with product specifications." The changes in the firmware relate to "detection algorithms for the diagnosis of bradycardia, asystole (pause), and atrial fibrillation (AF)," including "second pass undersensing discriminators" and a "P-wave detection discriminator."

Given the information provided, it's not possible to present a table of acceptance criteria and reported device performance in the context of an AI study as you described.

However, I can extract the relevant information regarding the firmware update validation and
address the closest approximations to your questions for this type of medical device submission.

Analysis of the Provided Document Regarding Acceptance Criteria and Study:

The document describes an update to the firmware of an existing, already cleared device. The "study" here is the validation of the firmware update to ensure it doesn't negatively impact safety or effectiveness and that the new algorithms perform as intended.

1. A table of acceptance criteria and the reported device performance

The document states that the "Completion of all verification and validation activities demonstrated that the device with updated firmware meets its predetermined design and performance specifications and that the product is substantially equivalent to the predicate Confirm Rx™ ICM device (K182981)." It also states, "The results of the testing show that the candidate Confirm RxTM ICM performs as intended and is safe for its intended use."

The updated firmware includes changes to detection algorithms for bradycardia, asystole (pause), and atrial fibrillation (AF). The acceptance criteria would inherently be related to the accuracy and reliability of these detections compared to established benchmarks or the predicate device, although specific numerical performance metrics (e.g., sensitivity, specificity, accuracy percentages) are not detailed in this summary.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

The document does not specify the sample size (number of patients, number of EGM recordings) used for the verification and validation (V&V) testing. It also does not specify the data provenance (country of origin, retrospective/prospective). This type of detail is typically found in the full testing report, not usually summarized in this section of a 510(k) summary.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

The document does not specify the number or qualifications of experts used to establish ground truth. For embedded device algorithm testing, ground truth might often be established through simulated signals, pre-recorded clinical data with confirmed diagnoses, or expert review of EGMs, but this detail is not provided.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

The document does not specify any adjudication method for ground truth establishment.

5. 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, an MRMC comparative effectiveness study was not conducted or described. This is a device firmware update, not a new AI-assisted diagnostic tool where human reader performance would be compared. The focus is on the device's internal algorithm performance.

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

Yes, the testing described appears to be a standalone validation of the algorithm's performance within the device, given the context of "Software/Firmware Verification and System Verification" and "Design Validation." The purpose is to confirm the algorithm's internal logic and detection capabilities. The document states:

• "Second pass undersensing discriminators added to the Asystole and Bradycardia detection algorithms to reject false Pause and Bradycardia detections."
• "Second pass P-wave detection discriminator to reject false AF detections."

This implies that the algorithm itself was tested for its ability to correctly identify and reject false detections, which is a standalone performance metric.

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

The type of ground truth is not explicitly stated. For cardiac rhythm detection algorithms, ground truth typically involves a highly accurate reference ECG/EGM interpretation, which could be established via:

• Expert Consensus: Review by multiple cardiologists or electrophysiologists.
• Manual Annotation: Beat-by-beat or episode-by-episode annotation of EGM data by trained personnel, often adhering to specific criteria.
• Validation against high-fidelity recordings: Comparing device output to a gold-standard recording from a different, validated system.

Given the focus on "reject[ing] false detections," it implies that there was a reference against which the algorithm's detection (true positive/false positive) was measured.

8. The sample size for the training set

The document does not provide any information about a training set size. This indicates that this submission is about validating a firmware update for an already cleared device, not seeking de novo clearance for a new machine learning algorithm that typically requires a distinct training phase. While the algorithms were likely "trained" or designed using data at some point in their development, that information is not part of this 510(k) summary for a firmware update.

9. How the ground truth for the training set was established

Since there is no mention of a training set in this document, there is no information on how its ground truth was established.

Ask a specific question about this device

The Confirm RxIM ICM is indicated for the monitoring and diagnostic evaluation of patients who experience wersplained symptoms such as: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atrial fibrillation or who are susceptible to developing atrial fibrillation.

The Confirm RxIM ICM has not been specifically tested for pediatric use.

The ICM is intended as a minimally invasive, implantable diagnostic monitoring device, with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability, which help physicians monitor, diagnose, and document patients who are susceptible to cardiac arrhythmias. It has a two-year longevity, MR conditional labeling, sensing and detection algorithms, and Bluetooth communication. Specific features include:

• Patient-initiated triggering of EGM storage using the myMerlin™™ Patient App for o mobile devices. This includes capability for the patient to identify symptoms, which are stored with the EGM for physician review.
• Automated triggering of EGM storage when tachycardia, bradycardia, or pauses are o detected; with physician-programmable values for pause duration, bradycardia rate, tachycardia rate, and number of tachycardia intervals.
• Automated triggering of EGM storage when atrial fibrillation (AF) is detected, with O physician programmable values for AF duration.
• The ability to identify EGM anomalies as a consequence of noise or vigorous activity o and inhibit EGM storage as applicable.
• Remote care monitoring. o

Here's an analysis of the provided text regarding the Abbott Confirm Rx Insertable Cardiac Monitor (ICM) System, Model DM3500, focusing on acceptance criteria and the supporting study:

Important Note: The provided document is a 510(k) clearance letter and related submission materials. It primarily focuses on demonstrating "substantial equivalence" to a predicate device rather than presenting a detailed standalone performance study with comprehensive acceptance criteria and results for the new device. Therefore, some of the requested information (like specific performance metrics and their ranges) is not explicitly listed as "acceptance criteria" and "reported device performance" in the way one might expect for a de novo device clearance. The document emphasizes that the fundamental technological characteristics are not changing, and the focus is on minor firmware updates and a manufacturing material change.

1. Table of Acceptance Criteria and Reported Device Performance

As mentioned, the document doesn't explicitly define a table of new acceptance criteria with numerical performance targets and reported results for the DM3500 in the way a clinical study report would. Instead, it states that the device "meets its predetermined design and performance specifications" and "performs as intended and is safe for its intended use."

The "acceptance criteria" are implied by the verification and validation activities conducted to ensure the device with the minor changes:

• Functions in accordance with product specifications.
• Performs as intended.
• Is safe for its intended use.
• Is substantially equivalent to the predicate (K163407).

The reported device performance is therefore that these criteria were met, specifically through:

• Firmware Verification and System Validation: This would ensure the updated firmware functions correctly and that the overall system operates as specified.
• Mechanical Performance Testing: This would verify the mechanical integrity and function of the device with the new UV Cure material.

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

The document does not specify a "test set" sample size in terms of patient data or clinical cases. The testing conducted was primarily bench testing and system validation for the firmware and mechanical changes. No clinical study on human subjects is mentioned for this particular 510(k) submission.

• Sample Size: Not applicable in the context of human clinical data. For engineering verification and validation, it would refer to the number of devices or test units, which is not stated.
• Data Provenance: Not applicable for clinical data. The testing described is internal engineering and validation testing.

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

Not applicable. This submission is for a device modification (firmware update and material change) and relies on engineering verification and validation, not on expert adjudication of diagnostic performance on a test set of clinical cases. The "ground truth" here would be the predefined functional and performance specifications of the device.

4. Adjudication Method for the Test Set

Not applicable. As no clinical test set requiring human adjudication is described, there is no adjudication method.

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

No MRMC study was done and none is described. This device is an insertable cardiac monitor, and its capabilities are assessed through its detection algorithms and hardware performance, not through human interpretation of its outputs in a comparative effectiveness study involving reader performance improvement with AI.

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

The device's core function is automatic detection of cardiac events (tachycardia, bradycardia, pauses, AF). The document states:

• "Automated triggering of EGM storage when tachycardia, bradycardia, or pauses are detected"
• "Automated triggering of EGM storage when atrial fibrillation (AF) is detected"
• "The ability to identify EGM anomalies as a consequence of noise or vigorous activity and inhibit EGM storage as applicable."

The "Firmware Verification and System Validation" would have evaluated the performance of these algorithms in a standalone manner (without human intervention) against known inputs. However, no specific metrics (e.g., sensitivity, specificity for AF detection) from such a study are provided in this regulatory document. The statement implies that the existing algorithms (from the predicate) have been verified with the updated firmware.

7. Type of Ground Truth Used

For the Firmware Verification and System Validation, the ground truth would be:

• Predefined system specifications: The expected behavior and output of the device's firmware and algorithms under various conditions.
• Known input signals: Simulated or recorded ECG/EGM data with precisely defined events (e.g., specific heart rates, AF episodes, pauses) to test the detection algorithms.
• Mechanical engineering standards: For the mechanical performance testing.

8. Sample Size for the Training Set

Not applicable. The document does not describe the development of new AI algorithms that require a "training set." The firmware updates are described as "minor changes" to an existing ERI detection algorithm and magnet response, implying fine-tuning or bug fixes rather than a re-training of a predictive model.

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

Not applicable, as no training set for new AI algorithms is described.

Ask a specific question about this device

The Confirm Rx™ ICM is indicated for the monitoring and diagnostic evaluation of patients who experience unexplained symptoms such as: dizziness, palpitations, chest pain, syncope, and shortness of breath, as well as patients who are at risk for cardiac arrhythmias. It is also indicated for patients who have been previously diagnosed with atrial fibrillation or who are susceptible to developing atrial fibrillation.

The St. Jude Medical Confirm Rx™ system consists of the following key features and components:

• Confirm RxTM ICM Model DM3500 Implantable Device: The ICM is intended as a minimally invasive, implantable diagnostic monitoring device, with subcutaneous electrodes, looping memory, and automatic as well as patient-activated EGM storage capability, which help physicians monitor, diagnose, and document patients who are susceptible to cardiac arrhythmias. It is predicated on SJM Confirm™ DM2102 with a two-year longevity, MR conditional labeling, and identical sensing and detection algorithms as SJM Confirm™ DM2102, but with downsized hardware and Bluetooth communication.
• Implant Tools: Model DM3520 incision tool and Model DM3510 insertion tool to implant the device subcutaneously.
• Model 3111 Magnet (existing SJM donut magnet) facilitates faster startup of Bluetooth connection and provides user authentication (required for programmer sessions).
• Clinician Programmer (Merlin PCS Programmer Model 3650): The Merlin PCS Programmer 3650 operates using Merlin PCS Model 3330 software and provides the means for the physician to program device parameters and retrieve diagnostic information from the device, including electrograms, heart rate history, episode duration and trend information.
• myMerlin™ Patient App (Model APP1000 Android): The Patient App provides the means for the patient to activate EGM recording in the Confirm Rx™ device, with data pass-through functionality to enable physician follow-up via the Merlin.net Patient Care Network.
• Remote Care/Clinician Portal (Merlin.net MN5000 Report Generator): The Merlin.net MN5000 system allows physicians to remotely monitor and diagnose patients' cardiac events.

The provided text describes the Confirm Rx™ Insertable Cardiac Monitor (ICM) System, Model DM3500.

Here's an analysis of the acceptance criteria and the studies mentioned:

1. Table of Acceptance Criteria and Reported Device Performance:

The document mentions that the Confirm Rx™ ICM leverages the existing market-cleared SJM Confirm™ (DM2102) algorithms and functionality. Therefore, the "acceptance criteria" for the detection algorithms are implicitly inherited from the predicate device. While specific numerical targets for metrics like sensitivity or specificity are not explicitly stated as acceptance criteria for the Confirm Rx™ ICM in this summary, the key performance aspects verified through testing are:

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices. It typically does not contain the detailed clinical study reports or comprehensive performance metrics that would be found in a full PMA application or a detailed peer-reviewed publication. The "acceptance criteria" here are therefore inferred from the context of substantial equivalence to a previously cleared device.

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

• Test Set Sample Size: The document does not explicitly state a specific sample size for a clinical test set used to evaluate the Confirm Rx™ ICM's diagnostic performance for arrhythmia detection. It states: "R-wave detection and device migration were verified via bench and animal testing for the Confirm Rx™ ICM DM3500." and "The Confirm Rx™ ICM leverages the existing market cleared SJM Confirm™ (DM2102) algorithms and functionality for which the clinical testing, performed on the SJM Confirm™ (DM2102) device per St. Jude Medical IDE G080090, is applicable and was not repeated."
• Data Provenance: The document does not specify the country of origin for the data, but it refers to an IDE (Investigational Device Exemption) study (G080090) conducted for the predicate device, SJM Confirm™ (DM2102). IDE studies are typically prospective clinical trials.

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

• This information is not provided in the 510(k) summary for the Confirm Rx™ ICM. Since the clinical performance data is leveraged from the predicate device, the details about ground truth establishment would reside in the original IDE G080090 submission for the SJM Confirm™ (DM2102).

4. Adjudication Method for the Test Set:

• This information is not provided in the 510(k) summary. Details on adjudication methods would typically be found in the full clinical study report for the predicate device (IDE G080090).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs. without AI assistance:

• No MRMC comparative effectiveness study is mentioned. The Confirm Rx™ ICM is an insertable cardiac monitor that automatically detects and records cardiac events. It is not an AI-assisted diagnostic tool designed to improve human reader performance in interpreting medical images or complex waveforms. Its primary function is automated detection and recording, with physician review of the recorded electrograms (EGMs).

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:

• Yes, the document implies standalone performance evaluation of the detection algorithms. It states that the Confirm Rx™ ICM utilizes "identical sensing and detection algorithms as SJM Confirm™ DM2102." These algorithms are designed for automated triggering of EGM storage based on detected events like tachycardia, pauses, and atrial fibrillation. The verification of R-wave detection (a fundamental aspect of these algorithms) was performed via bench and animal testing, suggesting an evaluation of the algorithm's performance independent of a human in the loop for the core detection task. Physicians later review the automatically captured EGMs.

7. The Type of Ground Truth Used:

• For the R-wave detection and device migration verification in the Confirm Rx™ ICM, the ground truth would likely be based on direct physiological measurements from bench testing and animal studies (e.g., direct electrical signals or physical tracking of device position).
• For the leveraged clinical performance of the detection algorithms (from SJM Confirm™ DM2102 IDE G080090), the ground truth for arrhythmia detection would typically involve expert consensus of ECG/EGM interpretation by cardiologists or electrophysiologists, potentially corroborated with other clinical data or findings.

8. The Sample Size for the Training Set:

• The document does not specify a training set sample size. Given that the device leverages "identical sensing and detection algorithms" from a predicate device, the algorithms were likely developed and "trained" (or more accurately, designed and optimized) at an earlier stage with data that is not detailed in this 510(k) summary. This summary focuses on verifying the new device's implementation of those existing algorithms, not on new algorithm development.

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

• This information is not provided in the 510(k) summary. As mentioned, the algorithms are inherited from a predicate. Details on their initial development and the establishment of ground truth for any underlying "training" or optimization data would be found in the documentation for the predicate device (SJM Confirm™ DM2102).

Ask a specific question about this device