Search Results

The Jot Dx™ 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 Jot Dx™ ICM DM4500 System consists of the Jot Dx™ ICM Model DM4500 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.

This document is a 510(k) premarket notification for the Abbott Jot Dx™ Insertable Cardiac Monitor (ICM) DM4500. The core of this submission is to demonstrate substantial equivalence to an existing predicate device, the Abbott Confirm Rx™ ICM DM3500 (K202888).

Therefore, the study supporting acceptance criteria isn't a traditional clinical study with human readers and ground truth established by experts. Instead, the "study" is a non-clinical test summary demonstrating that the new device is identical to the predicate device in all relevant aspects affecting safety and effectiveness.

Here's a breakdown based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

Since the submission claims identity to a predicate, the acceptance criteria are effectively that the Jot Dx™ ICM DM4500 must perform identically to the Confirm Rx™ ICM DM3500.

"The fundamental technological characteristics of the candidate Jot Dx™ ICM DM4500 are not changing in comparison to the predicate device, the current Confirm Rx™ ICM DM3500 (510(k) K202888). The candidate Jot Dx™ ICM DM4500 system has the same:

• Intended Use and Indications for Use
• Operating rules
• Device/tool functionality
• Packaging materials and process
• Shelf life
• Device Longevity
• Software"

"The candidate Jot Dx™ ICM DM4500 is identical in design and function and has the same indications and intended use as the predicate Confirm Rx™ ICM DM3500 (K202888)." |
| Safety and Effectiveness: The minor differences (name, model number, laser marking) do not raise new issues of safety and effectiveness. | "The minor differences in name, model number, and laser marking do not raise new issues of safety and effectiveness."

"Completion of all verification and validation activities demonstrated that the candidate Jot Dx™ ICM DM4500 meets its predetermined design and performance specifications and that the product is substantially equivalent to the predicate device (Model DM3500, K202888)."

"The results of the testing show that the candidate Jot Dx ICM DM4500 system performs as intended and is safe for its intended use."

"The candidate Jot Dx™ ICM system is substantially equivalent in terms of safety and technological characteristics to the identified predicate device (Confirm RxTM ICM System; K202888). Product verification and validation testing demonstrate that the candidate Jot Dx ICM system is as safe and as effective and performs as well as the predicate system (K202888)." |
| Risk Assessment: Acceptable risk profile. | "The risk analysis method used to assess the impact of the addition of the candidate Jot Dx™ ICM DM4500 documents the investigation of hazards and mitigation of associated risks and reports the result of the investigation. The risk analysis method used to assess the impact of the modifications was a Failure Mode and Effects Analysis (FMEA/FMECA). It was determined that the overall risk is acceptable." |

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

• Test Set Sample Size: Not applicable in a traditional sense. The "test set" here refers to the engineering verification and validation testing performed on the single design of the Jot Dx™ ICM DM4500 to confirm its identity and performance against the predicate. This isn't a statistical sample of independent clinical cases.
• Data Provenance: Not applicable for a traditional clinical study. The "data" comes from internal engineering verification and validation activities. It's retrospective in the sense that they are comparing it to an already cleared predicate device's specifications and performance. No country of origin is specified for these internal engineering tests, but the company is based in the USA.

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

• Number of Experts: Not applicable. Ground truth, in the context of substantial equivalence for an identical device, is established by its adherence to the design and performance specifications of the predicate device, not through expert human interpretation of clinical data on the new device.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable. There is no ambiguous clinical data requiring adjudication.

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:

• MRMC Study: No. This submission does not involve an AI component or a comparative effectiveness study with human readers. The device is an insertable cardiac monitor that automatically detects events.

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

• Stand-alone Performance: While the device automatically detects cardiac arrhythmias (an "algorithm" in a broad sense), the submission doesn't present a standalone performance study with metrics like sensitivity and specificity against a clinical ground truth. Instead, it relies on the established performance of the identical predicate device. The document explicitly states the "Automated triggering of EGM storage when tachycardia, bradycardia, or pauses are detected" and "Automated triggering of EGM storage when atrial fibrillation (AF) is detected." The performance of these detection algorithms is considered equivalent to the predicate.

7. The Type of Ground Truth Used:

• Type of Ground Truth: The "ground truth" for this submission is the established design, performance specifications, and safety/effectiveness profile of the legally marketed predicate device (Confirm Rx™ ICM DM3500, K202888). The new device is asserted to be identical in these respects, making the predicate the reference "truth."

8. The Sample Size for the Training Set:

• Training Set Sample Size: Not applicable. There is no machine learning or AI algorithm being trained for this device submission as it is presented as a re-branding/model number change of an existing technology.

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

• Ground Truth for Training Set: Not applicable, as there is no training set mentioned in this 510(k) application.

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 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 Agilis HisPro Steerable Catheter With Electrodes is indicated to provide a pathway for delivery and support of transvenous devices within the chambers and vasculature of the heart and can be used for electrogram recording and stimulation.

The Agilis HisPro Steerable Catheter With Electrodes is a deflectable, slittable catheter with two distal tip electrodes. It serves as a delivery conduit for devices such as cardiac leads. The distal portion can be formed into a "U" shape, when fully deflected, to facilitate positioning of the tip at a desired location in the heart. The 10.5 Fr catheter has a braided shaft with a multi-durometer outer Pebax jacket. The catheter has a 7 Fr diameter lumen that allows for delivery of a 6Fr cardiovascular transvenous device, including a 6Fr pacing lead. The Agilis HisPro catheter's proximal handle consists of a rotating actuator with passive locking mechanism for deflecting the distal portion, a hemostasis valve for leak-proof delivery, and an integrated cable incorporating a 4-pin electrical connection for connecting to external electrical systems via a commercially available electrophysiology cable. The tip electrodes provide the ability to sense intracardiac electrogram (EGM) and pace when connected to the Merlin™ Pacing System Analyzer (PSA) or the WorkMate Claris™ Recording System. The sensing and pacing feature of the Agilis HisPro catheter provides the ability to identify the desired location in the heart. Accessories packaged for use with the Agilis HisPro catheter include dilator, guidewire for vascular access, cable adaptor pins for connection to the Merlin PSA via the electrophysiology cable, valve bypass tools for lead insertion, three-way stopcock and slitter. The catheter and the packaged accessories are provided as a sterile single-use device.

The provided FDA 510(k) summary for the Agilis HisPro Steerable Catheter With Electrodes does not contain information about a study proving the device meets specific acceptance criteria in the context of AI/machine learning or diagnostic performance metrics.

The document describes the device's technical specifications, indications for use, comparison to predicate devices, and a list of performance bench testing, packaging and shelf-life testing, biocompatibility assessment, and some animal testing. However, it does not mention:

• Acceptance criteria directly related to diagnostic performance (e.g., sensitivity, specificity, accuracy).
• Any study with a "test set" and "training set" of data, ground truth establishment, or expert adjudication that would be typical for validating an AI/ML medical device.
• Multi-reader multi-case (MRMC) comparative effectiveness studies.
• Standalone algorithm performance.

The listed tests are primarily focused on the physical, electrical, functional, and biological safety and performance of a medical catheter, not on a diagnostic or prognostic algorithm's performance.

Therefore, I cannot populate the requested table or answer the specific questions related to AI/ML device validation based on the provided text.

The information that is available relates to the overall performance testing for regulatory clearance of a physical medical device. Below is a summary of the performance testing performed, but it doesn't align with the requested format for AI/ML device performance.

Summary of Performance Testing (as described in the document):

The device underwent various performance tests to demonstrate it meets design specifications and is as safe and effective as predicate devices.

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

• The document lists categories of tests but does not provide specific numerical acceptance criteria (e.g., "deflection force must be X N ± Y N") or quantified "reported device performance" values for each criterion. It only states that testing "demonstrated that the subject device is as safe and effective as the predicate devices."

Summary of Performance Tests Performed:

Since the document does not relate to an AI/ML device, the following points cannot be addressed:

• 2. Sample sized used for the test set and the data provenance
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
• 4. Adjudication method for the test set
• 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
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
• 7. The type of ground truth used
• 8. The sample size for the training set
• 9. How the ground truth for the training set was established

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 Abbott Confirm RxTM (ICM) System consists of the following key features and components:

• Confirm Rx™ 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 to implant the device subcutaneously.
• Model 3111 Magnet: 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) and APP1001 (iOS)): The mobile application provides the means for the patient to activate EGM recording in the Confirm RxTM 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 a 510(k) premarket notification for the "myMerlin Mobile Application (Android)" and "myMerlin Mobile Application (iOS)" by Abbott (St. Jude Medical). This application is part of the Confirm Rx™ Insertable Cardiac Monitor System. The submission claims substantial equivalence to a previously cleared predicate device (K192593, Confirm Rx™ Insertable Cardiac Monitor System).

The submission focuses on updates to the myMerlin™ mobile application, primarily related to scheduled background workflows and telemetry connectivity improvements, as well as the ability to transfer a patient's remote monitoring support profile on Merlin.net.

The document states that the fundamental technological characteristics, intended use, indications for use, operating rules, cybersecurity, and usability testing remain the same as the predicate device. Therefore, the testing performed was to demonstrate that the updated mobile application maintains its safety and effectiveness for its intended use, rather than proving performance against new acceptance criteria for a novel functionality.

Given this context, the acceptance criteria and study details are presented as follows:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the sample size of a "test set" in terms of patient data or scenarios used. The testing described is primarily focused on software verification, system verification, design validation, and Bluetooth Low Energy proxy software verification. This implies testing involved the software application itself and its interaction with the ICM device, rather than a clinical study with a patient cohort.

• Data Provenance: Not applicable in the context of a clinical test set. The provenance of the software updates is from the manufacturer, Abbott. The nature of the changes (software updates) suggests internal testing and technical verification.

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

This information is not provided. Given the nature of the submission (updates to a mobile application interacting with an already cleared device), the "ground truth" would likely be established by engineering and software performance standards, rather than expert clinical consensus on patient data.

4. Adjudication Method for the Test Set

This information is not provided. As noted in point 3, the testing appears to be technical in nature rather than clinical, so a traditional clinical adjudication method would not be expected.

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 MRMC comparative effectiveness study was mentioned. The myMerlin™ mobile application is primarily a patient interface for activating EGM recording and data pass-through. It is not an AI-assisted diagnostic tool for "human readers," so this type of study would not be relevant.

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

The submission describes the myMerlin™ mobile application (APP1000/APP1001) as a component of the Confirm Rx™ ICM System. The application enables patients to activate EGM recording and facilitates data pass-through to the Merlin.net Patient Care Network for physician review. The focus is on the functional performance of the application and its connectivity, not on a standalone algorithm for diagnosis without human input. Therefore, a standalone algorithm performance study as typically understood for diagnostic AI was not done or described. The "standalone" performance here refers to the application's ability to fulfill its intended technical functions.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

For the specific updates to the myMerlin™ mobile application, the "ground truth" for verification and validation would be defined by predetermined design and performance specifications or product specifications. This means the software was tested against its expected behavior and technical requirements, rather than against clinical outcomes, pathology, or expert consensus on a clinical dataset. The objective was to confirm that the updated software performed as intended and did not negatively impact the already cleared system's functionality.

8. The Sample Size for the Training Set

This information is not applicable. The myMerlin™ mobile application is not described as involving a machine learning or AI algorithm that would require a "training set" in the conventional sense (i.e., for learning to identify patterns in data). The changes are described as software updates to workflows and connectivity.

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

This information is not applicable, as no training set for a machine learning algorithm is mentioned or implied.

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