Search Results

SCS:
This system is indicated as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach for chronic, intractable pain of the trunk and/or limbs, including unilateral pain. The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

PNS:
This system is indicated for pain management in adults who have severe intractable chronic pain of peripheral nerve origin, as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach. The Nalu Neurostimulation System for PNS is not intended to treat pain in the craniofacial region. The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu Neurostimulation System (referred to as the "Nalu System") incorporates a miniature implantable pulse generator (IPG), powered by an externally worn Therapy Disc device. The Nalu System therapy utilizes pulsed electrical current to create an energy field that acts on peripheral nerves or central nerves to inhibit the transmission of pain signals to the brain. The Nalu System may be implanted following a successful trial period using the Nalu Neurostimulation trial system. This device is intended to be used in the spinal column as well as the peripheral nerves in arm, leg, pelvic and other areas, as is typical of other devices and treatments for the same intended use.

The Nalu System is intended for stimulation of the spinal cord or peripheral nerves for patients experiencing chronic, intractable pain. This system is indicated for pain management in adults who have severe intractable chronic pain, as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach. The system is not intended to treat pain in the craniofacial region. The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu System is comprised of the following components:
• Implantables (there are no proposed changes to these components as previously provided in K221376):
o Implantable pulse generator (IPG; available either as an integrated lead unit or with separately connected lead(s)) – provides electrical stimulation pulses that are transmitted through the leads, to the desired location, either on the spinal cord or peripheral nerve site(s).
o Leads – implantable and designed to deliver electrical pulses to the nerves via an array of four (4) or eight (8) cylindrical electrodes at the distal end.
o Surgical and Trial Tools – includes anchors, spoonbill needs, stylets, tearaway introducers, pocket tunneler, torque wrench, IPG insertion tool, straw tunneler; tools to support implantation of lead and IPG.

• Externals, Non-Sterile:
  o Externally worn controllers (for use with the permanent implant) and accessories – includes the Therapy Disc, Adhesive Clip, Wearable Garment, Therapy Disc Charger; houses the battery and electronics for RF power and controls the IPG for therapy delivery via the remote programmer (subject of this submission).
  o Externally worn stimulator (for use with the trial lead) and accessories – includes the Trial Therapy Disc; sends signals to the percutaneous leads during the trial period by way of the Electrode Interface Cable (EIC).
  • Software (subject of this submission):
  o Clinician Programmer, Patient Remote Control – used to configure the system parameters; also manages patient records, Therapy Discs and remote controls for patients with the Nalu System; runs on Android and iOS platforms and can be optionally used to control and manage Therapy Discs over a secure Bluetooth® Low Energy connection.

The provided text is a 510(k) premarket notification for the Nalu Neurostimulation System. It details modifications made to an existing device, primarily to its external components and software, and argues for substantial equivalence to a previously cleared predicate device (K221376).

Crucially, this document does not describe a study to prove a device meets acceptance criteria related to efficacy or performance comparable to what would be found in a multi-reader, multi-case (MRMC) study or a standalone algorithm performance evaluation for an AI/ML medical device.

Instead, the "acceptance criteria" and "proof" provided are focused on engineering verification and validation to demonstrate that the modifications to the existing device do not raise new questions of safety or effectiveness, thus maintaining substantial equivalence to its predicate. The device itself is a neurostimulation system for pain relief, not an AI/ML diagnostic tool.

Therefore, many of the requested items (e.g., sample size for test set, data provenance, number of experts for ground truth, MRMC study, effect size of human reader improvement, standalone performance, type of ground truth, training set sample size, ground truth for training set) are not applicable to this submission, as it is not for an AI/ML algorithm requiring such performance evaluations.

However, I can extract information relevant to the engineering acceptance criteria and the validation activities performed for the modified device components.

Here's a breakdown of the information that can be extracted from the provided text, and an explanation of why other requested information is not present:

Acceptance Criteria and Device Performance (Engineering/Safety Context)

The document frames its "acceptance criteria" as demonstrating that the modified device's technological characteristics are effectively the same or do not raise different questions of safety and effectiveness compared to the predicate device. The performance is then shown through various engineering and validation tests.

Study Details (Context of Engineering Validation, Not AI Performance)

1. Sample size used for the test set and the data provenance: Not applicable in the context of clinical results from a test set as would be used for an AI/ML diagnostic device. The "test set" here refers to physical units of the modified device and its software undergoing various engineering and software validation tests. Data provenance is not described in terms of patient data.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth as typically defined for AI/ML performance (e.g., expert consensus on medical images) is not relevant for this engineering and software validation. The "ground truth" for these tests are largely defined by engineering specifications, regulatory standards, and functional requirements.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable. Adjudication methods are used in studies involving human interpretation or performance, typically for diagnostic accuracy.

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, an MRMC comparative effectiveness study was NOT done. The document explicitly states: "No clinical testing was performed."
   • This device is a neurostimulation system, not a diagnostic imaging AI/ML device that assists human readers.

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

   • Not applicable in the context of an AI/ML algorithm. The "software testing" mentioned evaluates the software's functional correctness against its specifications, not its standalone diagnostic or interpretive performance.

6. The type of ground truth used (expert concensus, pathology, outcomes data, etc.): Not applicable for an AI/ML context. For the engineering and software validation, the "ground truth" is adherence to established engineering specifications, industry standards (e.g., ISO, IEC), and regulatory guidance.

7. The sample size for the training set: Not applicable. This submission is for hardware and software modifications to a neurostimulation device, not for an AI/ML model that requires a training set.

8. How the ground truth for the training set was established: Not applicable, as there is no AI/ML training set in this context.

Ask a specific question about this device

This system is indicated for pain management in adults who have severe intractable chronic pain of peripheral nerve origin, as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach. The system is not intended to treat pain in the craniofacial region.

The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu Neurostimulation System for Peripheral Nerve Stimulation (also referred to as the "Nalu System") is used for peripheral nerve stimulation to provide therapeutic relief for chronic, intractable pain of peripheral nerve origin. The Nalu System incorporates a miniature implantable pulse generator, powered by an externally worn Therapy Disc device. The Nalu Neurostimulation therapy utilizes pulsed electrical current to create an energy field that acts on the peripheral nerves to inhibit the transmission of pain signals to the brain. The Nalu System may be implanted following a successful trial period using the Nalu Neurostimulation trial system. The Nalu System is comprised of 5 elements: Nalu Implantable Pulse Generator, Leads, Surgical and Trial Tools, Externally worn Therapy Disc, and Clinician Programmer and Remote Control.

This document describes a 510(k) premarket notification for the Nalu Neurostimulation System for Peripheral Nerve Stimulation. The submission aims to establish substantial equivalence to a previously cleared predicate device (K183579), primarily focusing on an update to the device's Magnetic Resonance (MR) Conditional Labeling to include full body scans.

Based on the provided text, there is no acceptance criteria table or specific study performance data for a device meeting acceptance criteria in the traditional sense of an AI/ML model for diagnostic or predictive purposes. This document is a regulatory submission for a physical medical device (implantable neurostimulator) and its associated external components and software, not an AI/ML diagnostic software. The "performance" discussed here relates to the safety and functionality of the device itself, particularly its compatibility with MRI, rather than the accuracy of a diagnostic algorithm.

Therefore, many of the requested elements (e.g., sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC study, standalone performance, training set details) are not applicable to this type of medical device submission.

However, I can extract the relevant information regarding the device's "performance" as presented in the context of this 510(k) submission, specifically concerning the MRI compatibility, as this is the primary change necessitating the resubmission.

Summary of Acceptance Criteria and Device (MRI) Performance:

Since this is not an AI/ML diagnostic device, the "acceptance criteria" are not framed in terms of metrics like accuracy, sensitivity, or specificity. Instead, they are related to established safety standards for medical devices, particularly regarding MRI compatibility. The "device performance" refers to the results of testing performed to ensure these safety standards are met.

1. Table of Acceptance Criteria and Reported Device Performance (Focusing on MRI Compatibility):

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

• Sample Size: The document does not specify the sample sizes used for the engineering tests (e.g., number of devices tested for MRI compatibility, displacement, torque, or artifacts). These are typically bench tests on physical units, not clinical data sets.
• Data Provenance: Not applicable in the context of clinical data. The tests are laboratory-based, non-clinical performance and bench testing.

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

• Not Applicable. This is not a study assessing the performance of a diagnostic algorithm where expert ground truth is established for medical images. The "ground truth" for this device's performance relies on engineering measurements and adherence to international and national standards (e.g., ISO, ASTM) for device safety and functionality.

4. Adjudication Method for the Test Set:

• Not Applicable. As there are no human readers or diagnostic interpretations involved in the "test set" (which consists of physical device tests), no adjudication method is necessary.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. This type of study is typically done for diagnostic imaging devices or AI tools that assist human readers. This submission is for an implantable neurostimulation system, not a diagnostic imaging or AI assistance tool.

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

• Not Applicable. There is no "algorithm only" performance being evaluated in this submission in the context of diagnostic AI. The device's functionality (e.g., electrical stimulation parameters) and safety (e.g., MRI compatibility) are evaluated.

7. The Type of Ground Truth Used:

• The "ground truth" for the device's safety and performance is established through adherence to recognized international and national consensus standards (e.g., ISO/TS 10974, ISO 14708, ASTM F2052-15, ASTM F2213-17, ASTM F2119-2013) and engineering verification and validation testing. It is not based on expert consensus on medical image interpretations or clinical outcomes data in the context of diagnostic accuracy.

8. The Sample Size for the Training Set:

• Not Applicable. This is not an AI/ML device that requires a training set of data.

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

• Not Applicable. (See point 8).

Ask a specific question about this device

Spinal Cord Stimulation (SCS)

This system is indicated as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach for chronic, intractable pain of the trunk and/or limbs, including unilateral pain. The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

Peripheral Nerve Stimulation (PNS)

This system is indicated for pain management in adults who have severe intractable chronic pain of peripheral nerve origin, as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach. The system is not intended to treat pain in the craniofacial region.

The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu Neurostimulation System has been cleared by the FDA for spinal cord stimulation (SCS; K203547) and peripheral nerve stimulation (PNS; K203547) to provide therapeutic relief for chronic, intractable pain of the trunk and/or limbs including unilateral, bilateral nerve pain. The Nalu Neurostimulation therapy utilizes pulsed electrical current to create an energy field that acts on nerves in the spinal cord or peripheral nerve to inhibit the transmission of pain signals to the brain. The Nalu System is implanted only following a successful trial period using the Nalu Neurostimulation trial system.

The Nalu Neurostimulation System consists of five (5) components. The implantable pulse generator (IPG) provides electrical stimulation pulses that are transmitted through the leads, to the desired location, either on the spinal cord or peripheral nerve site. The leads are implantable and designed to deliver electrical pulses to the nerves via an array of four (4) or eight (8) cylindrical electrodes at the distal end. The Trial Therapy Disc or the Therapy Disc houses the battery and electronics for RF power and controls the IPG for therapy delivery via the remote programmer. Implantation of the Nalu IPG and lead components for Spinal Cord Stimulation (SCS) or Peripheral Nerve Stimulation (PNS) is performed via standard surgical tools and techniques, as described in (K203547).

This looks like a 510(k) summary, which typically focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone study with specific acceptance criteria and performance metrics for a novel AI device. The document mostly highlights the similarities between the subject device (K221376) and its predicate (K203547).

Based on the provided text, there is no specific AI component or algorithm mentioned, nor are there acceptance criteria or a study described to demonstrate the performance of such a component. The device is a "Nalu Neurostimulation System" which appears to be a hardware device for spinal cord and peripheral nerve stimulation. The changes referenced are related to "Clinician Programmer" software differences for therapy configuration, rather than an AI/ML algorithm that interprets data or makes diagnostic decisions.

Therefore, most of the questions you've asked about acceptance criteria, study details, ground truth, sample sizes, and involvement of experts/AI effectiveness are not applicable to this submission as it doesn't describe an AI/ML device in the context of the typical information provided if it were an AI/ML device.

Here's an attempt to answer your questions based only on the provided text, highlighting where the information is absent because the device does not appear to be an AI/ML product as you seem to be assuming:

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

The document does not explicitly state acceptance criteria in the form of performance metrics (e.g., sensitivity, specificity, AUC) that would be expected for an AI device. Instead, it demonstrates an acceptance of "substantial equivalence" to a predicate device by showing that the technological characteristics and indications for use are the same, and that non-clinical testing confirms safety and performance within established limits.

The tables (Table 1, Table 2, Table 3) provided in the document compare the technological characteristics and therapeutic parameters of the subject device (K221376) and its predicate device (K203547). The "reported device performance" in this context is that these characteristics are "Same as predicate" or that any differences "do not impact the safety and effectiveness of the device."

Table of Acceptance Criteria and Reported Device Performance (as inferred from the document):

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

Not applicable. The document states, "Nalu Medical determined that bench and non-clinical testing are sufficient to demonstrate that the Nalu Neurostimulation system is as safe and effective as the predicate device." No clinical data (which might involve a test set, sample size, or patient data provenance) was required or submitted for this 510(k) submission, as the device's substantial equivalence was established through non-clinical testing and comparison to the predicate.

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)

Not applicable. As no clinical study or test set for an AI/ML algorithm was conducted/submitted, there was no need for experts to establish ground truth. The device is a neurostimulation system, not an AI diagnostic or interpretive tool.

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

Not applicable. No test set requiring adjudication was used.

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

Not applicable. This device is not an AI-assisted diagnostic or interpretive tool, and no MRMC study was performed.

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

Not applicable. This device is not an AI algorithm. Its functionality involves hardware for neurostimulation, with software controlling the programming and delivery of stimulation.

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

Not applicable. Ground truth for an AI algorithm is not relevant here as the device is not an AI/ML product. The "ground truth" for this submission is implicitly the established safety and effectiveness of the predicate device, validated through non-clinical engineering and performance testing.

8. The sample size for the training set

Not applicable. No AI/ML model training was described or performed for this device.

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

Not applicable. As no training set for an AI/ML model was used, no ground truth needed to be established for it.

Ask a specific question about this device

For Spinal Cord Stimulation: This system is indicated as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach for chronic, intractable pain of the trunk and/or limbs, including unilateral or bilateral pain. The trial devices are solely used for trial stimulation (no longer than 30 days) to determine efficacy before recommendation for a permanent (long term) device.

For Peripheral Nerve Stimulation: This system is indicated for pain management in adults who have severe intractable chronic pain of peripheral nerve origin, as the sole mitigating agent, or as an adjunct to other modes of therapy used in a multidisciplinary approach. The system is not intended to treat pain in the craniofacial region. The trial devices are solely used for trial stimulation (no longer than 30 day) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu Neurostimulation System has been cleared by the FDA for spinal cord stimulation, and peripheral nerve stimulation (K201618), to provide therapeutic relief for chronic, intractable pain of the trunk and/or limbs including unilateral, bilateral nerve pain. The Nalu Neurostimulation therapy utilizes pulsed electrical current to create an energy field that acts on nerves in the spinal cord or peripheral nerve to inhibit the transmission of pain signals to the brain. The Nalu System is implanted only following a successful trial period using the Nalu Neurostimulation trial system. The Nalu Neurostimulation System consists of several components. The implantable pulse generator (IPG) provides electrical stimulation pulses that are transmitted through the leads, to the desired location, either on the spinal cord or peripheral nerve site. The leads are implantable and designed to deliver electrical pulses to the nerves via an array of four or eight cylindrical electrodes at the distal end. The Trial Therapy Disc or the Therapy Disc houses the battery and electronics for RF power and controls the IPG for therapy delivery via the remote programmer. Implantation of the Nalu IPG and lead components for spinal cord stimulation (SCS) or peripheral nerve stimulation (PNS) is performed via standard surgical tools and techniques, as described in (K201618).

Here's a breakdown of the acceptance criteria and study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria or performance metrics in the way one might expect for a diagnostic or AI-based device's clinical performance. Instead, the submission describes the Nalu Neurostimulation System and its substantial equivalence to predicate devices, focusing on technical specifications and safety rather than a measurable clinical outcome in a performance study.

The closest to "acceptance criteria" are the parameters defining the device's operational range, and the "reported device performance" is that these parameters are within acceptable limits compared to predicate devices, demonstrating substantial equivalence.

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

The document does not describe a clinical performance study with a "test set" from real patient data in the context of an AI/diagnostic device. Instead, it refers to "testing" performed to support the safety and performance of the device. This testing appears to be primarily non-clinical (bench/laboratory) testing of electrical and software parameters.

Therefore, there is no mention of a sample size for a test set of patient data, nor data provenance (country of origin, retrospective/prospective).

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not applicable and not provided. The study focuses on evaluating technical parameters against established medical device safety standards and comparison to predicate devices, not on a ground truth established by medical experts for diagnostic accuracy.

4. Adjudication Method

This information is not applicable and not provided, as the submission does not involve expert review or adjudication of clinical cases for diagnostic or performance accuracy.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. This device is a neurostimulation system for pain relief, not a diagnostic imaging or AI-assisted diagnostic tool that would typically undergo MRMC studies to assess human reader improvement. The submission focuses on demonstrating substantial equivalence in technical characteristics and safety.

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

This concept is not directly applicable. The "device" itself (Nalu Neurostimulation System) is a therapeutic electrical stimulator. The "software" changes described are modifications to its operational parameters. The performance testing referenced is likely to evaluate the hardware and software functionality as an integrated system, ensuring it operates within safe and effective limits. There isn't an "algorithm only" component in the sense of an AI interpreting inputs to provide diagnostic outputs.

7. The type of ground truth used

The "ground truth" for this submission appears to be regulatory and engineering standards, and the specifications and performance characteristics of legally marketed predicate and reference devices. The evaluation focuses on whether the subject device's technical specifications and functionality (particularly the updated software parameters) fall within the established safe and effective ranges of these comparable devices.

8. The sample size for the training set

This information is not applicable and not provided. The device is not an AI/ML model that would train on a dataset. The software changes are operational programming changes for the neurostimulator.

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

This information is not applicable and not provided, as there is no "training set" for an AI/ML model.

Ask a specific question about this device

The Nalu Neurostimulation System is indicated as the sole mitigating agent or as an adjunct to other modes of therapy used in a multidisciplinary approach for chronic, intractable pain of the trunk and/or limbs, including unilateral or bilateral pain.

The trial devices are solely used for trial stimulation (no longer thank 30 days) to determine efficacy before recommendation for a permanent (long term) device.

The Nalu Neurostimulation system (also referred to as the "Nalu System") is used for spinal cord stimulation to provide therapeutic relief for chronic, intractable pain of the trunk and/or limbs including unilateral or bilateral pain. The Nalu Neurostimulation system incorporates a miniature implanted neurostimulator, powered by an externally worn device. Similar to the predicate Stimwave system, the Nalu Neurostimulation therapy utilizes pulsed electrical current to create an energy field that acts on nerves in the spinal cord to inhibit the transmission of pain signals to the brain. The Nalu System is implanted only following a successful trial period using the Nalu Neurostimulation trial system.

The Nalu Neurostimulation System is comprised of 5 elements: Nalu Implantable Pulse Generator, Leads, Surgical and Trial Tools, Externally worn Therapy Discs, and Programmer, Remote.

This document is a 510(k) premarket notification for the Nalu Neurostimulation System, indicating that clinical performance data was not required for substantial equivalence. Therefore, there is no study described in this document that proves the device meets specific acceptance criteria based on human clinical data.

The acceptance criteria described in the document relate to non-clinical performance testing (bench testing, biocompatibility, and animal testing) to demonstrate safety and effectiveness relative to a predicate device.

Here's an breakdown of the information requested, based on the provided text:

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

Since no clinical acceptance criteria or performance metrics were provided in the document due to the nature of a 510(k) without clinical studies, I will summarize the general approach to substantial equivalence and the scope of non-clinical testing.

General Acceptance Criteria (Implied for 510(k) clearance): The Nalu Neurostimulation System is substantially equivalent to the predicate device (Stimwave Freedom SCS System K170141) in terms of:

• Intended Use
• Technological Characteristics
• Principles of Operation

Reported Device Performance (Non-Clinical):

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

• Test Set (Non-Clinical):
  • Animal Study: Six Nalu Neurostimulation IPGs and Lead systems were used in a porcine model. This was a prospective animal study. The specific country of origin for the animal study is not mentioned.
  • Bench Testing: The document does not specify exact sample sizes for each bench test (electrical, mechanical, software), but it implies sufficient testing was conducted to meet relevant international standards and guidance documents. This is typically prospective testing conducted in a laboratory setting.
  • Biocompatibility Testing: The number of samples for biocompatibility testing is not specified but would follow established protocols for ISO 10993. This is typically prospective testing.

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)

• Not applicable for clinical studies. For the non-clinical tests described:
  • Animal Study: The study was conducted by researchers/veterinary staff, but the "ground truth" was established by direct observation and measurement of device performance, tissue response, and lack of complications in the porcine model. No external experts for ground truth establishment were specifically mentioned in this context.
  • Bench/Biocompatibility/Software Testing: Ground truth is established by engineering specifications, validated test methods, and compliance with recognized standards. Expertise would come from internal design and quality engineers, and potentially third-party testing laboratories, but not in the "expert medical consensus" sense.

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

• Not applicable for clinical studies. For the non-clinical tests described, adjudication methods like 2+1 or 3+1 are not used. Results are based on objective measurements and compliance with predefined specifications and standards.

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 done. The document explicitly states: "Nalu Medical determined that bench and non-clinical testing are sufficient to demonstrate that the Nalu Neurostimulation system is as safe and effective as the predicate device. Note that the predicate device did not need clinical evidence to obtain a determination of substantial equivalence." This is a premarket notification (510(k)) that established substantial equivalence based on non-clinical data, not clinical performance or AI assistance for human readers.

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

• Not applicable. The Nalu Neurostimulation System is an implantable medical device for pain relief, not an AI or imaging diagnostic tool. Therefore, standalone algorithm performance is not relevant to this submission.

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

• Non-Clinical Ground Truth:
  • Bench Testing: Engineering specifications, validated test methods, and compliance with national and international standards (e.g., ISO 14708, IEC 60601 series, ISO 11135, CISPR 11).
  • Biocompatibility Testing: Standards-based evaluation (ISO 10993-1) of material interactions with biological systems.
  • Animal Study: Direct observation of surgical usability, RF communication, device stability, and histopathological tissue response in the porcine model, as interpreted by veterinary and scientific experts.

8. The sample size for the training set

• Not applicable. This device is hardware for neurostimulation, not an AI/ML algorithm that requires a training set.

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

• Not applicable. As stated above, this device does not use an AI/ML algorithm with a training set.

Ask a specific question about this device