AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The SOLTIVE™ Laser System (SOLTIVE™ Pro SuperPulsed Laser, SOLTIVE™ Premium SuperPulsed Laser, SOLTIVE™ Laser Fibers, and Accessories) is intended for incision, resection, ablation, coagulation, hemostasis, and vaporization of soft tissue, with or without an endoscope, in the following indications: urology, lithotripsy, gastroenterological surgery and gynecological surgery.

Device Description

The SOLTIVE™ Laser System is a thulium fiber laser, producing a pulsed beam of coherent nearinfrared light (1940 nm) upon activation by a footswitch. The beam is then directed to the treatment zone by means of an optical fiber coupled to a handpiece. An integrated LED touch screen gives the user control over the necessary laser system parameters. The SOLTIVE Laser System is equipped with a 550 nm aiming beam. The SOLTIVE Laser System is comprised of a choice of two models - Premium Laser System and Pro Laser System, laser fibers and accessories. The Premium laser has a maximum power output of 60 Watts and a maximum Frequency output of 2400 Hz and a secondary, foldable screen is provided. The Pro laser can operate at a maximum power of 35 Watts and Frequency output limited to 100Hz. Both systems are compact, designed to fit onto an optional laser cart and are operated with a footswitch (wired or wireless). The Soltive Laser System must be operated with a Soltive Laser Fiber, offered in quartz core diameters from 150 - 940 microns.

AI/ML Overview

The provided document is a 510(k) Premarket Notification for the SOLTIVE™ Laser System. It focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets acceptance criteria through a traditional clinical study with a defined test set and ground truth.

The "Performance Data" section (Section VII) describes non-clinical testing and software verification. Since this is a 510(k) submission, the primary goal is to show the device is as safe and effective as a legally marketed predicate, not necessarily to establish de novo "acceptance criteria" against clinical outcomes in the same way one might for a novel AI diagnostic device.

Therefore, many of the requested details (like sample size for a test set, expert involvement for ground truth, MRMC studies, and standalone performance) are not applicable or not provided in the context of this 510(k) for a medical laser system. The "study" here is primarily non-clinical and software-based to support the claim of substantial equivalence despite minor changes.

However, I can extract the relevant information from the provided text regarding the closest equivalent to "acceptance criteria" and the "study" conducted.

Here's a breakdown of the available information based on your request:

1. Table of acceptance criteria and the reported device performance:

The document describes "acceptance criteria" within the context of design verification testing.

Acceptance Criteria (from Design Verification testing)Reported Device Performance
Tissue thermal effect from accidental exposure over the range of laser settings has remained unchanged despite changes to energy parameters."All data sets demonstrated statistical equivalency with p-value greater than 0.05 between the data set containing the predicate preset and the data set containing revised presets, meeting the acceptance criteria of the Design Verification testing. This demonstrates the tissue effect from accidental exposure over the range of laser settings has remained unchanged despite the changes to the preset energy parameters."
Implicit acceptance: Software is verified and validated to industry guidelines."Software verification and validation regression testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff. 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'"

2. Sample sized used for the test set and the data provenance:

  • Sample Size: Not explicitly stated as a "sample size" for a typical test set. The non-clinical testing involved "porcine ureter tissue" for thermal effect testing and "simulated stones" for ablation testing. The number of samples/tests is not quantified in the provided text.
  • Data Provenance:
    • Country of Origin: Not specified for the non-clinical testing data.
    • Retrospective/Prospective: These were non-clinical, in-vitro tests, so the concept of retrospective or prospective doesn't directly apply in the same way as for human clinical data. They were conducted specifically for this submission.

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

  • Not Applicable. For this type of submission (510(k) for a laser, with non-clinical and software testing), expert-established ground truth on a test set (e.g., for diagnostic accuracy) is not typically required or reported. The "ground truth" for the non-clinical tests would be the measured physical properties (e.g., thermal effect depth, ablation rate).

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

  • Not Applicable. This is not a diagnostic device or a study involving human readers/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:

  • No. This is a surgical laser system, not an AI diagnostic device. MRMC studies are not relevant here.

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

  • Not applicable in the AI sense. The "device" itself (the laser system) was tested in a standalone fashion in a lab setting (non-clinical tissue and simulated stone testing), but this is "device performance" rather than "algorithm only" in the context of an AI-driven device.

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

  • Measured Physical Properties:
    • For Soft Tissue Thermal Effect Testing: The "ground truth" involved measurements of "tissue thermal effect depths and widths."
    • For Simulated Stone Ablation Testing: The "ground truth" involved characterizing the "stone ablation rate."

8. The sample size for the training set:

  • Not Applicable. This device is a laser system and its software manages system parameters; it does not employ machine learning that would require a "training set" in the typical sense of AI/ML.

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

  • Not Applicable. (See point 8).

§ 878.4810 Laser surgical instrument for use in general and plastic surgery and in dermatology.

(a)
Identification. (1) A carbon dioxide laser for use in general surgery and in dermatology is a laser device intended to cut, destroy, or remove tissue by light energy emitted by carbon dioxide.(2) An argon laser for use in dermatology is a laser device intended to destroy or coagulate tissue by light energy emitted by argon.
(b)
Classification. (1) Class II.(2) Class I for special laser gas mixtures used as a lasing medium for this class of lasers. The devices subject to this paragraph (b)(2) are exempt from the premarket notification procedures in subpart E of part 807 of this chapter, subject to the limitations in § 878.9.