FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

• The creation of cuts / incisions in the cornea in patients undergoing cataract surgery or other ophthalmic treatment requiring cuts / incisions in the cornea.

Device Description

The VICTUS Femtosecond Laser Platform (VICTUS) is a precision ophthalmic surgical laser. For all indications for use, laser pulses are delivered through a sterile disposable Patient Interface, consisting of a contact lens and suction clip to provide suction. The contact lens and suction clip assembly creates a reference surface for depth control and fix the eye relative to the delivery of the laser beam. Surgical effects are produced by scanning thousands of individual pulses, producing continuous incisions. The location of the tissue photodisruption is controlled by a fixed laser beam focused through a scanning optic system to the desired location. The VICTUS Platform mode of operation delivers femtosecond pulses to produce a pattern of photodisruption to create cuts / separation in ophthalmic tissue. The VICTUS Platform uses vacuum to affix a suction ring to the corneal surface prior to use.

AI/ML Overview

The device referenced in the document is the VICTUS Femtosecond Laser Platform. The document describes a 510(k) submission, which means the device is being compared to a legally marketed predicate device to establish substantial equivalence. Therefore, the "acceptance criteria" discussed here are primarily about demonstrating that the modified device performs similarly to or no worse than the predicate device.

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for device performance in a table, but it does describe the outcomes of the non-clinical and clinical studies designed to show equivalence.

Performance Metric/Study Type	Acceptance Criteria (Implied)	Reported Device Performance
Non-Clinical Performance	Compliance with applicable safety standards (EN ISO 60601-1, -1-2, -2-22).	The VICTUS Femtosecond Laser Platform has undergone testing and is in compliance with applicable safety standards.
	Performance of modified VICTUS Platform remains substantially equivalent to the predicate (K132534).	A variety of test procedures were conducted and the collected data were evaluated by comparing the mean values to specified acceptance criteria and their 95% confidence intervals. The acquired test data successfully verified that the various parameters meet their pre-defined acceptance criteria. The VICTUS Femtosecond Laser Platform has been found to perform equivalently to the predicate device.
Clinical Performance	Intraoperative accuracy of biometry visualization (OCT) comparable to LENSTAR LS 900.	The lens thickness, ACD, and CCT measured by VICTUS OCT were compared with LENSTAR LS900 and the results are consistent.
	Successful completion of laser-assisted capsulotomy without manual intervention for all procedures.	All laser-assisted capsulotomy procedures were completed fully using the VICTUS laser platform with no need for manual intervention to complete the capsulotomy.
	No adverse or serious adverse events reported by investigators.	There were no adverse or serious adverse events reported by the investigators during the clinical study.
	No device malfunctions leading to adverse or serious adverse events.	In addition, there were no device malfunctions which led or potentially led to adverse or serious adverse events.

2. Sample Sizes and Data Provenance

Test Set (Clinical Study):
- Sample Sizes:
  - Femtosecond-laser flap creation (flap group): 58 eyes
  - Femtosecond laser assisted cataract surgery (cataract group): 113 eyes
- Data Provenance: Single-center clinical study (location not specified, but likely where Technolas Perfect Vision GmbH is active). Retrospective analysis of correlation and agreement of biometric data.

3. Number of Experts and Qualifications (for Ground Truth)

The document does not specify the number of experts used to establish ground truth or their qualifications.
For the clinical study, the "consistency" of VICTUS OCT measurements with LENSTAR LS900 implies that the LENSTAR LS900 measurements served as a reference or a highly accepted method. LENSTAR LS900 is a well-established biometer, and its measurements are generally accepted as a clinical standard for these parameters.

4. Adjudication Method (for Test Set)

The document does not describe any adjudication method for the clinical study data or for establishing a ground truth based on multiple expert opinions.
The comparison was made against LENSTAR LS900, suggesting it served as the reference standard.

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

No MRMC comparative effectiveness study was done comparing human readers with and without AI assistance. The device is a laser platform for surgical procedures, not an AI-assisted diagnostic tool for human readers.

6. Standalone (Algorithm Only) Performance Study

A form of standalone performance was done for the device. The non-clinical performance data involved testing the device against engineering specifications and predicate equivalence using various materials (porcine eyes, agarose gel, PETG, PMMA).
The clinical study also evaluated the device's performance in creating capsulotomies and biometry measurements directly.

7. Type of Ground Truth Used

Non-Clinical Performance: Engineering specifications, measurements against a predicate device, and physical properties of test materials (e.g., cut quality in various materials).
Clinical Performance:
- For biometry accuracy: Comparison with measurements from a commercially available and clinically accepted biometer (LENSTAR LS900). This acts as a proxy for "gold standard" or highly reliable measurement.
- For capsulotomy completeness: Observation of the actual surgical outcome (full completion without manual intervention).
- For adverse events: Reported clinical observations by investigators.

8. Sample Size for the Training Set

The document does not mention a training set in the context of an algorithm or AI. This submission is for a medical device (laser platform) that performs physical procedures, not a software algorithm that learns from data in the traditional AI sense. Its "training" would be more akin to design verification and validation, and calibration.

9. How Ground Truth for Training Set was Established

As there's no explicitly defined "training set" for an AI algorithm as per the question's premise, this question is not directly applicable. If interpreting "training set" as the data used during the device's development and design verification, the ground truth would have been established through engineering design specifications, bench testing protocols, and comparison with predicate device characteristics and safety standards.

Summary

Regulation Number and Section

§ 886.4390 Ophthalmic laser.

(a)
Identification. An ophthalmic laser is an AC-powered device intended to coagulate or cut tissue of the eye, orbit, or surrounding skin by a laser beam.(b)
Classification. Class II.