Search Results

The LenSx Laser system is indicated for use:

• In the creation of corneal cuts/incisions (single-plane, multi-plane, and arcuate), anterior capsulotomy and laser phacofragmentation during cataract surgery. Each of these procedures may be performed either individually or consecutively during the same surgery.
• In the creation of corneal cuts/incisions (single-plane, multi-plane, and arcuate) during Implantable Collamer Lens (ICL) surgery.
• In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea.
• In the creation of corneal pockets for placement/insertion of a corneal inlay device; and for creation of corneal tunnels for the placement of corneal rings.

The LenSx Laser system is an ophthalmic surgical laser which uses focused femtosecond laser pulses to create vapor bubbles which disrupts/separates tissue (photodisruption) within the lens capsule, crystalline lens, and the cornea. A computer-guided delivery system places the laser pulses in a pattern to produce an incision/cut.

The laser pulses are delivered through a sterile, disposable applanating lens and suction ring that contacts the cornea and fixes the eye with respect to the laser delivery system.

The interface between the laser and patient is the Patient Interface that connects to the delivery system which is docked to the patient's cornea. Two models of the Patient Interface accessory are offered for use with the LenSx Laser: the LenSx Laser Patient Interface and the LenSx Laser SoftFit Patient Interface. Both models consist of a sterile, disposable applanating lens and suction ring assembly. The LenSx Laser SoftFit Patient Interface also comes with a soft contact lens that is positioned against the external surface of the Patient Interface glass. For cataract procedures, the LenSx Laser SoftFit Patient Interface is used. The LenSx Laser Patient Interface is used for corneal, flap, tunnel, and pocket incisions. Refer to the Instructions for Use supplied with the LenSx Laser Patient Interface for preparation and application.

The LenSx Laser system is for prescription use and should only be operated by a trained physician. The LenSx Laser system is intended to be used within a clinic(s)/hospital(s)/surgical practice network.

Based on the provided FDA 510(k) Clearance Letter for the LenSx Laser System, this document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone study with detailed acceptance criteria and performance data for a new AI or novel diagnostic device.

The clearance is for a modified version of an existing device (LenSx Laser System) with software updates and an expanded indication for Implantable Collamer Lens (ICL) surgery. The general approach taken is to show that these modifications do not raise new questions of safety or efficacy and that the device remains substantially equivalent to its predicate. Therefore, the requested information regarding acceptance criteria and a study proving the device meets those criteria (especially in the context of an AI/diagnostic device) is not explicitly detailed in this 510(k) summary.

However, I can extract the relevant information presented, acknowledging that it's framed within the context of demonstrating substantial equivalence for a modified device, rather than a de novo clearance for a completely new technology with novel performance claims.

Here's an attempt to answer the questions based on the provided text, highlighting where the information is not applicable or not detailed in this type of submission:

Acceptance Criteria and Device Performance Study (as inferred from the 510(k) Summary)

The 510(k) summary indicates that the modifications to the LenSx Laser System are minor and do not introduce new safety or efficacy concerns. The "acceptance criteria" are implied by the successful completion of various non-clinical tests demonstrating that the device continues to meet its intended design specifications and functional requirements, performing as intended and being equivalent to the predicate. There are no specific numerical performance metrics provided in the summary that would typically be seen for a new diagnostic or AI device (e.g., sensitivity, specificity, accuracy against a gold standard).

Table of Acceptance Criteria and Reported Device Performance

Since this is a modification to an existing device, the "acceptance criteria" are generally about maintaining the performance and safety profiles of the predicate. The "reported device performance" refers to the successful completion of the tests.

Study Details (as applicable)

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: Not specified in terms of clinical cases or patient data, as no animal or clinical testing was deemed necessary for this submission. The "test set" primarily refers to bench testing, software verification/validation, and regulatory compliance checks.
   • Data Provenance: Not applicable as no clinical or animal data was collected for this submission. The data provenance for compliance testing is internal Alcon laboratories.

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

   • Not applicable as this 510(k) submission does not rely on expert-adjudicated ground truth from a clinical test set. The ground truth for engineering and software tests is based on design specifications, recognized standards, and regulatory guidance. For clinical ground truth, the submission relies on the established safety and efficacy of the predicate device and the assessment that the modifications do not alter this.

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

   • Not applicable. There was no clinical test set requiring expert adjudication.

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 MRMC study was performed or required. The device is a surgical laser, not an AI-assisted diagnostic tool that would typically involve 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 algorithm. However, the device itself, including its software, undergoes standalone functional and safety testing as part of the "Non-Clinical Testing" detailed in Section 7.1, such as "Software verification and validation testing" and "Performance Testing." These tests ensure the device (algorithm and hardware) performs its functions correctly according to specifications, independent of operator interaction after initial surgical planning.

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

   • For the non-clinical and software testing, the "ground truth" is defined by:
     • Engineering Specifications: The pre-defined technical and functional requirements for the laser system.
     • International and National Standards: Compliance with standards like IEC 60601 series, ANSI Z80.36-2021 for safety and performance.
     • FDA Guidance Documents: Compliance with FDA recommendations for software documentation and cybersecurity.
     • Predicate Device Performance: The established safety and effectiveness of the existing LenSx Laser System serves as the clinical benchmark.

7. The sample size for the training set:

   • Not applicable. This is not an AI/machine learning device that relies on a "training set" of data in the typical sense for a new diagnostic algorithm. The software modifications are deterministic or rule-based enhancements (e.g., embedded calculator, new cut patterns).

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

   • Not applicable for the same reason as above. If there were internal development/optimization processes for the new features (e.g., nomogram calculations), their accuracy and "ground truth" would be established through mathematical validation, simulation, and bench testing against known physical principles or desired outcomes, rather than a data-driven training set.

Ask a specific question about this device

The LenSx Laser System is indicated for use:

• · In the creation of corneal cuts/incisions (single-plane, and arcuate), anterior capsulotomy and laser phacofragmentation during cataract surgery. Each of these procedures may be performed either individually or consecutively during the same surgery.
• · In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea.
• · In the creation of corneal pockets for placement/insertion of a corneal inlay device and for creation of corneal tunnels for the placement of corneal rings.

The LenSx Laser System is an ophthalmic surgical laser which uses focused femtosecond laser pulses to create incisions and to separate tissue within the lens capsule, crystalline lens, and the cornea. A femtosecond light pulses is focused into a sufficiently small spot in order to achieve photodisruption of the tissue inside the focus. A tiny volume of tissue, a few microns in diameter, is thereby photodisrupted at the laser focus. A computer-controlled scanning system directs the focused laser beam throughout a three-dimensional pattern to produce an incision. The surgical effect is produced by scanning thousands of individual pulses per second to produce a continuous incision or tissue separation.
The location of the tissue photodisruption is controlled by moving the focus of the laser beam to the desired surgical target location. A computer-controlled scanning system directs the laser beam throughout a three-dimensional pattern to produce an incision. The laser pulses are delivered through a sterile, disposable applanating lens and suction ring assembly that contacts the cornea and fixes the eye with respect to the delivery system.

The provided text describes a 510(k) premarket notification for the LenSx Laser System, which is an ophthalmic surgical laser. The submission aims to seek clearance for additional indications for use: the creation of corneal tunnels and corneal pockets. The document states that the LenSx Laser System is "essentially the same device as the predicate LenSx Laser System" and that "All modifications were tested to show substantial equivalence to the predicate device as safe and as effective as the predicate device."

However, the provided text does not contain specific acceptance criteria, reported device performance metrics, or details about the study design elements such as sample sizes, ground truth establishment, expert qualifications, or MRMC studies. The "Performance Data" section discusses that the accuracy and reproducibility of depths and geometry of treatment patterns were evaluated, but it does not provide the quantitative results or the acceptance criteria used for these evaluations.

Therefore, based solely on the provided text, I cannot complete the requested information, specifically:

1. A table of acceptance criteria and the reported device performance: This information is not present in the document. The document mentions "acceptance criteria established for the predicate LenSx Laser" but does not state what those criteria are or the quantitative results achieved by the modified device against them.
2. Sample sized used for the test set and the data provenance: Not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
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 a surgical laser, not an AI-assisted diagnostic tool for human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This device is a surgical laser, not an AI algorithm. Its performance is intrinsic to its mechanical and optical capabilities in creating cuts.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): While it mentions evaluating "accuracy and reproducibility of the depths and geometry," it doesn't specify how these were measured to establish ground truth (e.g., using imaging, physical measurements, etc.).
8. The sample size for the training set: Not applicable. This is a hardware device with software controls, not a machine learning model requiring a training set in the typical sense.
9. How the ground truth for the training set was established: Not applicable for the same reason as above.

Summary of what is present:

• Device Name: LenSx Laser System
• Purpose of Submission: Seek clearance for additional indications for use:
  • Creation of corneal pockets for placement/insertion of a corneal inlay device.
  • Creation of corneal tunnels for the placement of corneal rings.
• Comparison to Predicate: The modified system is stated to be "substantially equivalent" to the primary predicate device (K163551) and additional predicate devices (K141852, K141476) in terms of indications for use, technological characteristics, and fundamental scientific technology.
• Performance Data Mentioned (but no specifics): Evaluation of accuracy and reproducibility of depths and geometry of previously cleared and new treatment patterns.
• Safety Standards Compliance: The device underwent medical electrical equipment testing and was found compliant with several IEC and ANSI AAMI standards (e.g., IEC 60601-1, IEC 60601-1-2, IEC 60601-2-22, IEC 60825-1, IEC 62304, IEC 62366).
• Software Verification and Validation: Conducted according to FDA guidance for "major" level of concern software, demonstrating fulfillment of functional and safety critical requirements.

Conclusion: The provided document is a 510(k) summary focusing on substantial equivalence for a surgical laser, and while it mentions performance data were collected, it does not disclose the quantitative acceptance criteria or the specific results of those performance tests. It does not describe a study that would typically involve a test set with ground truth established by experts, as is common for diagnostic imaging AI devices, but rather focuses on engineering and functional performance of the laser itself.

Ask a specific question about this device

The LenSx Laser is indicated for use:
· In the creation of corneal cuts/incisions (single-plane, multi-plane and arcuate), anterior capsulotomy and laser phacofragmentation during cataract surgery. Each of these procedures may be performed either individually or consecutively during the same surgery.
· In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea.

The LenSx Laser System is an ophthalmic surgical laser which uses focused femtosecond laser pulses to create incisions and to separate tissue within the lens capsule, crystalline lens, and the cornea. A femtosecond light pulses is focused into a sufficiently small spot in order to achieve photodisruption of the tissue inside the focus. A tiny volume of tissue, a few microns in diameter, is thereby photodisrupted at the laser focus. A computer-controlled scanning system directs the focused laser beam throughout a three-dimensional pattern to produce an incision. The surgical effect is produced by scanning thousands of individual pulses per second to produce a continuous incision or tissue separation.
The laser pulses are delivered through a Patient Interface accessory that is placed on the surface of the cornea and fixes the position of the eye with respect to the delivery system. Two models of the Patient Interface accessory are offered for use with the LenSx Laser System: the LenSx Laser Patient Interface and the LenSx SoftFit Patient Interface. Both models consist of a sterile, disposable applanating lens and suction ring assembly that contacts the cornea and fixes the eye with respect to the delivery system. The LenSx SoftFit Patient Interface model is offered with three different sizes of soft contact lenses that are positioned against the internal surface of the patient Interface glass. For cataract procedures, the LenSx SoftFit Patient Interface is used. For corneal flap procedures, the LenSx Laser Patient Interface is used.

Here's a breakdown of the acceptance criteria and the study information based on the provided text, formatted as requested:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the exact sample size used for the performance testing of the new SoftFit Insert sizes. It generally states "Performance testing on the new sizes."

The data provenance is not explicitly stated (e.g., country of origin). The testing described appears to be internal device validation rather than a clinical study with patient data provenance in the context of country of origin. The study is prospective in nature, as it involves testing new versions of a device component.

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

This information is not provided in the document. The performance testing described focuses on objective measurements of device output (accuracy and reproducibility of laser patterns) rather than subjective human assessment requiring expert ground truth in the traditional sense of clinical imaging interpretation.

4. Adjudication Method for the Test Set

This information is not applicable as the testing described focuses on objective device performance metrics and does not involve human interpretation or subjective assessment that would require an adjudication method.

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

There is no indication that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was performed or that AI is involved. The changes relate to physical device components (contact lens inserts) and their impact on laser performance during surgery, not an AI-assisted diagnostic or interpretative system.

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

This is not applicable. The device is an ophthalmic surgical laser system, and the changes relate to patient interface accessories. There is no mention of algorithms or AI being evaluated in a standalone capacity within this document.

7. The Type of Ground Truth Used

The ground truth used for this performance testing is based on the objective measurements of the physical outcomes of the laser treatment patterns created by the device, such as the depths and geometry of corneal cuts and capsulotomies. This would likely involve metrology and precision instruments to characterize the laser's output when the new inserts are used, compared to established specifications for the predicate device.

8. The Sample Size for the Training Set

This information is not provided and is not applicable in the context of this device modification. The device is a physical laser system, not a machine learning or AI model that requires a training set.

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

This information is not applicable as there is no training set for an AI/ML model for this device.

Ask a specific question about this device

In the creation of corneal cuts/incisions (single-plane, multi-plane and arcuate), anterior capsulotomy and laser phacofragmentation during cataract surgery. Each of these procedures may be performed either individually or consecutively during the same surgery.
In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea.

The LenSx Laser System is an ophthalmic surgical laser which uses focused femtosecond laser pulses to create incisions and to separate tissue within the lens capsule, crystalline lens, and the cornea. A femtosecond light pulses is focused into a sufficiently small spot in order to achieve photodisruption of the tissue inside the focus. A tiny volume of tissue, a few microns in diameter, is thereby photodisrupted at the laser focus. A computer-controlled scanning system directs the focused laser beam throughout a threedimensional pattern to produce an incision. The surgical effect is produced by scanning thousands of individual pulses per second to produce a continuous incision or tissue separation.

The laser pulses are delivered through a Patient Interface accessory that is placed on the surface of the cornea and fixes the position of the eye with respect to the delivery system. Two models of the Patient Interface accessory are offered for use with the LenSx Laser System: the LenSx Laser Patient Interface and the LenSx SoftFit Patient Interface. Both models consist of a sterile, disposable applanating lens and suction ring assembly that contacts the cornea and fixes the eye with respect to the delivery system. In addition, LenSx SoftFit Patient Interface model comes with a soft contact lens that is positioned against the internal surface of the patient Interface glass. For cataract procedures, the LenSx SoftFit Patient Interface is used. For corneal flap procedures, the LenSx Laser Patient Interface is used.

The provided text describes modifications to the LenSx Laser System and its substantial equivalence to predicate devices, but it does not contain the specific details about acceptance criteria and a study proving those criteria as requested in the prompt.

The document states:

• "Evaluation of the accuracy and reproducibility of the depths and geometry of each of the previously cleared treatment patterns using the modified LenSx Laser in comparison to acceptance criteria established for the predicate LenSx Laser."
• "Evaluation of the accuracy and reproducibility of energy stability using the modified LenSx Laser in comparison to acceptance criteria established for the predicate LenSx Laser."

However, the actual values for these acceptance criteria are not provided, nor are the detailed results of the studies that would prove the device met these criteria. The document summarizes the findings in a high-level manner ("high degree of accuracy and reproducibility").

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, sample size, ground truth details, or info on MRMC studies based solely on the provided text.

Based on the provided information, I can only provide general statements about what was tested and concluded:

Summary of Device Evaluation (Limitations apply as specific criteria and study details are missing):

1. Acceptance Criteria and Reported Device Performance:

2. Sample Size and Data Provenance:

• The document does not specify sample sizes for any of the non-clinical tests.
• The data provenance (e.g., country of origin) is not mentioned. The testing is described as "Non-clinical Testing."

3. Number of Experts and Qualifications:

• The document does not mention the use of experts to establish ground truth for testing. The testing appears to be objective, engineering-focused verification and validation.

4. Adjudication Method:

• Adjudication methods are not applicable or mentioned, as the testing described is non-clinical performance verification.

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

• No MRMC comparative effectiveness study was performed. The document explicitly states: "The scope of the software and hardware modification did not require clinical testing to establish safety and effectiveness of the modified device."

6. Standalone Performance (Algorithm Only):

• This is not an AI algorithm; it's a laser surgical system. The "performance data" refers to the accuracy, reproducibility, and energy stability of the physical device and its software functions in a non-clinical setting.

7. Type of Ground Truth Used:

• For the non-clinical testing, the "ground truth" would likely be engineering specifications, established physical measurements, and comparison to the performance of the predicate device. Details are not provided.

8. Sample Size for the Training Set:

• This is not an AI/machine learning device, so there is no concept of a "training set" in the context of the device's function or the described testing.

9. How Ground Truth for Training Set was Established:

• Not applicable (see point 8).

Ask a specific question about this device

The LenSx Laser System is indicated for use:

• In the creation of corneal cuts/incisions, anterior capsulotomy and laser phacofragmentation during cataract surgery. Each of these procedures may be performed either individually or consecutively during the same surgery.
• In the creation of a lamellar cut/resection for lamellar keratoplasty, and in the creation of a penetrating cut/incision for penetrating keratoplasty.
• In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea.

The LenSx Laser System uses focused femtosecond laser pulses to create incisions and separate tissue in the lens capsule, crystalline lens, and the cornea. Individual photodisruption locations are controlled by repeatedly repositioning the laser focus. The light pulse is focused into a sufficiently small spot in order to achieve photodisruption of the tissue inside the focus. A tiny volume of tissue, a few microns in diameter, is thereby photodisrupted at the laser focus. The surgical effect is produced by scanning thousands of individual pulses per second to produce a continuous incision or tissue separation. The location of the tissue photodisruption is controlled by moving the focus of the laser beam to the desired surgical target location. A computer-controlled scanning system directs the laser beam throughout a three-dimensional pattern to produce an incision. The laser pulses are delivered through a Patient Interface accessory that is placed on the surface of the cornea and fixes the eye with respect to the delivery system. This 510(k) premarket notification is being submitted to seek clearance for an additional patient interface accessory to be offered for use with cataract procedures in addition to the original patient interface accessory to the LenSx Laser System (cleared under K120732 for cataract and lamellar resection procedures). The SoftFit Patient Interface differs from the original Patient Interface (K120732) in that it has an extended suction ring skirt that enables positioning of a soft contact lens against the internal surface of the patient interface glass. The soft contact lens is similar to a standard daily wear contact lens indicated for the correction of ammetropia, with a slightly modified edge to enable fitting into the SoftFit Patient Interface. The materials and manufacturing processes used for the soft contact lens component of the proposed SoftFit Patient Interface accessory are identical to the processes used for the predicate daily wear soft contact lens (K100244). With the soft contact lens insert in place, the SoftFit Patient Interface is then mounted onto the LenSx laser system for docking onto the eye in a manner that is identical to the original LenSx Laser Patient Interface. As a result, use of the soft contact lens substantially reduces intraocular pressure (IOP) during the laser procedure, enhancing comfort and addressing potential concerns in patients with a history of glaucoma. For cataract procedures, either a LenSx Laser Patient Interface or a SoftFit Patient Interface may be used. The original LenSx Laser Patient Interface is used for keratoplasty and corneal flaps.

The provided text describes a 510(k) premarket notification for an additional patient interface accessory (SoftFit Patient Interface) for the LenSx Laser System. The primary purpose of this submission is to demonstrate substantial equivalence to a predicate device and to show that the new accessory does not raise new questions of safety or effectiveness.

Here's an analysis of the acceptance criteria and study information based only on the provided text:

1. Table of acceptance criteria and reported device performance:

The document doesn't explicitly define formal "acceptance criteria" in a quantitative manner (e.g., "accuracy must be >X%"). Instead, it describes performance evaluations conducted to demonstrate substantial equivalence to the predicate device, particularly focusing on the differences introduced by the SoftFit Patient Interface.

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

The document does not explicitly state the sample sizes used for the performance evaluations (e.g., number of eyes, number of procedures).

The data provenance is not explicitly mentioned as retrospective or prospective, nor is the country of origin.

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

This information is not provided in the document. The type of performance evaluation described (holding force, IOP, accuracy of laser patterns) suggests objective measurements rather than expert consensus on a diagnostic outcome.

4. Adjudication method for the test set:

Not applicable, as the performance tests described involve objective measurements rather than subjective assessments 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:

Not applicable. This device is a surgical laser system with a patient interface accessory, not an AI-assisted diagnostic or imaging device that would typically involve a multi-reader multi-case study to assess human reader improvement.

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

Not applicable. The "device" in question is a surgical laser system designed for in-vivo use with human intervention, not a standalone algorithm. The performance tests assessed the physical and mechanical aspects of the new patient interface.

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

The "ground truth" for the performance evaluations would be:

• Intraocular Pressure (IOP): Direct measurement using appropriate medical devices.
• Holding Force: Direct measurement using mechanical testing methods.
• Accuracy and Reproducibility of Cataract Treatment Patterns (depths and geometry): Measurement of the laser's physical output (e.g., incision depth, shape) using precision instruments (e.g., optical coherence tomography, microscopy, or other metrology tools).

8. The sample size for the training set:

Not applicable. The device described is a medical device (laser system accessory) and not an AI/ML model that requires a "training set."

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

Not applicable, as there is no training set for this type of medical device submission.

Ask a specific question about this device

The LenSx Laser is indicated for use in patients undergoing cataract surgery for removal of the crystalline lens. Intended uses in cataract surgery include anterior capsulotomy, phacofragmentation, and the creation of single plane and multi-plane arc cuts/incisions in the cornea, each of,which may be performed either individually or consecutively during the same procedure.

The LenSx Laser is indicated for use in patients undergoing penetrating keratoplasty for full thickness corneal replacement and in patients undergoing lamellar keratoplasty for partial thickness corneal replacement. The intended use in penetrating and lamellar keratoplasty includes the creation of single plane and multi-plane arc and circular cuts/incisions in the cornea.

The LenSx Laser System uses focused femtosecond laser pulses to create incisions and separates tissue in the lens capsule, crystalline lens and cornea. Individual photodisruption locations are controlled by repeatedly repositioning the laser focus. The light pulse is focused into a sufficiently small spot in order to achieve photodisruption of the tissue inside the focus. A tiny volume of tissue, a few microns in diameter, is thereby photodisrupted at the laser focus. The surgical effect is produced by scanning thousands of individual pulses per second to produce a continuous incisions or tissue separation.

The location of the tissue photodisruption is controlled by moving the focus of the laser beam to the desired surgical target location. A computer-controlled scanning system directs the laser beam throughout a three-dimensional pattern to produce an incision. The laser pulses are delivered through a sterile, disposable applanating lens and suction ring assembly that contacts the cornea and fixes the eye with respect to the delivery system.

The LenSx Laser is an ophthalmic surgical laser that has previously been cleared for use in:

• • Anterior capsulotomy (K082947), performed by delivering a cylindrical pattern of laser pulses to intersect the anterior lens capsule.
• · Phacofragmentation (K090452), performed by delivering series of laser pulses to form two intersecting ellipsoidal planes that divides the lens into quadrants.
• . Cuts/incisions for keratoplasty (K092647) which are performed by delivering a pattern of circles and arcs with programmable incision length and depth.

Here's an analysis of the provided text regarding the acceptance criteria and study for the LenSx Laser System:

1. Table of Acceptance Criteria and Reported Device Performance:

The document explicitly states that the acceptance criteria for the modified LenSx Laser System were the "same parameter acceptance criteria as established for single plane cuts/incisions" for the predicate LenSx 550 Laser and modified LenSx Laser. However, the document does not provide the specific numerical values or ranges for these acceptance criteria. It only mentions what was evaluated against them.

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

• Test Set Sample Size: The document mentions "Evaluation of stepped cuts/incisions in human cadaver eyes for lamellar keratoplasty, penetrating keratoplasty and cataract surgery." However, the exact number of human cadaver eyes used for this evaluation, or any other test set, is not specified.
• Data Provenance: The only explicit mention of data provenance for testing is "human cadaver eyes." No country of origin is specified. The study is retrospective in the sense that cadaver eyes are used, not living patients.

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

The provided document does not specify the number of experts used to establish ground truth for the test set, nor does it detail their qualifications.

4. Adjudication Method for the Test Set:

The document does not provide any information regarding the adjudication method (e.g., 2+1, 3+1, none) used for the test set.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it discuss the effect size of human readers improving with or without AI assistance. This device is a surgical laser system, not an AI diagnostic tool that would typically involve human readers.

6. Standalone (Algorithm Only) Performance Study:

The document describes the performance testing of the device itself, which is a surgical laser system. In this context, "standalone algorithm performance" is not directly applicable in the same way it would be for an AI diagnostic algorithm. The performance tests evaluate the physical capabilities of the laser system (accuracy and reproducibility of cuts), not an algorithm's diagnostic output.

7. Type of Ground Truth Used:

The ground truth for the performance evaluations appears to be based on physical measurements and observations of the cuts and incisions created by the laser system. This would infer measurement of depth, geometry, and potentially histological examination in cadaver eyes, but the document does not explicitly state "pathology" or "outcomes data." It implies objective physical assessment.

8. Sample Size for the Training Set:

The document does not specify a training set sample size. This is consistent with the nature of the device; it's a physical surgical tool, not an AI algorithm that undergoes a distinct "training phase" on labeled data in the traditional sense. Its development and refinement would involve engineering and testing, rather than algorithmic training.

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

As there is no "training set" in the context of an AI algorithm, the document does not describe how ground truth for a training set was established. The development of the device would rely on engineering principles, iterative design, and performance testing, rather than labeled data for algorithm training.

Ask a specific question about this device