Search Results

The HP-OCT™ instrument is a non-contact ophthalmic imaging and analysis device. It is indicated for visualization of the posterior segment of the eye.

The Cylite Hyperparallel Optical Coherence Tomographer (HP-OCT) is an ophthalmic OCT system, intended to assist ophthalmic professionals in the diagnosis of ophthalmic conditions via non-contact imaging of the posterior segment. OCT imaging is accomplished in the HP-OCT instrument using a micro-lens array to separate the illumination from a super-luminescent diode (SLD) source into an array of parallel beamlets. The beamlet array is then projected simultaneously onto the eye. Each of the individual beamlets is equivalent to a single beam of an SD-OCT (Spectral Domain OCT) system. Each beamlet generates a spectral interferogram, equivalent to a single SD-OCT interferogram, which is processed to produce an individual A-scan. A set of 1008 parallel, SD-OCT type A-scans is thus acquired for each frame of the CMOS sensor, and multiple frames can be acquired to create dense volume images.

The HP-OCT instrument is supplied with an exchangeable lens which supports OCT imaging of the posterior segment.

The HP-OCT instrument is operated from the Cylite Focus softwarethat runs from a Windows 10 personal computer (PC) supplied by the user. The PC hosts the HP-OCT Capture and Focus Review software and connects to the HP-OCT instrument via a USB 3.0/3.1 cable. From the PC/software, the user employs the PC monitor, keyboard and mouse to interact with the HP-OCT instrument to perform instrument alignment, preview images, capture images, save or load image or patient data, review images, and manage patient data.

The Cylite HP-OCT is an ophthalmic OCT system intended for non-contact imaging and analysis of ocular structures, specifically for visualization of the posterior segment of the eye. Its substantial equivalence to the predicate device, the Carl Zeiss Meditec, Inc. Cirrus HD-OCT 5000 (K181534), was evaluated through both non-clinical and clinical performance testing.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state acceptance criteria in a quantitative format for either the non-clinical or clinical performance. Instead, it describes the assessment of various performance aspects and concludes with a qualitative statement of "favorable clinical performance profile that supports a determination of substantial equivalence."

However, based on the comparative effectiveness study, we can infer the acceptance criterion was likely non-inferiority or comparability in the ability to identify anatomical structures and retinal abnormalities.

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

• Sample Size (Test Set): A total of 83 eyes (43 normal eyes, 40 retinal diseased eyes) were enrolled in the clinical study.
• Data Provenance: The document does not explicitly state the country of origin for the clinical data. It mentions the study was conducted at three sites, implying prospective data collection for this specific study.

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

• Number of Experts: Three independent graders were used.
• Qualifications of Experts: The specific qualifications (e.g., years of experience, subspecialty) of these graders are not provided in the document. They are identified as "image graders."

4. Adjudication Method for the Test Set

The document states that "For each image grader attempted to identify 9 anatomic structures and 11 abnormalities which were pre-defined and scored 1 (if identifiable) or 0 (if unidentifiable) for each structure/abnormality." It also mentions "inter-grader difference for HP-OCT for each structure and abnormity." However, it does not explicitly describe an adjudication method (like 2+1 or 3+1) to resolve discrepancies or establish a single ground truth from the three graders' individual assessments for either structures or abnormalities. It appears each grader's scores were compared directly between devices.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• MRMC Study: Yes, a comparative effectiveness study involving multiple readers (three independent graders) and multiple cases (83 eyes) was performed, comparing the HP-OCT to the predicate device.
• Effect Size of Human Reader Improvement with AI: This information is not applicable as the HP-OCT is presented as an imaging device, not an AI-assisted diagnostic tool for human readers. The study compares the imaging performance of the device itself to a predicate, not the improvement of human readers using the device with AI versus without AI.

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

• Standalone Performance: The document describes the device as a "non-contact ophthalmic imaging and analysis device" indicated for "visualization." The clinical study evaluated the device's ability to generate images that aid qualitative diagnosis by human graders. The results are based on human interpretation of the images produced by the device. Therefore, a standalone algorithm-only performance without human-in-the-loop is not explicitly described or indicated as the primary assessment. The device itself is not
  stated to perform automated diagnoses.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The ground truth for the clinical study was established by the identification and scoring of pre-defined anatomical structures and abnormalities by three independent expert graders based on the images generated by both the HP-OCT and the predicate device. This is a form of expert consensus/interpretation of imaging data. There is no mention of pathology, outcomes data, or other independent gold standards.

8. The Sample Size for the Training Set

The document does not provide information on a training set sample size. The clinical study described is a performance validation study, not a study describing the development and training of an algorithm within the HP-OCT device itself. The HP-OCT is an imaging device, and while it uses software (Cylite Focus software), the provided information focuses on its image acquisition capabilities rather than an AI/ML component that would require a distinct training set for diagnostic purposes.

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

As no training set is mentioned for an AI/ML diagnostic component, this information is not applicable.

Ask a specific question about this device

KOWA SL-19 is intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma which affect the structural properties of the anterior eye segment.

The KOWA SL-19 is a non-invasive ophthalmic device that is able to illumination, magnification and observation of the human eye.

Illumination light that emitted from a white light source is applied to the eyeball, Refractive media, Eye Anatomy, Ocular Adnexa, Iris, etc. are magnified and observed with a binocular microscope. Fluorescence of the cornea, conjunctiva, etc. can be observed by irradiating background illumination light and irradiating blue illumination light with a built-in light source.

The background White LED function is added to the KOWA SL-19.

The blue filter with white LED for the predicated device is removed, and this function is replaced by blue LED for the KOWA SL-19.

Duration of illumination is lengthened from 140 min to 360 min from predicate device to the KOWA SL-19 due to replace the battery type from AAA battery to AA battery.

The provided text describes a 510(k) premarket notification for the Kowa SL-19, a handheld slit-lamp biomicroscope. This document asserts substantial equivalence to a predicate device (Kowa SL-17) rather than providing a detailed study of an AI/ML-driven device's performance against specific acceptance criteria.

Therefore, the information required to answer your questions regarding acceptance criteria, performance studies, sample sizes, expert involvement, ground truth establishment, and MRMC studies for an AI/ML device is not present in the provided text. The document focuses on the safety and efficacy of a traditional medical device through comparison with a predicate device and adherence to established standards for electrical safety, biocompatibility, software validation, and optical radiation safety.

The acceptance criteria mentioned are related to compliance with recognized standards for safety and performance of a slit lamp, not a new AI-driven diagnostic or assistive technology.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• No AI/ML Device: The Kowa SL-19 is a hardware device (a slit lamp), not an AI/ML algorithm. Its "software" refers to internal operational software, not an AI model that processes images for diagnosis or assistance.
• No "Acceptance Criteria" for AI Performance: The document does not define specific performance metrics (e.g., sensitivity, specificity, accuracy) for an AI model, nor does it present data demonstrating such performance.
• No "Study Proving Device Meets Acceptance Criteria" for AI: The "Performance Testing" section refers to compliance with safety and performance standards (e.g., IEC, ANSI, ISO), not a clinical study evaluating an AI's diagnostic performance.
• No Discussion of Test Sets, Training Sets, Ground Truth, or Experts for AI: These concepts are relevant to the development and validation of AI/ML models, which are not described here.

In summary, the provided document is a regulatory submission for a conventional medical device and does not contain the information necessary to describe an acceptance criteria and study for an AI/ML-driven device.

Ask a specific question about this device

MiiS Horus Eye Anterior Camera is a digital hand-held slit lamp system indicated for non- invasive illumination, magnification, visualization and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area.

MiiS Horus Eye Anterior Camera is a digital hand-held slit lamp system indicated for non-invasive illumination, magnification, visualize and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. It is a Li-ion battery-powered optical device. It brings more complete medical records about the static photos as well as the dynamic videos. MiiS Horus Eye Anterior Camera has an LED light source with visible white light. The device is designed with high-resolution lens and 5M pixels CMOS Sensor, faithful rendering color of the anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. The device can store pictures or videos in memory card, or via the USB, Wi-Fi and Bluetooth transfer pictures or videos to a computer. In addition to rendering images in the 3.5-inch full color TFT-LCD, through the HDMI output, you can connect the device to the big screen (TV, LCD screen) showing the pictures or videos.

MiiS Horus Eye Anterior Camera includes two models. The first model consists of control unit DSC 300 and lens unit DEA 200. The second model consists of control unit DSC 300P and lens unit DEA 200P. Either auto or manual focus can be used in first model while only manual focus is used in the second model.

The control unit DSC 300 includes a cover glass while DSC 300P does not. The contact rim in lens unit DEA 200 is different from that in DEA 200P.

This document does not include information about AI/ML features, acceptance criteria, or ground truth establishment. The device described, MiiS Horus Eye Anterior Camera, is a digital hand-held slit lamp system. It is a traditional medical device for visualization and recording of the anterior segment of the eye, not an AI/ML-powered diagnostic tool.

Therefore, I cannot provide details on acceptance criteria for AI/ML performance, study designs involving AI assistance, or related ground truth methodologies, as these are not relevant to the information provided in the input text.

The closest relevant sections in the provided text are regarding nonclinical tests and optical radiation safety assessment. These sections outline tests performed to ensure the device's safety and functionality in a traditional sense, not related to AI/ML performance metrics.

Specifically, the document states:

• Nonclinical Tests: "The following tests have been performed in support of the substantial equivalence determination: IEC 62304 for Software verification and validation testing. - IEC/EN 60601-1:2005/2006+A1:2012/2013 for electrical safety. - IEC/EN 60601-1-2:2014/2015 for electromagnetic compatibility. - Bluetooth testing for compatibility and functionality. - HDMI compliance test was conducted in compliance with HDMI 1.4b sink and source devices. - ISO 14971:2007 and EN ISO 14971:2012 for risk management. - -ISO 15004-2:2007 for light hazards. ISO10993-5:2009 and ISO10993-10:2010 standards for biocompatibility. The patient contacting parts are the holder of chin rest CR100 and the forehead stopper."
• Clinical Tests: "No clinical studies were performed."
• Optical Radiation Safety Assessment: "The MiiS Horus Eye Anterior Camera was tested according to 15004-2:2007 to determine acceptable light safety limits for both the illumination and background lights. The test results demonstrate the MiiS Horus Eye Anterior Camera is in compliance with the of Group 2 instrument requirements provided by the standard."

These tests confirm the device's compliance with safety and performance standards for a medical imaging device, but not for an AI/ML algorithm's diagnostic accuracy or performance.

Ask a specific question about this device

The Chongqing Sunkingdom Slit Lamp LS-1A, LS-1B are AC --- powered slit lamp Biomicroscopes intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma which affects the structural properties of the anterior eye segment.

Sunkingdom slit lamp LS-1A, LS-1B are an AC-powered slit lamp biomicroscope is intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma, which affects the structural properties of the anterior eye segment. An AC-powered Slit lamp Bio-microscope is an AC-powered device that is a microscope intended for use in eye examination that projects into a patient's eye through a control diaphragm a thin, intense beam of light. Components: The optical body, movement mechanism, illumination system, portable handle, power supply.

The given text is a 510(k) Pre-market Notification for the Sunkingdom Slit Lamp LS-1A, LS-1B. It details the device's technical characteristics and performance testing conducted to demonstrate substantial equivalence to a predicate device.

Acceptance Criteria and Device Performance:

The document primarily relies on demonstrating compliance with relevant industry standards and showing that the proposed device's performance characteristics are comparable to or better than the predicate device. The acceptance criteria are implicitly defined by these standards and the comparison table.

Study Information:

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

   • The document does not explicitly state a "test set" in the context of clinical data for performance evaluation. The performance data provided is primarily from bench testing and compliance with standardized tests (Biocompatibility, Electrical safety, EMC, Performance testing according to ISO 10939, Light Hazard Protection according to ISO 15004-2).
   • For biocompatibility, the tests were conducted with specific samples (e.g., "Chinrest pat and Forehead band extract," "rabbitskin," "guinea pig," "L-929 cells").
   • The data provenance is not specified beyond the tests being conducted on the "Sunkingdom Slit Lamp LS-1A, LS-1B" and under recognized FDA standards and Good Laboratory Practice (21 CFR 58). This suggests the tests were carried out by the manufacturer or a contracted lab. There's no indication of retrospective or prospective human clinical data.

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

   • This question is not applicable as the study did not involve human expert interpretation of clinical cases to establish ground truth. The "ground truth" for the performance claims were objective measurements and adherence to technical specifications and international standards.

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

   • Not applicable, as no human adjudication of clinical cases was performed.

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 comparative effectiveness study was done. This device is a traditional medical instrument (slit lamp biomicroscope), not an AI-powered diagnostic tool.

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

   • Not applicable, as this is a medical device for direct human use in eye examination, not an algorithm.

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

   • The ground truth is established by objective measurements against engineering specifications and compliance with international standards for medical device safety and performance (e.g., ISO 10993 for biocompatibility, IEC 60601 series for electrical safety/EMC, ISO 10939 for slit lamps, ISO 15004-2 for light hazard).

7. The sample size for the training set:

   • Not applicable. This device does not use an AI component requiring a training set.

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

   • Not applicable. This device does not use an AI component or a training set.

Ask a specific question about this device

The IOLMaster 700 is intended for biometric measurements and visualization of ocular structures. The measurements and visualization assist in the determination of the appropriate power and type of intraocular lens. The IOLMaster 700 measures:

• · Lens thickness
• · Corneal curvature and thickness
• · Axial length
• · Anterior chamber depth
• · Pupil diameter
• · White-to-white distance (WTW)

The IOLMaster 700 is a non-invasive optical biometry instrument for visualization and measurement of ocular structures. The IOLMaster 700 is the latest generation device in the IOLMaster series. The version of the IOLMaster 700 that is the subject of this submission is a modified version of the IOLMaster 700 cleared under K170171.

Here's a breakdown of the acceptance criteria and study details for the IOLMaster 700 device, based on the provided FDA 510(k) summary.

It's important to note that this document is for a 510(k) submission, which primarily aims to demonstrate substantial equivalence to a predicate device. Therefore, the "acceptance criteria" discussed are largely about demonstrating comparability or non-inferiority to the predicate device and established clinical methods, rather than setting absolute performance thresholds for a novel device. The study design reflects this goal.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a 510(k) for a modified device, the "acceptance criteria" are not explicitly stated as numerical targets in the same way they might be for a de novo device. Instead, the performance data aims to demonstrate that the new features (Total Keratometry and Posterior Corneal Surface measurements) are either:

• Interchangeable with conventional methods for normal eyes.
• Perform better than or comparably to existing history-free approximation methods (like Haigis-L) for post-LVC eyes, especially when historical data is unavailable.
• And that repeatability and reproducibility are comparable to the conventional keratometry.

The reported performance is summarized in the "Results" sections of the clinical studies. For the purpose of this table, I will infer the acceptance criteria from the conclusions drawn by the manufacturer regarding comparability and suitability.

2. Sample Sizes and Data Provenance

• Test Set (Clinical Data):

  • Normal Eyes (Study IOLM71): 142 normal eyes (without previous surgery or pathologies except cataract), 738 measurements. (Provenance: Raw data collected prospectively, non-significant risk clinical study at three sites, described as "normal eyes = without prior Laser Vision Correction").
  • Normal Eyes (Study IOLMaster 2017-01909): 32 non-cataract eyes (281 measurements) and 31 cataract eyes (278 measurements). (Provenance: Prospective, monocentric, non-significant risk clinical R&R study, one eye per patient).
  • Post-LVC Eyes (Study HamburgLVC): 30 eyes, 60 measurements (one pre- and one post-operative measurement for each eye). 29 myopic LASIK, 1 hyperopic LASIK. (Provenance: Prospective, single-site clinical study, one eye per patient).
  • Post-LVC Eyes (Study IOLMaster 2017-01909): 30 post-LVC eyes, 267 measurements. (Provenance: Prospective, monocentric, non-significant risk clinical R&R study, one eye per patient).
  • Country of Origin: Not explicitly stated, but the mention of "HamburgLVC" suggests Germany for at least one study site. The applicant "Carl Zeiss Meditec AG" is based in Germany.

• Training Set: Not explicitly mentioned in this 510(k) summary, as the device improvements are primarily related to algorithms for new measurement calculations (Total Keratometry, Posterior Cornea Surface) derived from existing OCT technology, rather than an AI/ML model that requires explicit "training" in the traditional sense. The software verification and validation are for the overall product, and bench testing with "test targets of known curvatures" was used for accuracy and repeatability of the new measurement calculations.

3. Number of Experts and their Qualifications for Ground Truth

• Not applicable in the context of this 510(k). This device is a measurement instrument. The ground truth for the performance of the measurements is based on:
  • Bench testing with "test targets of known curvatures."
  • Comparison to existing, established clinical measurement methods (conventional keratometry, Gullstrand model, Clinical History Method for post-LVC eyes).
  • The "experts" involved would be the clinicians conducting the clinical studies and presumably validating the established methods used for comparison. The document does not specify the number or qualifications of these clinicians beyond them being study site personnel.

4. Adjudication Method for the Test Set

• Not applicable. This study is focused on the performance of a measurement device. There is no subjective interpretation being adjudicated. The measurements are quantitative.

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

• No. This is not an imaging device where human readers interpret and then AI assists in that interpretation. It is a biometric measurement device. The studies compare the device's measurements to established measurement methods.

6. Standalone (Algorithm Only) Performance

• Yes, implicitly. The device itself performs the measurements for Total Keratometry and Posterior Corneal Surface (via its software algorithm). The performance data (Table 1, Figure 1, Figure 2, Tables 2, 3) represent the output of the device's algorithms. There isn't a human-in-the-loop component for these specific measurements; the device generates the numbers. The clinical data then validates these algorithm outputs against established clinical practices.

7. Type of Ground Truth Used

• For Accuracy/Deviation:
  • Known Reference Standards: Bench testing used "test targets of known curvatures."
  • Established Clinical Methods/Models:
    • Conventional keratometry and the Gullstrand model (for normal eyes).
    • Clinical History Method (CHM) for post-LVC eyes, which is considered the "gold standard" when historical data is available.
• For Repeatability & Reproducibility:
  • Multiple measurements on the same patients/eyes using the device itself across different scans, and sometimes different devices/operators.

8. Sample Size for the Training Set

• Not applicable / Not stated. This 510(k) describes a device that utilizes "Spectral domain interferometry (OCT principle)" and "Swept source laser" to obtain biometric measurements. The improvements are primarily algorithmic enhancements to interpret these optical measurements for new parameters (TK, PCS). It's not described as a machine learning model that undergoes a distinct "training set" phase in the typical AI/ML sense. Bench testing and clinical data validate the performance of these algorithms.

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

• Not applicable / Not stated as there is no explicitly defined "training set" for an AI/ML model. The underlying physics and algorithms are based on established optical principles (OCT, interferometry). The validation data compares the device's output to established clinical measurement techniques and physical standards.

Ask a specific question about this device

The KH Ophthalmic Slit-lamp Microscope is an AC-powered slitlamp biomicroscope intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma which affects the structural properties of the anterior eye segment.

The KH Ophthalmic Slit-lamp Microscope is an AC-powered device that is a microscope intended for use in eye examination that projects into a patient's eye through a control diaphragm a thin, intense beam of light. The KH Ophthalmic Slitlamp Microscope is composed of the following components: microscope unit, illumination unit, base unit, chinrest, and table and power unit. The slitlamp biomicroscope is used for the observation of the eye. It has an illumination unit to illuminate the eye, and a binocular stereoscopic microscope to zoom and observe patient's eyes, and also can observe the three-dimensional image.

The provided text is a 510(k) summary for an ophthalmic slit-lamp microscope (SLM-1ER, SLM-2ER). It describes the device, its intended use, a comparison to a predicate device, and non-clinical testing performed to support substantial equivalence.

Based on the content, this document does not describe an AI/ML-driven medical device, nor does it detail a study that proves a device meets acceptance criteria related to AI/ML performance metrics (like sensitivity, specificity, or AUC). The acceptance criteria described are for a traditional medical device (slit-lamp biomicroscope) and focus on safety, EMC, biocompatibility, and general performance standards.

Therefore, it is not possible to provide the requested information about acceptance criteria for an AI/ML model and a study proving device performance against those criteria, including details on sample size, data provenance, expert ground truth, adjudication, MRMC studies, standalone performance, training set details, or effect sizes for human readers.

The document focuses on demonstrating substantial equivalence to a predicate device (Keeler Slit Lamp H-Series, K131589) by showing compliance with established medical device standards for safety and performance of an ophthalmic slit-lamp.

Here's an overview of what is in the provided text, related to its acceptance:

Acceptance Criteria and Reported Device Performance (as per the document):

The acceptance criteria are implied by the compliance to various international standards. The "reported device performance" is essentially that the device met these standards.

Regarding the other requested information (which is not applicable to this document as it's not an AI/ML device study):

• Sample size for the test set and data provenance: Not applicable. The testing is for compliance with physical and electrical standards, not diagnosis or detection using a dataset.
• Number of experts used to establish ground truth & qualifications: Not applicable. Ground truth for AI/ML performance is not relevant here.
• Adjudication method: Not applicable.
• MRMC comparative effectiveness study: Not applicable. This is not an AI/ML diagnostic aid.
• Standalone (algorithm only) performance: Not applicable. This is a physical device, not an algorithm.
• Type of ground truth used: Not applicable.
• Sample size for the training set: Not applicable. There is no AI/ML model trained here.
• How the ground truth for the training set was established: Not applicable.

In summary, the provided document details the submission for a traditional ophthalmic slit-lamp biomicroscope, not an AI/ML diagnostic or assistive device. Therefore, the requested information pertaining to AI/ML acceptance criteria and performance studies cannot be extracted from this text.

Ask a specific question about this device

MiiS Horus+ Scope DEA 200 is a digital hand-held slit lamp system indicated for non-invasive illumination, magnification, visualization and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area.

MiiS Horus* Scope DEA 200 is a digital hand-held slit lamp system indicated for non-invasive illumination, magnification, visualize and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. It is a Li-ion battery-powered optical device. It brings more complete medical records about the static photos as well as the dynamic videos. MiiS Horus* Scope DEA 200 has an LED light source with visible white light. The device is designed with high-resolution lens and 5M pixels CMOS Sensor, faithful rendering color of the anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. The device can store pictures or videos in SD memory card, or via the USB transfer pictures or videos to a computer. In addition to rendering images in the 3.5-inch full color TFT-LCD, through the AV output, you can connect the device to the big screen (TV, LCD screen) showing the pictures or videos. Below includes a summary of the technical information used in the substantial equivalence comparison. It is more efficient and suitable for many different applications, such as electronic filing.

The provided document is a 510(k) Pre-market Notification from the FDA for a device named "MiiS Horus+ Scope DEA 200". This document focuses on demonstrating substantial equivalence to predicate devices and does NOT contain information about acceptance criteria, device performance, or human-in-the-loop studies as typically found in clinical validation reports for AI/CAD devices.

Therefore, the following information CANNOT be extracted from the document:

1. A table of acceptance criteria and the reported device performance: This document does not describe specific acceptance criteria (e.g., sensitivity, specificity, AUC targets) for detecting conditions, nor does it provide performance metrics against such criteria.
2. Sample size used for the test set and the data provenance: No information on a test set, its size, or origin is provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: The document does not describe any expert-established ground truth or the qualifications of such experts.
4. Adjudication method for the test set: No test set means no 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: The document explicitly states, "No clinical studies were performed." This implies no MRMC study was conducted.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The device described in the document is a digital hand-held slit lamp system, a hardware device for imaging and recording. It is not an AI algorithm, so a standalone algorithm performance study is not applicable.
7. The type of ground truth used: Not applicable as there's no mention of a test set or performance evaluation against any ground truth.
8. The sample size for the training set: The device is a hardware imaging system, not an AI model, so there is no concept of a "training set" in the context of this document.
9. How the ground truth for the training set was established: Not applicable.

What the document does describe is a technical comparison of the "MiiS Horus+ Scope DEA 200" with two predicate devices (KOWA SL-15 and MiiS Horus Scope DEC 100) to demonstrate "substantial equivalence" based on similar intended use, technological characteristics, and safety evaluations (e.g., EMC, electrical safety, and optical radiation hazard assessment according to ISO 15004-2:2007). The document concludes that "bench performance tests support the conclusion of substantial equivalence."

In summary, this document is a regulatory submission for a medical imaging device (a digital hand-held slit lamp) and not an AI/CAD algorithm. Therefore, it does not contain the information requested about acceptance criteria, device performance, or clinical validation studies typically associated with AI systems.

Ask a specific question about this device

Portable Slit Lamp Microscope Model KJ5S is intended for use in the anterior and posterior segment of the eye.

The Portable Slit Lamp Microscope is a hand held converging stereomicroscope system powered by rechargeable batteries.

This document describes the FDA 510(k) clearance for the Portable Slit Lamp Microscope Model KJ5S by Suzhou Kangjie Medical Inc.

Here's an analysis of the provided information regarding acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" in the typical sense of numerical thresholds for clinical performance metrics (e.g., sensitivity, specificity). Instead, the performance evaluation for this device is based on non-clinical tests to ensure safety and functionality, and a comparison to a predicate device to demonstrate substantial equivalence.

The comparative table on pages 6-7 serves as the primary method to show the device's technical characteristics meet acceptable standards by demonstrating similarity to a legally marketed device.

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

• No clinical test set was used. The document explicitly states: "Discussion of Clinical Tests Performed: None".
• The "test set" for this device largely consists of its physical specifications and performance against recognized electrical, safety, and optical standards (IEC, ISO). The data provenance for these non-clinical tests is internal to the manufacturer's testing and compliance processes.

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

• Not applicable. Since no clinical studies were performed, there was no need for experts to establish ground truth for a clinical test set. The validation relies on engineering and safety standards.

4. Adjudication Method for the Test Set

• Not applicable. No clinical test set or subjective interpretations requiring adjudication were involved.

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

• No. The document explicitly states: "Discussion of Clinical Tests Performed: None". Hence, no MRMC study or assessment of human reader improvement with AI assistance was conducted.

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

• No. This device is a hardware medical device (a slit lamp microscope), not an AI algorithm. Therefore, "standalone" algorithm performance is not applicable.

7. The Type of Ground Truth Used

• For the non-clinical tests, the "ground truth" is defined by the specifications and requirements outlined in the international standards (IEC, ISO) referenced (e.g., IEC 60601-1 for basic safety, ISO 10939 for slit-lamp microscope specific requirements). The device's performance characteristics (e.g., light intensity, dimensions, temperature) were measured and compared against these established engineering and safety benchmarks.
• For biocompatibility, the ground truth is established by the ISO 10993 series of standards.

8. The Sample Size for the Training Set

• Not applicable. Since this is not an AI/Machine Learning device, there is no "training set."

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

• Not applicable. No training set was used.

Ask a specific question about this device

An AC-powered slit lamp biomicroscope is intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma which affect the structural properties of the anterior eye segment.

The SL 220 can be used in performing a wide range of conventional eye care applications. It is used for ophthalmic observation of structural properties of the eye. The illumination can be adjusted from slit type illumination to a full-field type illumination by beam forming elements. The instrument is primarily used by ophthalmologists, opticians and optometrists.

This document is a 510(k) summary for the Carl Zeiss Meditec SL 220, an AC-powered slit lamp biomicroscope.

Here's an analysis based on your request:

Acceptance Criteria and Reported Device Performance

The provided document does not contain a table of acceptance criteria nor reported device performance in the context of diagnostic accuracy (e.g., sensitivity, specificity, AUC). This is a submission for a Slit Lamp Biomicroscope, which is a diagnostic tool that physicians use, not an AI or algorithm-driven diagnostic device that would typically have such performance metrics.

Instead, the "acceptance criteria" for a device like this are compliance with recognized performance standards related to safety and effectiveness, and then a comparison to predicate devices for substantial equivalence.

Here's what is presented:

Study Information (as per the document)

The document describes non-clinical tests to demonstrate compliance with standards and a comparison to predicate devices. It does not describe a clinical study of diagnostic accuracy or comparative effectiveness in the way an AI/CADe/CADx device would.

1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable for this type of device submission. There is no "test set" in the context of diagnostic accuracy.
2. 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. Ground truth for diagnostic accuracy is not discussed.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
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: Not applicable. This is not an AI-assisted device.
5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. This is not an algorithm-only device. It's a medical instrument used directly by a human.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable in the context of diagnostic accuracy. The ground truth for this device's performance is adherence to engineering and safety standards.
7. The sample size for the training set: Not applicable. This is not a machine learning device.
8. How the ground truth for the training set was established: Not applicable.

Summary of the Device and Submission:

The SL 220 is a conventional slit lamp biomicroscope intended for eye examination of the anterior eye segment to aid in the diagnosis of diseases or trauma. The submission focuses on demonstrating substantial equivalence to existing predicate devices (Carl Zeiss Meditec (CZM) Slit Lamp SL 130 and C.S.O. SL990) and compliance with relevant international safety and performance standards (IEC 60601-1, IEC 60601-1-2, ISO 15004-2). The main technological differences highlighted are top-illumination versus bottom-illumination and Halogen versus LED illumination. The document concludes that the SL 220 is safe and effective and substantially equivalent to the predicate devices.

Ask a specific question about this device

The SLIT LAMP SL-2000 is intended for use in eye examination of the anterior eye segment, from the corneal epithelium to the posterior capsule. This device is used to aid in the diagnosis of diseases or trauma which affect the structural properties of the anterior eye segment.

The SLIT LAMP SL-2000 is used to magnify the eyeball, eyelid, and eyelash of patients for observation, using slit illumination light.

The SL-2000 comprises the main unit that incorporates the microscope unit, illumination unit, base plate unit, and power supply box.

This document is a 510(k) premarket notification for the Nidek Co., Ltd. Slit Lamp SL-2000. It focuses on demonstrating substantial equivalence to predicate devices rather than proving performance against specific clinical acceptance criteria. Therefore, much of the requested information regarding specific performance metrics, clinical study design, and ground truth establishment is not present in this document because it is not typically required for a 510(k) submission for a device like a slit lamp.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

This document does not provide a table of quantitative acceptance criteria for diagnostic performance (e.g., sensitivity, specificity) for the slit lamp, as it is a diagnostic tool observed by a human, not an automated diagnostic system. Instead, it focuses on demonstrating that the device meets safety and performance standards equivalent to predicate devices. The "performance" mentioned primarily refers to compliance with international standards for ophthalmic instruments and electrical safety.

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

The document does not detail specific "test set" sample sizes in the context of clinical performance data for diagnosis of diseases. The testing described is primarily limited to bench testing and compliance with engineering and safety standards. There is no mention of clinical data or patient samples being used in the validation tests outlined.

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

Not applicable, as a clinical test set with ground truth established by experts is not described in this document for a device like a slit lamp in a 510(k) submission.

4. Adjudication Method for the Test Set

Not applicable, as a clinical test set with expert adjudication is not described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of AI Improvement

Not applicable. The Slit Lamp SL-2000 is a manual observation device, not an AI-powered diagnostic tool. Therefore, no MRMC study or AI improvement metrics are relevant or discussed.

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

Not applicable, as this is a manually operated medical device without an AI algorithm.

7. The Type of Ground Truth Used

Not applicable in the context of clinical diagnostic accuracy. The "ground truth" for the tests performed would be the specifications and requirements outlined in the referenced ISO, IEC, and AAMI/ANSI standards (e.g., a specific light intensity, magnification, or electrical characteristic).

8. The Sample Size for the Training Set

Not applicable, as this is not an AI/machine learning device that requires a training set.

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

Not applicable, as this is not an AI/machine learning device.

Ask a specific question about this device