Search Results

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

KOWA nonmyd 8 is indicated for true color, infrared and fundus autofluorescent (FAF) imaging of a human retina without the use of a mydriatic agent.

The KOWA nonmyd 8 is an instrument that enables retinal examination and retinal image capturing using infrared rays without requiring the patients to take any mydriatics. The KOWA nonmyd 8 is used with KOWA VK-2s software (510(k) number is K190056) which is designated filing software installed in a computer and enables to save, register or print the captured images. The KOWA nonmyd 8 has Color mode and FAF mode for photographing. Those are the functions to capture a normal color image and the Fundus Autofluorescence (FAF) image.

The KOWA nonmyd 8 is an ophthalmic camera used for true color, infrared, and fundus autofluorescent (FAF) imaging of the human retina without pupil dilation.

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

1. Table of Acceptance Criteria and Reported Device Performance:

   Acceptance Criterion (Implicit)	Reported Device Performance
   Electrical Safety and Electromagnetic Compatibility (EMC): Compliance with relevant standards.	Complies with IEC60601-1:2005 and IEC60601-1-2:2014.
   Biocompatibility: No new biocompatibility concerns for patient contact parts (forehead rest, chin rest).	Forehead rest is identical to KOWA nonmyd 7 (K053026); chin rest is identical to KOWA DR-1α (K190573). Nature and duration of body contact are identical to reference devices. Determined no new biocompatibility concern.
   Software Verification and Validation: Compliance with FDA guidance for software in medical devices.	Software has been validated according to FDA guidance "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
   Optical Radiation Safety: Classification regarding light hazard and compliance with optical safety standards.	Classified in Group 1 of continuous wave instrument according to ANSI Z80.36-2016. Complies with ISO 10940:2009. Risk of radiation is low level, even with higher output power for photographing compared to the predicate device.
   FAF Image Quality: FAF image quality similar to or better than a legally marketed reference device (Canon CR-2 Plus AF).	75% of images taken by KOWA nonmyd 8 were superior or equivalent to the Canon CR-2 Plus AF (K123208). The remaining 25% were inferior but diagnosable. The clinical testing demonstrates that FAF image quality of the proposed device is similar to that of the Canon CR-2 Plus AF (K123208) and no new concern was raised.

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

   • Sample Size: 8 subjects.
   • Data Provenance: Not explicitly stated, but the study was conducted to compare the KOWA nonmyd 8 with the Canon CR-2 Plus AF, which implies prospective data collection for this purpose. The country of origin is not mentioned.

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

   • Number of Experts: One doctor (referred to as "a doctor").
   • Qualifications: "a doctor" is mentioned, indicating a medical professional capable of evaluating diagnostic image quality. Specific qualifications (e.g., years of experience, subspecialty) are not provided.

4. Adjudication method for the test set:

   • The method described is that "a doctor determined that the FAF image is not good quality for diagnosis" to prompt re-takes, and then the FAF images from the KOWA nonmyd 8 were "evaluated by comparing image quality with the FAF image from the Canon CR-2 Plus AF (K123208)." This suggests a single reader evaluation rather than a multi-reader adjudication method (like 2+1 or 3+1).

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study was done in the context of human readers improving with or without AI assistance. The study described is a comparison of image quality between two devices (KOWA nonmyd 8 and an existing Canon device). There is no mention of AI.

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

   • This question is not applicable as the KOWA nonmyd 8 is an ophthalmic camera, not an AI algorithm. The performance evaluation focuses on the image quality produced by the camera.

7. The type of ground truth used:

   • Expert Consensus: The "ground truth" for FAF image quality comparison was established by a single doctor's determination of diagnostic quality and subsequent comparison of images between the two devices. This leans towards expert opinion/evaluation. There is no mention of pathology or outcomes data being used as ground truth for image quality.

8. The sample size for the training set:

   • Not applicable. The document describes a comparison study of a new photographic device (KOWA nonmyd 8) against an existing one, not the training of an algorithm via a training set.

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

   • Not applicable, as there was no training set for an algorithm.

Ask a specific question about this device

The KOWA DR-1a is an ocular surface interferometer, which is an ophthalmic imaging device that is intended for use by physician in adult patients to observe and record a video image of specular (interferometric) observations of the tear film, which can be visually monitored and photographically documented.

The KOWA DR-1a is ocular surface interferometer, which is an ophthalmic imaging device that is intended for use by a physician in adult patients to observe and record a video image of specular (interferometric) observations of the tear film, which can be visually monitored and photographically documented. This instrument is intended to observe and record a video of the interference image with illuminating white light on the tear film layer. Users can replay the recorded image on the instrument's monitor to observe the condition of the tear film layer. In addition, using the image currently being replayed, users can measure the duration time by specifying 2 different point of time. This instrument has a function that allows users to output a video or a still image clipped from the video to an external personal computer.

Here's an analysis of the acceptance criteria and study proving the device meets them, based on the provided text, categorized by your requests.

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device for regulatory clearance. It is not a detailed clinical study report designed to prove clinical accuracy or effectiveness of an AI algorithm in the specific ways you requested (e.g., MRMC study, standalone performance, expert consensus as ground truth for AI model). The KOWA DR-1a is an ophthalmic camera, and the performance data presented primarily focuses on its physical and optical characteristics compared to the predicate, and safety/electrical/biocompatibility testing. There is no mention of an AI component in this device or its performance evaluation. Therefore, many of your questions related to AI performance, such as sensitivity, specificity, MRMC studies, or training/test set ground truth for AI, cannot be answered from this document.

Acceptance Criteria and Device Performance (Based on Device Characteristics and Comparative Testing, Not AI Performance)

1. Table of acceptance criteria and the reported device performance

Since this is a substantial equivalence submission for an ophthalmic camera and not an AI algorithm, the "acceptance criteria" are generally that the new device is as safe and effective as the predicate, with no new safety or effectiveness concerns. The performance data presented focuses on physical and optical characteristics.

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

• Sample Size for Comparative Testing: Not explicitly stated with patient numbers. The performance comparison refers to "Test was performed to evaluate performance of the KOWA DR-1a compared to the LipiView regarding Illumination area, Image resolution and Interference image." It doesn't specify if this involved human subjects or just device measurements.
• Sample Size for Repeatability: "The repeatability was investigated by comparing the hue values measured with three units of DR-1α and by three examiners. Each measurement was repeated 5 times." This refers to device measurements, not a patient test set.
• Data Provenance: The document is a 510(k) submission from Kowa Company, Ltd. in Japan. The testing described would typically be conducted by the manufacturer in a controlled environment. The document does not specify country of origin for any "test set" and given it's a device performance study for substantial equivalence, it's unlikely to involve large-scale retrospective or prospective patient data in the way an AI algorithm study would.

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

• This device is an ophthalmic camera. The performance tests described relate to its physical and optical characteristics (e.g., image resolution, illumination, repeatability of hue values) and safety. There is no mention of "ground truth" in the context of clinical interpretation by experts because the device itself does not provide a diagnosis or interpretation that would require clinical ground truth for validation in this submission.
• For the repeatability test, "three examiners" were used. Their qualifications are not specified, but they would likely be trained operators or engineers.

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

• Adjudication methods like 2+1 or 3+1 are typically used in clinical studies where multiple human readers interpret medical images and their consensus or a tie-breaker establishes a "ground truth" for disease presence/absence or findings.
• Not applicable for the device performance tests described in this 510(k) summary, as it does not involve clinical interpretation or a "test set" requiring adjudication of clinical findings.

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

• An MRMC study is designed to evaluate the impact of a new technology (like AI) on physician performance.
• No MRMC study was performed or needed for this 510(k) submission, as the KOWA DR-1a is an ophthalmic camera and the document does not indicate it incorporates an AI component influencing clinical decision-making or diagnosis. The focus is on the device's ability to capture images.

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

• This question pertains to the performance of an AI algorithm independent of human interaction (e.g., its sensitivity, specificity, AUC for a diagnostic task).
• Not applicable. The KOWA DR-1a is an ophthalmic camera. The document does not describe any standalone AI algorithm for interpretation or diagnosis.

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

• As explained above, the "ground truth" concept (e.g., for disease diagnosis) is not relevant to the performance tests reported here.
• The reported performance tests rely on technical measurements and compliance with established standards:
  • Illumination area and image resolution are measured specifications.
  • Repeatability is assessed against an "acceptance range" for hue values (an objective measurement).
  • Safety checks (optical radiation, EMC, electrical, biocompatibility) are assessed against specific industry and regulatory standards.

8. The sample size for the training set

• This question applies to AI/machine learning models.
• Not applicable. This document is for the clearance of an ophthalmic camera and does not describe the development or validation of an AI algorithm, thus there is no "training set."

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

• This question applies to AI/machine learning models.
• Not applicable. As there's no mention of an AI model or training set, this information is not provided.

Ask a specific question about this device