The Demi Pro is an LED visible light curing unit intended for polymerization of light-cured materials by dental professionals. It is also intended to provide illumination to aid in visualization during oral procedures.

The Demi Pro is a pen-style cordless curing light used for the polymerization of light cured dental material and is powered by a rechargeable lithium-ion battery pack. An intraoral transillumination tip is available as an additional accessory. It is also intended to provide illumination to aid in visualization during oral procedures.
The LED Light Curing System operates by emitting high-intensity blue light from a powerful LED to activate the photo initiators contained in the resin, thereby initiating polymerization (curing).
Wavelength range:

• Usable wavelength range: 380 nm – 515 nm
• Peak wavelengths: 400 nm, 460 nm
  Light intensity levels:
• PLS STD: 1100 -1330 mW/cm²
• PLS HIGH: 2200 – 2500 mW/cm²
• ORTHO: 2500 mW/cm²
• DIAGNOSIS: 20 – 24 mW
  Duty cycle:
• PLS STD: 20 sec ON / 60 sec OFF
• PLS HIGH: 5 sec ON / 60 sec OFF
• ORTHO: 3 sec x 3 times ON / 60 sec OFF
• DIAGNOSIS: 60 sec ON / 60 sec OFF
  Waterproof rating: IPX4 (Applies to Handpiece)

N/A

Ask a specific question about this device

The Bluemoon is intended to polymerize resinous dental materials, restorative composite materials, and orthodontic brackets, bonding and sealing materials that are photopolymerized in the 385~515nm waveband of visible light.

The Bluemoon Dental Curing Light is an instrument for photopolymerizing dental materials and starting agents by irradiating them with visible light between 385-515nm wavelength. It offers four modes (HYPER, TURBO, LOW, and SOFT START) depending on the output intensity and irradiation time.

The FDA 510(k) clearance letter for the Bluemoon Dental Curing Light provides information on several aspects of device testing, but it does not detail acceptance criteria for all performance metrics, nor does it present the study in a format that directly addresses the specific questions about AI/human-in-the-loop and ground truth establishment for AI models. This device is a dental curing light, a hardware device, not an AI/ML software. Therefore, the concepts of "AI assistance," "human readers," "test set," "training set," "ground truth" as typically defined for AI/ML performance studies are not directly applicable here.

However, I can extract and interpret the provided information to answer the relevant questions as best as possible for a hardware medical device.

1. A table of acceptance criteria and the reported device performance

The document lists "Performance Data" which includes various properties and their corresponding values. These values can be interpreted as the acceptance criteria for those specific properties, and the implicit reported performance is that the device meets these criteria, as stated in the conclusion.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document describes "performance bench testing" but does not explicitly state the sample size (e.g., number of devices tested, number of dental material samples cured) for each test. Given it's a hardware device, the "test set" would refer to the units of the device and the materials it acts upon, rather than a dataset of clinical cases. The provenance of the data is not specified; however, the company is based in the Republic of Korea. The testing would be prospective (i.e., new tests conducted on the manufactured device) rather than retrospective clinical data.

3. 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)

This question is not applicable to a hardware dental curing light. "Ground truth" for this device is established by objective physical measurements (e.g., wavelength, power output, temperature, polymerization depth and strength measured by calibrated instruments) rather than expert interpretation of images or clinical findings. Therefore, no experts in the sense of trained clinicians interpreting data were used for establishing ground truth for the performance tests.

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

This question is not applicable to a hardware dental curing light. Adjudication methods like 2+1 or 3+1 are typically used for establishing ground truth in clinical or image-based studies where expert consensus is required for ambiguous cases. The performance tests for this device involve objective measurements.

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

This question is not applicable. The Bluemoon is a dental curing light, not an AI-powered diagnostic or assistive tool. It does not involve "human readers" or "AI assistance."

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

This question is not applicable. The Bluemoon is a hardware device; there is no standalone algorithm to evaluate.

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

For the performance data listed (Irradiation time, Peak wavelength, Polymerization strength, Depth of cure, Light Probe temperature, Energy-saving mode, Auto power off), the "ground truth" is established through objective physical measurements using calibrated instruments and standardized test methods. For biocompatibility, the ground truth is established by the results of specific biocompatibility tests (Cytotoxicity, Skin Sensitization, Intracutaneous reactivity) conducted according to ISO 10993 standards.

8. The sample size for the training set

This question is not applicable. The Bluemoon is a hardware device and does not involve a "training set" in the context of machine learning or AI models. Its design and manufacturing process are validated through engineering principles and bench testing.

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

This question is not applicable as there is no training set for this hardware device.

Ask a specific question about this device

For dental clinics treatment to irradiate polymer-based restorative materials to cure them. The instrument must only be used in hospital environments, clinics or dental offices, by qualified practitioners.

The LED Curing Lights (Model: DB686 HALO) is an oral device for repairing teeth. It uses the principle of light curing to make the dental repair resin material solidify rapidly under the action of light wave in the specific wavelength range (385~515nm), so as to fill the tooth cavity or bond the bracket. It is a cordless pen-style device, and consists of handpiece, LED cure tip, charging base, power adapter, eyes protector, eye protector unit and disposable protective sleeve. The LED Curing Lights protects the handpiece and LED cure tip from gross contamination and prevent cross infection between patients by applying the disposable protective sleeve. The disposable protective sleeve (patient contact part) is made of PP material.

The provided FDA 510(k) clearance letter and summary for the LED Curing Light (DB686 HALO) describes a device that uses light to cure dental materials. It is crucial to understand that this submission primarily focuses on demonstrating substantial equivalence to predicate devices based on non-clinical performance and safety data, rather than conducting a comparative effectiveness study with human readers or presenting clinical trial data.

Therefore, many of the requested points, particularly those related to clinical studies, human reader performance, expert consensus, and ground truth establishment from patient data, are not applicable to this type of 510(k) submission for a non-diagnostic, non-AI device. The device is a direct energy device (light source) that acts on materials, not a diagnostic AI device that interprets images.

Here's an analysis based on the provided document:

Acceptance Criteria and Device Performance (Based on Non-Clinical Testing)

The "acceptance criteria" here are implicitly the standards and specifications that the device must meet to demonstrate substantial equivalence to its predicate devices. The "reported device performance" are the results of the non-clinical tests proving compliance with these standards.

1. Table of Acceptance Criteria and Reported Device Performance

Study Details (Focus on Non-Clinical Demonstrations)

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

• For a device like an LED curing light, the "test set" and "data provenance" refer to the physical devices and materials tested in the non-clinical studies.
• The document does not specify the exact sample size (number of devices or material samples) used for each non-clinical test. This information would typically be detailed in the full test reports submitted to the FDA, but is summarized in the 510(k) summary.
• Data Provenance: The tests are described as "Non-clinical data" and "All nonclinical testing performed on new devices." This implies that the tests were conducted on the manufacturer's own (proposed) devices and materials as part of their design verification and validation activities. The country of origin for the data generation (testing laboratories) is not explicitly stated, but the applicant is based in China. The testing would be considered prospective in the sense that it was conducted specifically for this 510(k) submission.

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

• Not Applicable. This device is an active medical device (light source) for material polymerization and caries detection, not a diagnostic imaging AI algorithm. Therefore, there is no "ground truth" based on expert image interpretation or patient outcomes in the context of diagnostic accuracy, nor were human experts involved in establishing a "ground truth" for the performance testing of the device's physical parameters (e.g., light intensity, wavelength, electrical safety, biocompatibility, curing efficacy as measured by ISO standards). The "ground truth" for these tests is defined by the technical specifications and standards themselves.

4. Adjudication Method for the Test Set:

• Not Applicable. As there are no human readers or expert interpretations involved in the stated non-clinical performance and safety testing, there is no adjudication method required.

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

• No. An MRMC study is designed to evaluate how AI assistance impacts human reader performance (e.g., radiologists interpreting images). This device is a light curing unit, not a diagnostic AI system. Its clearance is based on demonstrating substantial equivalence in its ability to cure dental materials and meet safety standards, not on improving human diagnostic accuracy.

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

• Not Applicable. This is not an algorithm or software-only device. Its performance is measured as a standalone physical device (its light output, safety, biocompatibility, and ability to cure materials as per ISO standards).

7. The Type of Ground Truth Used:

• The "ground truth" for this device's acceptance is based on engineering and performance standards (e.g., ISO 10650, ISO 4049 for curing performance; IEC 60601 series for electrical safety; IEC 62471 for photobiological safety; ISO 10993 series for biocompatibility). The device's measured parameters must fall within acceptable ranges defined by these standards, and its performance must be comparable to the predicate devices.
• For the Caries Detection Mode (EAQ product code), while it's a diagnostic aid, the document doesn't detail specific "ground truth" for its diagnostic performance, rather it implies functional equivalence based on violet light emission for fluorescent reaction.

8. The Sample Size for the Training Set:

• Not Applicable. This is not an AI/machine learning device that requires a "training set" of data.

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

• Not Applicable. As there is no training set for an AI model, this question is irrelevant to this device.

In summary, the 510(k) for the LED Curing Light (DB686 HALO) is a traditional submission focused on demonstrating technical conformity to established safety and performance standards and substantial equivalence to existing predicate devices through non-clinical testing. It does not involve AI, diagnostic image interpretation, multi-reader studies, or clinical trials for comparative effectiveness.

Ask a specific question about this device

LED Curing Light is intended for use by trained dental professionals only for the purpose of light curing dental resins and composites.

LED Curing Light is classified as an Ultraviolet Activator for Polymerization (21 CFR 872.6070). It is used for polymerization of dental light cured materials by dental professionals. The device is based on blue LED (light emitting diode) technology. It has four curing modes. Using different modes gives dental professionals the flexibility to polymerize virtually dental resins and composites.

N/A

Ask a specific question about this device

The LOOP™ is a source of illumination for curing photo-activated dental restorative materials and adhesives.

LOOP™ is a high-performance LED (Light Emitting Diode) light source for polymerization of dental materials used by trained dental professionals. It is suitable for use with a broad range of light-cured dental materials including materials for restoratives such as light-cured and dual-cure cements, composites, bonding agents/adhesives, bases, liners, fissure sealants, temporaries, as well as luting materials for brackets and indirect restorations such as ceramic inlays. LOOP™ consists of a wireless handpiece and a charging base with an integrated calibration station. The device is a medical electrical device in accordance with IEC 60601-1-2. LOOP™ features a patented coaxial feedback sensing system that measures the actual irradiance, which is the light power striking the targeted tooth. The feedback data allows LOOPTM to make corrective adjustments to the LED power output hundreds of times per second. This continual corrected "closed loop" operation ensures that the targeted surface of the restorative dental material receives the intended irradiance independent of operator-induced distance variations.

This document is a 510(k) premarket notification for a dental device, the LOOP™ LED Curing Light System. It does not contain the detailed information necessary to fully answer your request regarding acceptance criteria and study proving the device meets those criteria, specifically concerning AI/ML capabilities, human expert adjudication, or large-scale clinical performance studies.

The provided text primarily focuses on demonstrating substantial equivalence to a predicate device based on technical specifications, intended use, and general safety and performance testing. It does not describe an AI/ML-driven device or studies that would typically involve acceptance criteria related to algorithmic performance metrics (e.g., sensitivity, specificity, AUC), human reader studies, or expert ground truth establishment for such a device.

Here's why the document doesn't provide the requested information:

• Device Type: The LOOP™ LED Curing Light System is a physical dental curing light. It is described as having a "patented coaxial feedback sensing system that measures the actual irradiance" and makes "corrective adjustments to the LED power output." This describes a control system, not an AI/ML algorithm that makes diagnoses, predictions, or image interpretations.
• Performance Data: The "Performance Data" section lists various engineering, electrical safety, biocompatibility, and software verification/validation tests. These are standard tests for medical devices, particularly electronic hardware. It explicitly states, "No animal or clinical studies were conducted." This confirms that no clinical performance study, particularly one involving human readers or comparative effectiveness, was performed or submitted.
• Lack of AI/ML Specifics: There is no mention of algorithms, machine learning models, training data, test data, ground truth establishment by experts, or any of the typical components of an AI/ML device submission. The "Software Verification and Validation Testing" section refers to software as a "moderate" level of concern due to potential minor injury from failure, which is standard for embedded software in medical devices, not for AI/ML functionality.

Therefore, I cannot populate the requested table or answer the specific questions about AI/ML study design, expert involvement, and performance metrics because this information is not present in the provided document.

The document describes a different type of device and a different type of substantial equivalence demonstration. If you are looking for information on AI/ML device approvals, this specific document does not provide such details.

Ask a specific question about this device

The CEFLA Dental Micromotors are brushless electric micromotors control unit inside CEFLA Dental Units. They are intended to be connected with an ISO-type handpiece attachment: straight or contra-angle of equal, gear reducing, or gear increasing speed.

They are intended for professional use in dental surgery such as: preventive applications, endodontic treatment, prosthetic applications and implantology practices.

The CEFLA Dental Micromotors are brushless electric micromotors controlled by a control unit inside CEFLA Dental Units.
The dental electric micro-motor is a dental tool, which allows performing the rotation, at a variable speed, of a drill (or another tool) supported by a handpiece connected to the micromotor. It is used for dental procedures concerning restorative and prosthetic dentistry, implant surgery, endodontic (including the reciprocating function). This device is included in the Instrument Boards of the Dental Units.
The CEFLA Dental Micromotors family presents two versions:

1. long version (long) available in two variants: with white Led light, or with white and UV LED light; the long version is especially suitable for implant & endodontic procedures:
2. short version (short) available in three variants: without any incorporated LED, with optional white Led light, or with white and UV LEDs; the short version is especially suitable for prosthetic & restorative procedures.
   Both versions are manufactured with the same essential technical specifications and mechanical performances; the only difference is related to the different lengths and the maximum available torques.
   Furthermore, both versions of micro-motors are intended to be connect with the following two parts:
3. CEFLA Dental Unit, legally marketed in USA, through a cord for connection between micromotor and the dental unit system including electronic board;
4. handpieces which transmit movement to their tips or other instrument, legally marketed in USA.
   The near-UV LED light is limited to visualization of dental composites with limited exposure time (i.e., observation of the margin of the composite and tooth structure). The near-UV LED light is not intended for use during rotation of the handpiece.

The provided text is a 510(k) Summary for a dental device (micromotors). It describes the device, its intended use, and compares it to predicate and reference devices to demonstrate substantial equivalence.

However, the document does not contain any information about acceptance criteria or a study that proves the device meets those criteria in the context of AI/ML performance evaluation. It focuses on non-clinical performance testing (electrical safety, EMC, photobiological safety) and states that clinical performance testing was not conducted.

Therefore, I cannot provide the requested information regarding AI/ML performance acceptance criteria, study details, sample sizes, expert ground truth establishment, adjudication methods, MRMC studies, standalone performance, or training set details because this information is not present in the provided text.

The closest relevant sections in the document discuss:

• Non-clinical Performance Testing (Page 18): This section lists various safety and compatibility tests carried out (Electrical safety, Electromagnetic compatibility, Photobiological safety). It states that other non-clinical performance tests were not repeated as the tests performed for the predicate device (K213022) are considered valid for the proposed variants.
• Clinical Testing (Page 18): Explicitly states, "Clinical performance testing was not conducted."
• Conclusion (Page 18): Asserts substantial equivalence based on similarities in intended use, principle of operation, functional design, and established medical use, with differences deemed minor and not negatively affecting substantial equivalence.

In summary, the provided document does not describe the kind of AI/ML performance study, acceptance criteria, or related details that your request asks for. This device is a dental micromotor, not an AI/ML-driven diagnostic or therapeutic device.

Ask a specific question about this device

The MaxCure9 is intended to polymerize resinous dental materials, restorative composite materials, and orthodontic brackets, bonding and sealing materials that are photo-polymerized in the 385~515nm waveband of visible light.

This Curing Light is a device which generates high intensity light for polymerization of light curing materials used for dental curing purpose. This curing light is intended for use by trained dental professionals for the purpose of light curing dental resins and composites and used to restore teeth.

The provided text is a 510(k) summary for the MaxCure 9 Curing Light. This document focuses on demonstrating substantial equivalence to a predicate device, not on proving that the device meets specific performance acceptance criteria for an AI/Software as a Medical Device (SaMD) product.

Therefore, the information required to answer your questions about acceptance criteria for AI performance, sample sizes for test and training sets, expert qualifications, ground truth establishment, MRMC studies, or standalone algorithm performance, is not present in this document.

The document primarily addresses:

• Device Description: The MaxCure 9 is a curing light used to polymerize dental materials.
• Comparison to Predicate: It compares the MaxCure 9 to the D-Lux+ predicate device, highlighting similarities and differences in features, specifications, and operation.
• Performance Data (Non-clinical): It lists the non-clinical tests performed, including biocompatibility, software validation, and electrical safety/EMC standards (e.g., IEC 60601-1, IEC 60601-1-2).
• Conclusion: It states that based on the similarities and test results, the device is substantially equivalent to the predicate.

In summary, this document is for a traditional medical device (a curing light), not an AI/SaMD. As such, the information you've requested regarding AI acceptance criteria and study details is not applicable to this specific submission.

Ask a specific question about this device

For light curing polymerization of small areas of dental materials capable of curing in the 385 – 425 nm wavelength range.

Fibercure is a handheld dental curing light intended for light curing polymerization of small areas of dental materials capable of curing in the 385 – 425 nm wavelength range. Fibercure functions by delivering light energy to photocurable dental materials, which utilize the light energy to induce a photopolymerization reaction.

Fibercure consists of a pen-shaped handpiece, that is powered with a detachable, rechargeable battery. The handpiece features a user interface containing two push buttons and three status LEDs. The hand-piece is equipped with a solid-state laser diode to generate light energy at a wavelength of 405 ± 5mm and a power of 40 mW. The laser diode is coupled to single-use cure tips containing an optical fiber of 200 µm diameter. The cure tip emits light with an irradiance of 1800 - 2200 mW/cm2 and allows the light to be precisely targeted on the area to be photocured. Fibercure has 2 operation modes to provide either 10 or 20 second irradiation. Fibercure is delivered with a charging stand that is connected to the mains power using a USB power supply. It provides two charging stations and a photometer to confirm the intensity of the emitted light.

Fibercure's handpiece is manufactured from anodized aluminum and houses the electronic assembly. The cure tip consists of a silica-ETFE optical fiber, a stainless-steel fiber guide, a plastic housing and a ceramic ferrule. The detachable battery, charging base and power supply are manufactured from injection-molded plastic.

This is a 510(k) summary for the device Fibercure, an ultraviolet activator for polymerization used in dentistry. The document focuses on establishing substantial equivalence to a predicate device, rather than proving a device meets specific acceptance criteria through a study with statistical measures.

The information provided is primarily a comparison between the subject device (Fibercure) and predicate devices, detailing various technical specifications and indicating that non-clinical tests were performed. However, it does not include the typical acceptance criteria format (e.g., sensitivity, specificity, AUC with thresholds) or a detailed study description to demonstrate that the device "meets" those criteria in the way one would expect for a diagnostic or AI-driven device.

Here's an attempt to answer your questions based on the provided text, while acknowledging the limitations of this type of regulatory submission in addressing your specific points:

Since the document provided is a 510(k) summary for a dental curing light, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study with acceptance criteria in the manner of a diagnostic or AI-driven device. Therefore, many of your questions, particularly those related to sample size, expert ground truth, MRMC studies, and training sets, are not applicable or cannot be answered from this type of document.

However, I can extract the "performance parameters" and the general conclusion that these parameters meet requirements as a proxy for "acceptance criteria."

1. A table of acceptance criteria and the reported device performance

The document doesn't explicitly state "acceptance criteria" with specific numerical thresholds for aspects like irradiance or depth of cure as pass/fail conditions. Instead, it presents the device's performance parameters and compares them to predicate devices and general standards. The "acceptance criteria" here are implied to be "meeting the requirements of recognized standards and guidance" and being "comparable" to predicate devices.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not provided in the 510(k) summary. The document describes non-clinical performance testing but does not detail the methodology, sample sizes, or provenance of the data in the way you would expect for a clinical study or AI algorithm validation. The testing appears to be laboratory-based physical measurements rather than human-data-driven.

3. 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)

This information is not applicable/provided. The device is a dental curing light, not an AI or diagnostic device that requires expert ground truth for evaluating performance on a test set of cases. The "ground truth" for its performance relates to physical measurements and adherence to technical standards.

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

This information is not applicable/provided. Adjudication methods are relevant for consensus among experts, typically in diagnostic or AI performance studies on clinical data. For this device, performance is evaluated against technical standards and physical measurements.

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

This information is not applicable/provided. This type of study is specifically for AI-assisted diagnostic devices involving human readers. The Fibercure device is a dental curing light, a tool used by dental professionals, not an AI-driven diagnostic system.

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

This information is not applicable/provided. This question is relevant for AI algorithms. The Fibercure device is a physical instrument for light curing, not an algorithm.

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

The "ground truth" for this device's performance would be derived from physical measurements and adherence to recognized industry and regulatory standards. For example, irradiance is measured with a photometer, wavelength with a spectrometer, and depth of cure according to ISO 4049. It is not based on expert consensus, pathology, or outcomes data in the context of clinical disease.

8. The sample size for the training set

This information is not applicable/provided. The Fibercure device is a physical product (a dental curing light), not a software or AI algorithm that requires a "training set."

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

This information is not applicable/provided. As above, there is no "training set" for this device.

Ask a specific question about this device

This "BASE290 LED Curing Light" is a dental curing unit utilizing visible light programmed for the polymerization of light curing materials in the wavelength range of 380-500 nm by dental professionals.

Not Found

I am sorry, but the provided text is a 510(k) clearance letter from the FDA for a dental curing light. It does not contain information about the acceptance criteria, study details, or performance metrics of a device, nor does it discuss ground truth, human experts, or AI.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based on the provided input.

Ask a specific question about this device

CL-DP40 (Dr's Light PRIME)/CL-DP40 (Dr's Light CHOICE)is a hand held LED polymerization light intended to cure dental composites using visible light.

This unit is a battery type wireless LED curing light. User can adjust light intensity and time by selecting six program modes. Both of Dr's Light PRIME and Dr's Light Choice are characterized by high power intensity, slim head height, large irradiation area (12mm), adjustable intensity power, highly readable color touch screen, 360° twistable head and big capacity of the battery.

The provided text describes a 510(k) premarket notification for a dental curing light, CL-DP40 (Dr's Light PRIME) / CL-DP40 (Dr's Light CHOICE). This submission aims to demonstrate substantial equivalence to legally marketed predicate devices.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the technical specifications of the predicate device, particularly the primary predicate, "Dr's Light 2" (K173157). The subject device is deemed substantially equivalent because its performance metrics are comparable or superior to the predicate.

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

The document does not specify a "test set" in the context of a clinical study with patients or samples. Instead, non-clinical tests were performed on the device itself.

• Sample Size: Not explicitly stated for each test (e.g., how many devices were tested for depth of cure, electrical safety).
• Data Provenance: The tests were non-clinical, likely conducted in a laboratory setting. There is no information regarding country of origin or whether they were retrospective or prospective.

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

Not applicable. This device is a dental curing light, and the evaluation did not involve human interpretation of medical images or data requiring expert-established ground truth. The "ground truth" for its performance is based on established engineering and materials science principles and measurements (e.g., light intensity, depth of cure).

4. Adjudication method for the test set

Not applicable, as there was no test set requiring expert adjudication for ground truth.

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 document is for a dental curing light, not an AI-powered diagnostic device. No MRMC study was conducted.

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

Not applicable. This device does not use an algorithm or AI. It is a manually operated medical device.

7. The type of ground truth used

The "ground truth" for the performance evaluation relies on:

• Physical measurements: For parameters like light intensity, peak wavelength, and depth of cure, standardized measurement techniques appropriate for dental curing lights would have been used. These measurements serve as the factual basis for performance.
• Engineering standards: Compliance with standards like IEC 60601-1 (Electrical Safety) and IEC 60601-1-2 (EMC & EMI) serves as the "ground truth" for electrical safety and electromagnetic compatibility.

8. The sample size for the training set

Not applicable. This device does not involve machine learning or AI, so there is no training set.

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

Not applicable, as there is no training set.

Ask a specific question about this device