Search Results

The non-contact forehead thermometer is an electronic thermometer using an infrared detector (thermopile detector) to detect body temperature from forehead center in people of all ages.

The thermometer (Mode: TH48FE, TH09F, THD2FE) are electronic thermometer using an IR sensor to measure infrared energy radiated from the forehead. This energy is collected through the lens and converted to an oral temperature value. The thermometer consists of an IR sensor with a built-in ambient temperature sensor, Application-Specific Integrated Circuitry including software, LCD display, buttons, and batteries.

The provided text describes a 510(k) premarket notification for a non-contact forehead thermometer. While it discusses the device's accuracy and clinical validation, it does not detail a study that proves the device meets complex acceptance criteria for an AI/ML-driven medical device, as typically outlined for such systems. The acceptance criteria and study described are for a traditional medical device (a thermometer), focusing on its accuracy and safety standards rather than AI performance metrics.

Therefore, for AI/ML specific criteria like MRMC studies, ground truth establishment for AI training/testing, or separate human-in-the-loop vs. standalone AI performance, the provided document does not contain this information. The questions will be addressed based on the information available in the document, and limitations will be noted where information is absent.

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

The device in question is a Non-contact Forehead Thermometer (Models TH48FE, TH09F, THD2FE), which is a traditional electronic medical device, not an AI/ML system. Therefore, the "acceptance criteria" and "study" described in the document relate to the performance of a thermometer, primarily its accuracy and compliance with relevant standards, rather than the complex AI/ML evaluation metrics (like sensitivity, specificity, MRMC studies, etc.) typically associated with AI-driven devices.

Here's a breakdown of the requested information based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

For a non-contact forehead thermometer, the primary performance criterion is accuracy.

Note: The document implies these are "acceptance criteria" by stating the device "met all design specifications" and "complied with" or "meet" the standards.

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

• Sample Size for Clinical Accuracy Validation (Test Set): 113 subjects.
• Data Provenance: Not explicitly stated, but the submission is from a Taiwan-based manufacturer (Radiant Innovation Inc.). It also doesn't specify if the clinical trial was retrospective or prospective, but clinical accuracy validation trials per ISO standards are typically prospective.

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

The document does not specify the number or qualifications of experts used to establish ground truth for the thermometer's clinical accuracy. For thermometer testing, "ground truth" typically refers to core body temperature measured by a highly accurate reference method (e.g., rectal thermometer in a controlled setting) against which the test device's readings are compared. This usually involves clinical staff following a standardized protocol rather than a panel of "experts" as in AI image interpretation.

4. Adjudication method for the test set

Not applicable/not specified. For simple temperature measurement, "adjudication" in the sense of resolving disagreements between multiple readers (as in AI image analysis) is not relevant. The ground truth would be established by the reference standard measurement.

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

Not applicable. This device is a standalone non-AI thermometer. There is no AI component or human-in-the-loop aspect for which an MRMC study would be performed.

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

This device is a "standalone" device in the sense that it provides a temperature reading without human interpretation beyond reading the display. Its "algorithm" is the internal software that converts IR signals to an oral temperature value. The document states:

• "Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions"."
• "The software for this device was considered as a "Basic" documentation level."

This confirms that the device's internal software/algorithm performance was validated.

7. The type of ground truth used

The ground truth for the clinical accuracy validation would be a reference body temperature measurement, typically obtained using a highly accurate clinical thermometer (e.g., a rectal thermometer) under controlled clinical conditions, as per the methodology outlined in ISO 80601-2-56 for clinical accuracy validation of medical thermometers. This is implicit in "Clinical Accuracy Validation."

8. The sample size for the training set

Not applicable. This is a traditional medical device, not an AI/ML device that requires a "training set" for model development. The internal software/firmware is developed and verified, not "trained" on data in the AI sense.

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

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

Ask a specific question about this device