Search Results

The Infrared thermometer is non-contact infrared thermometer intended for the intermittent measurement of human body temperature from forehead for people of all age. The device is reusable for home use and clinical use

The proposed device, infrared thermometer, is hand-held, battery powered device, which is intended to measure human body temperature by measuring forehead. The distance of the measurement is 1~5cm. The device is non-contacting infrared thermometer and intended for people of all age.

The provided document describes the FDA 510(k) clearance for an Infrared Thermometer (K202368). The study conducted focuses on demonstrating substantial equivalence to a predicate device, primarily through non-clinical and a single clinical study verifying accuracy and repeatability against a standard.

Here's an analysis based on your request, understanding that this is a medical device clearance, not an AI/ML product often associated with complex MRMC studies:

Acceptance Criteria and Reported Device Performance

The core acceptance criterion for the Infrared Thermometer is its accuracy. The study aims to show that the device meets the accuracy requirements specified in the standard ISO 80601-2-56 and ASTM E1965-98 (2016).

Table of Acceptance Criteria and Reported Device Performance:

Study Details:

1. Sample Size and Data Provenance:

   • Test Set Sample Size: The document states that a "controlled human clinical study was conducted." However, it does not specify the sample size (number of subjects/measurements) used in this clinical study.
   • Data Provenance: The location of the clinical study is not explicitly stated, but the company is based in China. The study is described as a "controlled human clinical study," which generally implies a prospective data collection for the purpose of the study.

2. Number of Experts and Qualifications (for Ground Truth Establishment):

   • This document describes the clearance of an infrared thermometer, not an AI/ML diagnostic device that typically relies on expert interpretation of complex medical images. The "ground truth" for temperature measurement is typically established using a reference thermometer (e.g., a rectal thermometer) adhering to an established clinical standard.
   • Therefore, the concept of "experts establishing ground truth" in the sense of radiologists reviewing images does not apply to this type of device. The ground truth for temperature is based on established metrological traceability and standard reference measurements.

3. Adjudication Method:

   • Not applicable as this is not a study involving expert adjudication of diagnostic findings. The clinical study for a thermometer compares its readings against a gold standard reference thermometer.

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

   • No, a MRMC study was not performed. This type of study is relevant for AI/ML diagnostic tools where human readers (e.g., radiologists) interpret images with and without AI assistance. This device is a direct measurement tool, not an AI diagnostic aid.

5. Standalone (Algorithm Only) Performance:

   • Yes, the clinical study essentially evaluates the standalone performance of the device by comparing its temperature readings against a reference method (the "predicate device" also serves as a comparison point, and the study was done "in accordance with ASTM E1965-98 (2016)," which sets standards for clinical thermometer performance). The device itself is an algorithm (software) translating sensor data into a temperature reading.

6. Type of Ground Truth Used:

   • For the clinical study, the ground truth for body temperature was established by comparing the proposed device's measurements against a reference method or established clinical standard as per ASTM E1965-98 (2016). This standard outlines procedures for determining the accuracy of clinical thermometers, typically involving comparisons to highly accurate reference thermometers in a controlled clinical setting. It is not based on expert consensus, pathology, or outcomes data in the typical sense used for diagnostic imaging AI.

7. Sample Size for Training Set:

   • This document describes the regulatory clearance of a finished medical device (an infrared thermometer). While it contains software, it is not described as an adaptable AI/ML model that undergoes a separate "training" phase with a large dataset in the way a deep learning model would.
   • Therefore, the concept of a separate "training set" with a specified sample size for an AI/ML algorithm is not directly applicable or described in this 510(k) summary for this device. The software verification and validation are more about traditional software engineering principles.

8. How Ground Truth for Training Set Was Established:

   • As there's no mention of a traditional "training set" for an AI/ML algorithm, this question is not applicable in the context of this 510(k) submission. The "ground truth" for the device's functionality and performance is based on its design specifications, adherence to standards, and the results of the clinical and non-clinical tests.

Ask a specific question about this device