(135 days)
The Infrared No-Touch Forehead Thermometer is intermittent measurement of body temperature from the forehead on people of all ages. It can be used by consumers in the household environment and by healthcare providers.
The iHealth PT3 Infrared No-Touch Forehead Thermometer is hand-held, reusable, battery operated device, which can measure human body forehead temperature without touching patient's skin. Its operation is based on measuring the natural thermal radiation from the central forehead. Put the probe of the thermometer at a measurement distance less than or equal to 1.18 inch (3cm) without touching the skin at the center of the patient's forehead. lt uses a thermopile sensor to measure the patient's forehead temperature and convert it to the oral equivalent. Pressing the activation button to start the measurement of proposed infrared radiation. The time from start of measurement to display of temperature reading is about 1 second. The electrical signal read out from the detector is fed to the circuit for amplification and calculation. The final measured temperature will be appeared on a LED display.
The provided document describes the clearance of an iHealth Infrared No-Touch Forehead Thermometer (Model: PT3) and includes information about its performance testing. However, it does not describe an AI/ML medical device where the performance is measured by metrics like sensitivity, specificity, or AUC, nor does it detail a study involving human readers or expert panels for ground truth establishment.
Instead, this document details the substantial equivalence of a clinical electronic thermometer to a predicate device. The performance criteria are related to the accuracy of temperature measurement and compliance with established standards (like ASTM E1965-98) for such devices.
Therefore, many of the requested categories related to AI/ML device evaluation (like sample size for test set, number of experts for ground truth, adjudication methods, MRMC study, standalone performance) are not applicable to this type of device and the information provided.
I will fill in the relevant available information, and mark non-applicable sections clearly.
Acceptance Criteria and Device Performance for iHealth Infrared No-Touch Forehead Thermometer (Model: PT3)
The device is an iHealth Infrared No-Touch Forehead Thermometer (Model: PT3) and its performance is assessed against the requirements for a clinical electronic thermometer, primarily focusing on temperature measurement accuracy.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Standard / Parameter) | Performance Standard | Reported Device Performance (iHealth PT3) |
|---|---|---|
| Accuracy | ±0.4°F (0.2°C) within 95 | ±0.4°F (0.2°C) within 95 |
| ±0.5°F (0.3°C) for other ranges | ±0.5°F (0.3°C) for other ranges | |
| Compliance Standard | ASTM E1965-98 (2016) | Complies with ASTM E1965-98 (2016) |
| Electrical Safety | IEC 60601-1:2005/(R)2012 And A1:2012,C1:2009/(R)2012 And A2:2010/(R)2012 | Test performed and device meets standard |
| Electromagnetic Compatibility (EMC) | IEC 60601-1-2:2014 | Test performed and device meets standard |
| Performance (Specific to Thermometers) | ISO 80601-2-56 (incl. Amendment 1 (2018)) | Test performed and device meets standard |
| Software Verification and Validation | FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005) | Conducted and demonstrates no new performance questions |
| Biocompatibility (for skin-contacting components) | ISO 10993-1, ISO 10993-5, ISO 10993-10 | Complies; no new risk for proposed device |
| Reprocessing: Cleaning and Disinfection | According to Instructions for Use | Validation performed |
2. Sample Size Used for the Test Set and Data Provenance
This is not an AI/ML device, so there isn't a "test set" in the typical machine learning sense. The performance was evaluated through clinical accuracy testing and laboratory testing.
- Clinical Accuracy Test Sample Size:
- Infants (0-1 year): 40 subjects
- Children (1-5 years): 40 subjects
- Adults (>5 years): 50 subjects
- Total: 130 subjects
- Data Provenance: Not explicitly stated, but the submission is from a Chinese company (Andon Health Co., Ltd., Tianjin, China). It is reasonable to assume the clinical testing was conducted in a region accessible to the manufacturer, but specific country/site is not detailed. The study type is prospective clinical investigation as implied by "Clinical investigation and data analysis have performed according to ASTM E1965-98. The test report shows result of 40 subjects..."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Not applicable in the context of an AI/ML device where experts establish ground truth. For a thermometer, "ground truth" is typically established by comparing the device's readings to highly accurate reference thermometers or established clinical methods (e.g., rectal temperature). The clinical accuracy test was conducted according to ASTM E1965-98, which outlines the methodology for such evaluations, often involving a comparison to a precise primary standard. The document does not specify human experts adjudicating temperature readings.
4. Adjudication Method for the Test Set
- Not applicable. There is no "adjudication" in the sense of reconciling differences between multiple human readers or expert opinions for this type of medical device. The accuracy is determined by direct comparison of the device's temperature readings to a reference standard as per the ASTM E1965-98 protocol.
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 thermometer, not an AI-assisted diagnostic tool that aids human readers.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Yes, in essence. The "standalone performance" refers to the device's direct measurement capabilities. The clinical accuracy test and laboratory tests (electrical safety, EMC, performance per ISO 80601-2-56) demonstrate the performance of the device itself, independent of human interpretation or assistance beyond its proper operation. The temperature reading is directly generated by the device's thermopile sensor and internal algorithms converting infrared radiation to a temperature display.
7. The Type of Ground Truth Used
- Reference Temperature Standard: The ground truth for temperature measurement accuracy in this context is established by a reference thermometer or method that conforms to the accuracy requirements of relevant standards (e.g., ASTM E1965-98), often involving core body temperature measurements (e.g., rectal temperature) as a comparator. The document states "Clinical investigation and data analysis have performed according to ASTM E1965-98," which specifies the methods for establishing true body temperature for comparative accuracy testing.
8. The Sample Size for the Training Set
- Not applicable. This is not an AI/ML device; therefore, there is no "training set" in the machine learning context. The device's internal algorithms are based on physics and engineering principles of infrared thermometry, not on machine learning from a large dataset.
9. How the Ground Truth for the Training Set Was Established
- Not applicable. As there is no training set for an AI/ML model, this question is not relevant. The device's calibration and internal functioning are based on established physical laws and engineering design that relate detected infrared radiation to temperature values.
§ 880.2910 Clinical electronic thermometer.
(a)
Identification. A clinical electronic thermometer is a device used to measure the body temperature of a patient by means of a transducer coupled with an electronic signal amplification, conditioning, and display unit. The transducer may be in a detachable probe with or without a disposable cover.(b)
Classification. Class II (performance standards). The device is exempt from the premarket notification procedures in part 807, subpart E of this chapter, subject to the limitations in § 880.9 and the following conditions for exemption:(1) Device is not a clinical thermometer with telethermographic functions;
(2) Device is not a clinical thermometer with continuous temperature measurement functions; and
(3) Appropriate analysis and testing (such as that outlined in the currently FDA-recognized editions, as appropriate, of ISO 80601-2-56, “Medical electrical equipment—Part 2-56: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement,” or ASTM E1965, “Standard Specification for Infrared Thermometers for Intermittent Determination of Patient Temperature,” or ASTM E1112, “Standard Specification for Electronic Thermometer for Intermittent Determination of Patient Temperature,” or ASTM E1104, “Standard Specification for Clinical Thermometer Probe Covers and Sheaths”) must validate specifications and performance of the device.