Search Results

The Clinical Digital Thermometer is intended to measure the body temperature oral or axillaries (under the arm) and to be used by consumers in household environments. It is intended for use on adults and children ages 4 and up.

The iHealth PT1 Clinical Digital Thermometer is hand-held, predictive, thermistor-based, stick thermometer capable of measuring temperature in about 30 seconds. The thermometer uses a negative temperature coefficient thermistor embedded in a measurement tip that is in contact with the measurement site. As the thermistor changes temperature, the resistance of the thermistor also changes, which is measured by the thermometer and converted to a measurement of the temperature of the tip of the thermometer. This temperature, following the use of the predictive algorithm, is then displayed to the end user. Because the thermometer displays the measurement for the physiological site at which it is used, it does not need to convert this temperature via clinical offset.

The provided text is for a Clinical Digital Thermometer (iHealth PT1). Here's a breakdown of the acceptance criteria and the study that proves the device meets those criteria:

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

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

• Sample Size: 110 subjects
  • 40 subjects in the children's group (4-5 years old)
  • 70 subjects in the adults' group (> 5 years old)
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective), but the study is described as a "Clinical investigation," which typically implies a prospective design.

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 clinical accuracy validation test. It only mentions that the "Clinical investigation and data analysis have performed according to ISO 80601-2-56." This standard outlines requirements for clinical accuracy, which would involve comparison to a reference thermometer reading.

4. Adjudication method for the test set

The document does not explicitly state the adjudication method (e.g., 2+1, 3+1). The clinical accuracy test was conducted according to ISO 80601-2-56, which specifies protocols for such measurements, likely involving a skilled operator taking readings against a reference.

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 is not applicable as the device is a clinical digital thermometer, not an AI-assisted diagnostic tool involving human readers.

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

This is a standalone device in the sense that it provides a temperature reading directly to the user. The "predictive algorithm" mentioned in the device description is integral to its function of displaying a rapid temperature measurement, so its performance (as part of the device) was evaluated.

7. The type of ground truth used

For the clinical accuracy validation test, the ground truth was established by comparison to a reference temperature measurement, as dictated by the ISO 80601-2-56 standard for clinical thermometers.

8. The sample size for the training set

The document does not explicitly mention a separate "training set" in the context of machine learning model training. The predictive algorithm used by the thermometer would likely have been developed and validated during the device's design phase, prior to this specific submission. The listed clinical accuracy validation test dataset (110 subjects) is for the evaluation of the device's performance, not necessarily for training the predictive algorithm itself.

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

As there's no explicit mention of a training set for an AI model in the context of this submission, the method for establishing its ground truth is not described. The predictive algorithm's development would likely have used a robust set of physiological temperature data paired with reference measurements, conforming to relevant scientific and engineering best practices for medical device software.

Ask a specific question about this device