Search Results

The Wireless thermometers are battery-operated electronic devices with intended use of measuring human body temperature precisely. The devices are single-use and intended for armpit temperature measurement for persons of all ages.

TempTraq is a single-use device used to monitor temperature. The type of temperature that can be taken by the TempTraq patch is axillary only. The TempTraq temperature patches consist of a flexible circuit board that is positioned between two pieces of foam. The TempTraq temperature sensor patch is applied to the patient via foam that is backed with a biocompatible adhesive and transmits body temperature data via low energy Bluetooth transmission to a smart device running a TempTraq application. The patch is worn on the underarm and senses, processes, stores, and transmits temperature data to a smart device running a compatible TempTrag application using Bluetooth LE.

The provided text describes the regulatory filing for the TempTraq thermometer, focusing on its substantial equivalence to a previously cleared predicate device. However, it does not contain specific acceptance criteria, test set sample sizes, expert qualifications, or detailed study results (like MRMC studies) for algorithm performance as would typically be found for an AI/ML powered medical device.

The document focuses on demonstrating that the new TempTraq models (TT-100, TT-200, TT-300) are substantially equivalent to the predicate TempTraq TT-100. The testing performed is primarily focused on confirming the hardware and software functionality, safety, and performance of the thermometer itself, rather than an AI/ML algorithm's diagnostic performance.

Therefore, I cannot fulfill your request for the specific details regarding AI/ML acceptance criteria and study results from this document. The information typically found in 510(k) summaries for AI-powered devices (e.g., AUC, sensitivity, specificity, expert reads, etc.) is not present here because this device is a thermometer, not an AI diagnostic tool.

The closest information related to "acceptance criteria" is under the "Accuracy" row in the comparison table, which states "+/- 0.1 °C (0.2 °F) between 30 °C ~ 42.4 °C (86 °F ~ 108.3 °F)". This is a performance specification for the thermometer's accuracy, not for an AI algorithm's diagnostic performance.

Please note: The document describes a thermometer, not a device powered by AI/ML that would require the typical acceptance criteria and study types requested in your prompt.

If you have a document describing an AI/ML device, please provide that, and I can attempt to extract the requested information.

Ask a specific question about this device

The Wireless thermometer, model TT-100, is a battery-operated electronic device with intended use of measuring human body temperature precisely. This device is single-use and intended for armpit temperature measurement for persons of all age.

The TempTraq™, Model TT-100 patch consists of a temperature sensor integrated circuit mounted to a flexible electronic printed circuit board that also contains a microprocessor and a Bluetooth Low Energy (BLE) radio transmitter. Two 1.5V flexible batteries are attached to the circuit board to supply 3.0V DC internal power. The temperature sensor integrated circuit utilizes diode technology where voltage varies with temperature. The sensor circuit is factory calibrated and converts the voltage to an output temperature. The algorithm for conversion is a proprietary algorithm which compensates for the nearly linear behavior of the diode voltage, providing an extremely accurate temperature measurement.

The Blue Spark Technologies TempTraq™, Model TT-100 is a battery-operated electronic device intended for measuring human body temperature precisely, specifically for armpit temperature measurement for persons of all ages. This device is single-use.

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

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states that "Clinical testing was not required to establish equivalency of the device." Therefore, there is no test set of clinical data from human subjects reported in this summary. The performance was demonstrated through "bench tests," "System Verification," "Software Verification and Validation," and compliance with voluntary standards.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
Since no clinical testing was performed on human subjects for the test set, no experts were used to establish ground truth for a clinical test set.

4. Adjudication Method for the Test Set
Not applicable, as no clinical test set on human subjects was used.

5. If a Multi-reader Multi-case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study was not done. The document explicitly states, "Clinical testing was not required to establish equivalency of the device."

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The document describes "bench tests" and "System Verification" which would inherently be standalone performance evaluations of the device itself and its integrated software/firmware. However, it does not explicitly use the term "standalone performance" in the context of an algorithm or AI. The device's primary function is a temperature sensor and transmitter, not an AI-driven diagnostic algorithm. The accuracy specified (±0.1 °C between 30 °C ~ 42.4 °C) likely comes from these standalone bench tests comparing the device's readings against a known accurate temperature source.

7. The Type of Ground Truth Used
For the bench tests and system verification, the ground truth would have been established by known, calibrated reference temperatures generated by laboratory equipment. This is implied by the nature of "bench tests" for thermometer accuracy.

8. The Sample Size for the Training Set
Not applicable. This device is a thermometer, and its core function relies on direct physical measurement via a diode's voltage proportionality to temperature, combined with a proprietary calibration algorithm. This kind of device does not typically involve "training" in the machine learning sense to establish its fundamental measurement accuracy for in-vitro/in-silico testing. The "proprietary algorithm" for temperature conversion is likely a fixed mathematical model based on physical principles and factory calibration, not a trained machine learning model requiring a training dataset.

9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no mention or implication of a machine learning "training set" for this device. The "factory calibrated" nature of the sensor circuit suggests a one-time calibration process against precise reference temperatures during manufacturing.

Ask a specific question about this device