Search Results

The CliniCloud Non-Contact Thermometer is an infrared thermometer intended for the periodic measurement of human body temperature for persons of all ages, to be used in conjunction with the CliniCloud app.

The CliniCloud Non-Contact Thermometer Model SPL1024 (abbreviated 'CliniCloud Non-Contact Thermometer') is a battery powered Bluetooth Low Energy (BLE) enabled portable infrared thermometer intended for the measurement of human body temperature for persons of all ages. It features no physical buttons or a display and must be used in conjunction with the CliniCloud App on a compatible BLE enabled smartphone. The CliniCloud App is free to download.

When power is applied to the device via 2 AAA batteries, the CliniCloud Non-Contact Thermometer starts to advertise via BLE, and can establish a BLE connection with BLE enabled smart phones with the CliniCloud app. The user could then request the CliniCloud non-contact thermometer to take temperature readings from within the CliniCloud app. The measured temperatures are sent back to the smart phone via the established Bluetooth link and displayed on the smartphone's display in the CliniCloud app. The CliniCloud Non-Contact Thermometer uses a medical grade MLX90614ESF-DCC thermopile sensor supplied by Melexis to passively measure object surface temperature using infrared radiation emitted by patients. The sensor also measures the ambient temperature with a built-in thermistor. The sensor is factory calibrated to meet consensus standard ASTM E1965-98. Upon receiving a request from the CliniCloud APP over the established BLE connection the onboard Nordic Semiconductor NRF51822 BLE SOC microcontroller communicates with the thermopile (MLX90614ESF-DCC) over the 12C bus and sends the received temperature readings including the object surface temperature and the ambient temperature to the CliniCloud app via the established BLE connection. On the smartphone app, the well-known heat loss equation is used to perform conversion of forehead surface temperature to oral equivalent temperature.

Here's a breakdown of the acceptance criteria and study information for the CliniCloud Non-Contact Thermometer, Model SPL1024, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are primarily derived from the ASTM E1965-98 standard for infrared thermometers.

Note on Measurement Accuracy: The document states that the sensor is "factory calibrated to meet consensus standard ASTM E1965-98" and also lists the measuring accuracy as ± 0.2ºC (0.4ºF) in the comparison table, which is a common accuracy requirement within that standard for clinical electronic thermometers.

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

• Sample Size: 60 subjects.
• Data Provenance: The document does not explicitly state the country of origin.
• Retrospective or Prospective: Prospective, as it was a "Validation study... performed to clinically validate the CliniCloud thermometer."

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• The document does not mention the number of experts used to establish ground truth or their specific qualifications.
• Instead of expert consensus for ground truth, the study utilized 4 calibrated reference devices (same model) used as gold standard. These would typically be high-precision, clinically validated thermometers.

4. Adjudication Method for the Test Set

• The document does not describe an adjudication method involving experts. The ground truth was established by calibrated reference devices.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This study is for a non-contact thermometer, which measures a physical parameter (temperature) and does not involve human readers interpreting images or data that an AI would assist with.

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

• Yes, a standalone performance assessment was conducted for the device. The "Validation study" in point 9 of the K510 summary refers to the clinical accuracy of the CliniCloud thermometer itself, comparing its measurements to the gold standard reference devices. While the device works "in conjunction with the CliniCloud app," the core measurement accuracy is evaluated independently of human interpretation of the results through an AI.

7. The Type of Ground Truth Used

• Gold Standard Reference Devices: The ground truth for the clinical validation study was established using "4 calibrated reference devices (same model) used as gold standard." This implies a comparison to highly accurate and independently verified temperature measurement tools.

8. The Sample Size for the Training Set

• The document does not explicitly mention a "training set" in the context of machine learning or AI algorithms. The device is a thermometer that relies on a physical sensor and conversion algorithms, not a learned model (like an AI).
• The "factory calibrated" statement for the sensor implies calibration data, but not a "training set" in the typical AI sense.

9. How the Ground Truth for the Training Set Was Established

• As mentioned above, there isn't a "training set" in the conventional AI sense for this device. The sensor itself is "factory calibrated to meet consensus standard ASTM E1965-98." This calibration process, which likely involves proprietary methods by the sensor manufacturer and CliniCloud, establishes the accuracy of the sensor and its algorithms to convert raw infrared readings into a human body temperature.

Summary of the Study Proving Acceptance Criteria:

The key study mentioned is a "Validation study" conducted to clinically validate the CliniCloud thermometer (Model SPL1024) according to ASTM E1965-98.

• Study Design: The study involved 60 subjects and compared the CliniCloud thermometer's readings against 4 calibrated reference devices (gold standard). A predicate device was also included for comparison.
• Result: The study "demonstrated that the clinical accuracy of the CliniCloud thermometer and the predicate devices yielded equivalent accuracy," implying that the CliniCloud device met the accuracy requirements of ASTM E1965-98, which typically involves a mean difference and standard deviation within specified limits when compared to a reference thermometer. The stated accuracy is ± 0.2ºC (0.4ºF).
• Non-Clinical Tests: Additional non-clinical tests were performed (e.g., IEC standards for electrical safety and EMC, FCC, biocompatibility, risk management, wireless functionality) to ensure the device met all safety and performance specifications.

Ask a specific question about this device