Search Results

The Digital Thermometers MT series are intended to measure the human body temperature in regular mode orally, rectally or under the arm. The devices are reusable for clinical or home use on people of all ages.

Models MT-1027, MT-4127, MT-4132, MT-4132, MT-4335, MT-4335, MT-4326, MT-09, MT-30, MT-31, and MT-36 are non-predictive digital thermometers. Models MT-4726 and MT-4735 are predictive digital thermometers. Both predictive and non-predictive models include a sensor, buzz films, housing, a stainless steel cap, a LCD display, and a measurement control module. The thermometers include a dustproof case as an accessory. Additionally, both models do not need to be used in conjunction with a disposable probe cover when taking temperature.

The provided document describes the Sejoy Electronics & Instruments Co., Ltd. Digital Thermometer MT series (Models MT-1027, MT-4127, MT-1032, MT-4132, MT-4333, MT-4326, MT-4726, MT-4335, MT-4735, MT-09, MT-30, MT-31, MT-36) and its substantial equivalence to predicate devices (MT-4119 and MT-4320).

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on demonstrating substantial equivalence to predicate devices and adherence to relevant standards. The key performance acceptance criteria can be inferred from the "Accuracy" row in the comparison table and the clinical accuracy evaluation for predictive models.

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

• Test Set Sample Size: The document does not explicitly state the sample size (number of subjects or measurements) for the "clinical accuracy evaluation" mentioned for predictive models MT-4726 and MT-4735. It only states that the evaluation was conducted "according to clause 201.102 of ISO 80601-2-56:2009". This standard would typically define the required sample size and testing methodology.
• Data Provenance: Not specified in the document. It does not mention the country of origin of the data or whether it was retrospective or prospective.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The document only references compliance with ISO 80601-2-56:2009 for the clinical accuracy evaluation. This standard would define the requirements for reference temperature measurements, which would implicitly involve qualified personnel, but their role as "experts to establish ground truth" in the context of an AI device is not directly applicable here as it's a device measuring a physical quantity.

4. Adjudication Method for the Test Set

• Not applicable as this is a medical device for measuring a physical parameter (temperature), not an AI device making a diagnostic or interpretive output that would typically require expert adjudication for ground truth. The "ground truth" for temperature measurement would be established by a primary reference thermometer meeting metrological standards as outlined in ISO 80601-2-56.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, an MRMC comparative effectiveness study was not done. This type of study is relevant for AI systems that assist human readers in interpreting medical images or data. The device in question is a standalone digital thermometer, not an AI-assisted diagnostic tool.

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

• Yes, a standalone performance evaluation was done. The entire submission describes the standalone performance of the digital thermometers. Specifically for the "predictive models MT-4726 and MT-4735," a "clinical accuracy evaluation has been conducted according to clause 201.102 of ISO 80601-2-56:2009." This evaluation assesses the device's accuracy in measuring temperature without human interpretation of its output beyond reading the displayed value. The predictive algorithm itself is a "standalone" component of the device's operation.

7. The Type of Ground Truth Used

• Reference standard/metrological ground truth: For temperature measurement, the ground truth would be established using reference thermometers or calibrated temperature baths as per the requirements of ISO 80601-2-56 and ASTM E1112. The specific details, like the type of reference standard and its traceability, are not provided but would be implied by adherence to these standards. For the predictive models, the proprietary algorithm aims to predict the "balanced temperature after 5 minutes," which would be the "ground truth" target for the prediction.

8. The Sample Size for the Training Set

• Not applicable / Not explicitly mentioned. The document describes a traditional medical device (digital thermometer), even with a predictive algorithm for some models. The term "training set" is typically used for machine learning models. While the predictive algorithm must have been developed and validated, the document does not present it as a machine learning model that would require a distinct "training set" in the sense of AI. The development of the proprietary algorithm would involve calibration and empirical data, but it's not described as a "training set" for an AI model.

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

• Not applicable / Not explicitly mentioned. As mentioned above, the concept of a "training set" with established "ground truth" for an AI model is not directly applied in the document's description of a digital thermometer, even for models with a predictive algorithm. The accuracy of the predictive algorithm would be validated against empirically measured "balanced temperatures" in a clinical setting as outlined by the ISO standard.

Ask a specific question about this device