Search Results

The infrared forehead Thermometer DPT-IFT100 is a non-contact thermometer intended for the intermittent measurement of human body temperature from forehead for people of one month old and above. The device is reusable for home use and clinical use.

The infrared forehead thermometer, Model DPT-IFT100, is an electronic thermometer using an infrared temperature sensor to measure infrared energy radiated from the forehead. This energy is collected through the infrared temperature sensor convert to a voltage signal. The signal is measured by the main microcontroller, calculated by the internal algorithm, finally converted into a digital temperature value to display on the LCD.

The design consists of a lens to focus the infrared thermal radiation on to a detector, which converts the radiant power to an electrical signal displayed in units of temperature after being compensated for ambient temperature. This permits temperature measurement from a 3~5 cm distance without contact with the object to be measured.

The Infrared forehead thermometer, Model DPT-IFT100, consists of the following parts:
a) Thermopile Sensor
b) Application-Specific Integrated Circuit
c) Housing
d) LCD and Backlight
e) 1 button (Power on/Power off/Measurement)
f) Alkaline batteries; size AAA, 2 x 1.5 V
g) LCD cover

This document (K202420) is a 510(k) summary for the Conmo Electronic Company Limited's Infrared Forehead Thermometer, Model DPT-IFT100. It details the device's characteristics, comparison to a predicate device, and the testing conducted to demonstrate substantial equivalence.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Infrared Forehead Thermometer DPT-IFT100 are primarily defined by adherence to recognized performance standards and demonstrated substantial equivalence to a predicate device. The performance data presented focuses on accuracy and the clinical study results.

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

• Sample Size: 150 subjects.
  • Breakdown: 50 infants (newborn to one year), 50 children (greater than one to five years), and 50 adults (greater than five years old).
• Data Provenance: Not explicitly stated regarding country of origin. The study was conducted for a device manufactured by Conmo Electronic Company Limited, based in Guangxi Province, China, and submitted through a US Agent in Arizona. Clinical studies are typically conducted where the product is intended for market or where clinical trial infrastructure exists. The document does not specify if it was retrospective or prospective, but clinical studies for regulatory submissions are generally prospective.

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

This document describes a clinical study for a medical device (thermometer) where the "ground truth" is the actual body temperature measurements. This is a direct measurement, not a subjective interpretation requiring multiple experts. The document does not mention the use of experts to establish a "ground truth" in the way one would for an AI-powered diagnostic image analysis system. The ground truth for temperature measurement would be established by the reference temperature measurement method used in the clinical setting, typically a calibrated device.

4. Adjudication Method for the Test Set

Not applicable. As described above, this is a temperature measurement device, not an interpretative diagnostic device requiring adjudication of expert opinions.

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 is a standalone medical device (thermometer) and not an AI-assisted diagnostic tool that involves human readers.

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

Yes, implicitly. The performance of the Infrared Forehead Thermometer DPT-IFT100 is its standalone measurement accuracy, clinical bias, and clinical repeatability. The device operates independently to measure temperature. The "algorithm" mentioned (CM3.1 Algorithm) is internal to the device for processing the infrared signal into a temperature reading. The clinical study directly assesses this standalone performance against accepted standards.

7. The Type of Ground Truth Used

The ground truth used for the clinical study was the actual body temperature, presumably measured by a reference thermometer, against which the DPT-IFT100's readings were compared to determine clinical bias and repeatability. This is akin to outcomes data or a highly accurate reference standard measurement. The study report stated: "The test report demonstrated that the clinical data, represented by clinical bias and clinical repeatability met the acceptance criteria of the clinical study protocol."

8. The Sample Size for the Training Set

Not applicable. This device is a traditional electronic thermometer, not an AI/machine learning device that requires a separate training set. The "algorithm" (CM3.1) refers to its internal firmware/logic for temperature calculation, not a learned model from a dataset.

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

Not applicable, as there is no training set mentioned for this type of device. The device's internal algorithm (CM3.1) is a fixed computational process, not an AI model that learns from a training set.

Ask a specific question about this device

Upper Arm Electronic blood pressure monitor is intended to measure the blood pressure and pulse rate of adult at household or medical center. (Not suitable for neonate, pregnancy or pre-eclampsia).

The Upper Arm Electronic Blood Pressure Monitor, Model BM100-EN operation is based on the oscillometric method. This method takes advantage of the pressure pulsations taken during measurements. An occluding cuff is placed on the left arm and is connected to an air pump and a pressure sensor. The cuff is inflated until a pressure higher than the typical systolic value is reached, then the cuff is slowly deflated. As the cuff deflates, when systolic pressure value approaches, pulsations start to appear. These pulsations represent the pressure changes due to heart ventricle contraction and can be used to calculate the heartbeat rate. Pulsations grow in amplitude until mean arterial pressure (MAP) is reached, then decrease until they disappear. The blood pressure information is displayed as digital information on the device's screen.

The provided text is related to a 510(k) premarket notification for an Upper Arm Electronic Blood Pressure Monitor, Model BM100-EN. The document describes the device, compares it to a predicate device, and outlines the testing conducted to support its substantial equivalence.

However, the request asks for specific details about acceptance criteria and a study that proves the device meets the acceptance criteria, particularly in the context of an AI/ML medical device. The provided document is for a traditional medical device (blood pressure monitor) and does not contain information about AI/ML acceptance criteria or an AI-based study. It focuses on performance standards (like IEC 80601-2-30) for blood pressure measurement accuracy, not AI performance metrics.

Therefore, I cannot fulfill the request as it asks for information (AI acceptance criteria, AI study details, expert ground truth, MRMC study, etc.) that is not present in the provided document. The document describes non-clinical and performance testing for a standard blood pressure monitor.

To directly answer the prompt and explain why I cannot provide the requested information, here's a breakdown of what is and is not in the text:

Information Present in the Document:

• Device Name: Upper Arm Electronic Blood Pressure Monitor, Model BM100-EN
• Predicate Device: Jiangsu Yuyue Medical Equipment & Supply Co., Ltd Upper Arm Type Electronic Blood Pressure Monitor Series, Electronic Blood Pressure Monitor: YE670D (K170605)
• Indication for Use: Measuring blood pressure and pulse rate of adults at household or medical center (not for neonate, pregnancy, or pre-eclampsia).
• Measurement Method: Non-invasive, oscillometric.
• Performance Standards Met: IEC 80601-2-30 (Medical electrical equipment Part 2-30: Particular Performance requirements for the basic safety and essential performance of automated non-invasive sphygmomanometers) and ISO 81060-2 (Non-invasive sphygmomanometers Part 2: Clinical validation of automated measurement type).
• Accuracy Claims (from characteristics table): Blood Pressure Range Accuracy: ±3 mmHg (±0.4kPa); Pulse Rate Measurement Accuracy: ±5% of reading value.
• Non-Clinical Testing: Safety and EMC (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-11), Software Verification and Validation (following FDA Guidance for moderate level of concern software), Cleaning Validation, Biocompatibility (ISO 10993-1, ISO 10993-5, ISO 10993-10).
• Clinical Study: "a comparative clinical study to verify the performance of the subject device and predicate device as well as a mercury sphygmomanometer according to ISO 81060-2:2013." This is a study to validate the accuracy of the blood pressure readings against a reference, not an AI performance study.

Information Not Present in the Document (and thus, cannot be provided to answer your specific questions about AI/ML acceptance criteria and studies):

• Table of AI acceptance criteria and reported device performance: The document lists performance criteria for a blood pressure monitor (e.g., accuracy ±3 mmHg) but not AI-specific metrics like sensitivity, specificity, AUC, F1-score, etc.
• Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): While a "comparative clinical study" is mentioned, no details about sample size (number of subjects), data provenance, or whether it was retrospective/prospective are provided.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as this is for a blood pressure monitor, not an AI image interpretation device. Ground truth for blood pressure is typically established by direct measurement with a reference standard (like a mercury sphygmomanometer) in a clinical setting.
• Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for this type of device.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not applicable for this device.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as this is a physical measurement device, not an AI algorithm.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For blood pressure, the ground truth is often the reading from a validated reference device (e.g., mercury sphygmomanometer) or invasive arterial pressure. The document mentions comparison to a mercury sphygmomanometer.
• The sample size for the training set: Not applicable, as this is not an AI/ML device that requires a training set in that context.
• How the ground truth for the training set was established: Not applicable.

In conclusion, the provided FDA 510(k) clearance document is for a basic medical device (blood pressure monitor) and does not describe an AI/ML device or its associated acceptance criteria and validation studies as detailed in your query.

Ask a specific question about this device

Body Fat Analyzer and Scale measures body weight and impedance and estimates percentage of body fat, body water and body muscle mass using BIA (bioelectrical impedance analysis). It is intended for use by healthy adults 18 years of age or older who are not ill, feverish, have a chronic or acute disease, or a condition that affects the level of hydration such as pregnancy for body composition assessment in the home environment.

The patient steps on the scale device, where four electrodes are located. The patient must step on the electrodes with bare feet, with normal moisture. Through harmless current stimulation of 500 µA, at 50 kHz, the Conmo Electronic Company Limited Body Fat Analyzer and Scale provides weight, calculates the body fat, body water and body muscle mass. This calculation is done via the Bioelectrical Impedance Method. The current is passed through the body and the impedance of the body determines the body fat. The calculation is based upon electrical impedance, height, weight, age, and gender. The calculation is performed via internal software, which uses the variables programmed in by the user. There are elements of this process that can produce erroneous readings, such as dry feet or improper-programmed data. The User's Manual defines items which could cause erroneous readings.

The Conmo Electronic Company Limited Body Fat Analyzer and Scale, Model 5786, measures body weight and impedance and estimates the percentage of body fat, body water, and body muscle mass using Bioelectrical Impedance Analysis (BIA). The provided 510(k) summary states that clinical testing was used to validate the effectiveness and accuracy of the device, with all test results reported as satisfactory. However, the document does not explicitly detail specific acceptance criteria or the study design (e.g., sample size, expert involvement, ground truth methodology) for this clinical testing.

Based on the information provided, here's what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The provided document does not explicitly state specific numerical acceptance criteria for accuracy, precision, or other performance metrics. It only states that "Clinical testing was used to validate the effectiveness and accuracy of the device. All test results were satisfactory." Without specific criteria, a direct comparison is not possible.

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

• Sample Size for Test Set: Not specified
• Data Provenance: The document does not specify the country of origin of the data or whether the study was retrospective or prospective. It only mentions "Clinical testing."

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

• Number of Experts: Not specified
• Qualifications of Experts: Not specified

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. The document does not provide details on how discrepancies in ground truth establishment (if any) were resolved.

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

• MRMC Study: No, an MRMC comparative effectiveness study was not mentioned or described in the document. This type of study typically involves human readers interpreting diagnostic images or data with and without AI assistance to measure the effect size of AI improvement. The device in question is a standalone measurement device for body composition, not an AI-assisted diagnostic tool.

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

• Standalone Performance: While the device functions as a standalone unit (measurements are taken by the device and calculations performed by internal software), the document does not provide a detailed breakdown of a standalone performance study with specific metrics beyond the general statement of "satisfactory" effectiveness and accuracy. The clinical testing mentioned seems to assess the overall device performance which, by its nature, is standalone as it outputs direct measurements.

7. The Type of Ground Truth Used

• Type of Ground Truth: The document does not explicitly state the specific "ground truth" method used for the clinical validation of body fat, body water, or body muscle mass. For body composition devices, common ground truth methods include:
  • DEXA (Dual-energy X-ray absorptiometry): A gold standard for body composition.
  • Hydrostatic weighing: Another accurate method.
  • Air displacement plethysmography (Bod Pod): Also considered accurate.
  • Calipers: For skinfold thickness.
    Without this information, it's unclear against what highly accurate measurement the device's outputs were compared.

8. The Sample Size for the Training Set

• Sample Size for Training Set: Not applicable/Not specified. The document describes a device that performs calculations based on Bioelectrical Impedance, height, weight, age, and gender using "internal software." It does not describe a machine learning or AI model that requires a distinct "training set" in the conventional sense. The "internal software" likely uses established BIA equations rather than a learned model from a large dataset.

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

• Ground Truth for Training Set: Not applicable/Not specified. As there is no mention of a training set for a machine learning model, the method for establishing ground truth for such a set is not relevant here. The device's calculations are based on programmed variables and scientific formulas for BIA.

Ask a specific question about this device