Search Results

The Wrist Digital Blood Pressure Monitor (Model: BSX313, BSX315, BSX322, BSX323, BSX353, BSX355) is a digital and non-invasive monitor intended to measure the diastolic, systolic blood pressure and pulse rate in adult with an inflatable wrist cuff circumference ranging from 13.5 to 19.5cm. It is intended for clinical and home use.

The Wrist Digital Blood Pressure Monitor (Model: BSX312, BSX313, BSX315, BSX322, BSX323, BSX353, BSX355) is a digital and non-invasive monitor that uses the cuff oscillometric method to measure diastolic and systolic blood pressure and pulse rate. It has an LCD digital display, is powered by two "AAA" batteries, and uses automatic inflation with an electric pump and automatic rapid deflation valve.

The provided text describes the 510(k) submission for a Wrist Digital Blood Pressure Monitor. I will extract the information requested regarding acceptance criteria and the study that proves the device meets them.

Acceptance Criteria and Device Performance

A digital blood pressure monitor's primary acceptance criteria are its accuracy in measuring blood pressure and pulse rate. The relevant standard cited is ISO 81060-2: 2018 (Non-invasive sphygmomanometers - Part 2: Clinical validation of automated measurement type) for clinical performance, and specific accuracy values are mentioned.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size:
  • Enrolled: 130 subjects
  • Selected (met inclusion requirements): 85 subjects (44 males and 41 females)
• Data Provenance: The document does not explicitly state the country of origin. It describes a "validation study" which implies a prospective clinical study rather than retrospective. The study was conducted as part of the regulatory submission process for a device from Shenzhen, China, suggesting the study might have been conducted there or in a region that supports compliance with international standards.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not provide any information about the number or qualifications of experts used to establish ground truth for this device, nor does it mention experts in the context of ground truth for a blood pressure monitor. For blood pressure devices, ground truth is typically established by simultaneous readings from a reference manometer (mercury sphygmomanometer) as per ISO standards, not expert readers.

4. Adjudication method for the test set

The document does not describe any adjudication method. For blood pressure monitor validation studies by ISO 81060-2, adjudication by multiple readers is not typically part of the ground truth establishment process in the same way it would be for image interpretation tasks. The standard relies on simultaneous measurements by trained personnel using 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 MRMC comparative effectiveness study was done or is applicable here. This document pertains to a digital blood pressure monitor, which is a standalone measurement device, not an AI-assisted diagnostic tool that human readers would interact with.

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

Yes, a standalone performance evaluation was performed. The device itself, which performs blood pressure and pulse rate measurements using an algorithm, was clinically validated against a ground truth (established by trained observers using a reference method as per ISO 81060-2) without human intervention in the device's measurement process.

7. The type of ground truth used

The ground truth used was based on clinical validation as per ISO 81060-2: 2018. This standard specifies that simultaneous auscultatory measurements by trained observers using a mercury sphygmomanometer (or an equivalent reference standard) serve as the ground truth. The document states: "All data's mean error and standard deviation of differences for systolic, diastolic pressure is not over the limits of ISO 81060-2: 2018." This directly refers to the comparison of the device's readings against this established ground truth.

8. The sample size for the training set

The document does not mention a training set or any machine learning/AI training process. This device is a traditional oscillometric blood pressure monitor, not an AI/ML-based device that would require a separate training set.

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

As there is no mention of a training set for an AI/ML model, this question is not applicable.

Ask a specific question about this device

The IPL Hair Removal Device is an over-the-counter device intended for removal of unwanted body and or facial hair.

IPL Hair Removal Device (Model: BSXT101, BSXT102, BSXT103, BSXT105, BSXT106, BSXT108), is an over-the-counter, home-use and personal device for hair reduction by using Intense Pulsed Light (IPL). It works below the skin's surface and does not involve any cutting or pulling, reducing hair growth with minimal pain. The device is only powered by the external power adapter (a.c.100~240V 50/60Hz) and its IPL emission activation is by finger switch. It contains a skin sensor to detect appropriate skin contact, if the Light Outlet of the device is not in full contact with the skin, the device cannot trigger a light pulse. The device have six models and these models share the same performance, structure and operation, the only difference is their enclosure color.

The provided document does not contain information about specific acceptance criteria related to clinical performance metrics (e.g., hair reduction percentage, adverse event rates) or a detailed study demonstrating the device meets such criteria. Instead, it focuses on non-clinical studies for safety and functional equivalence to predicate devices.

Therefore, the following information cannot be extracted from the document:

• A table of acceptance criteria and the reported device performance regarding hair removal efficacy.
• Sample size used for a test set (clinical or performance efficacy).
• Data provenance for a clinical test set.
• Number of experts used to establish ground truth for a clinical test set and their qualifications.
• Adjudication method for a clinical test set.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done.
• If a standalone (algorithm only) performance study was done.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.) for a clinical study.
• The sample size for the training set (as no AI/algorithm performance study is described).
• How the ground truth for the training set was established.

However, the document does describe non-clinical studies conducted to demonstrate substantial equivalence, focusing on safety and technical performance.

Here's a summary of the non-clinical studies and their conclusions as presented:

Acceptance Criteria and Reported Device Performance (Non-Clinical):

The document states that non-clinical tests were conducted to verify that the IPL Hair Removal Device meets all design specifications and complies with various safety standards. While specific numerical acceptance criteria for each test are not explicitly detailed (e.g., current limits, specific temperature ranges), compliance with the listed standards serves as the acceptance criterion for these non-clinical aspects.

Study Details:

The non-clinical studies were conducted to support the conclusion of Substantial Equivalence (SE) to predicate devices. These are laboratory-based tests rather than clinical trials with human subjects for efficacy.

1. Sample size used for the test set and the data provenance: Not applicable in the context of clinical efficacy; these were non-clinical, laboratory-based tests on the device itself.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience): Not applicable, as ground truth in this context refers to compliance with established technical and safety standards, not clinical diagnoses or outcomes. The tests were performed by a "reliable third-party lab" for biocompatibility.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for non-clinical compliance testing.
4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: No.
5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: No (not an AI/algorithm device in this context).
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For non-clinical tests, the "ground truth" is adherence to the specifications and requirements set forth by the cited international and national standards (e.g., ISO, IEC, ANSI AAMI).
7. The sample size for the training set: Not applicable, as no AI/machine learning algorithm requiring a training set is described in relation to clinical efficacy.
8. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The Infrared forehead thermometer is a non-contact infrared thermometer (model BSX976) intended for the intermittent measurement of temperature from forehead at a distance of 1~3cm for people older than 2 years. The device is reusable for home use and clinical use and the safety of the device has not been established for use in neonates/infants.

BSX976 measures the body temperature through receiving the infrared energy radiation from the surface of objects. It is with forehead temperature mode, directly show on the LCD screen.

• The device is widely used for home healthcare, medical institutes, and many other occasions.
• The product is mainly composed with infrared temperature sensors, signal receiving processor, buttons, buzzer, LCD display, battery, etc.
• It focuses the infrared from the human's forehead by the Fresnel lens.

The provided document is a 510(k) summary for a non-contact infrared forehead thermometer (Model BSX976). It outlines the device's characteristics and its comparison to a predicate device to demonstrate substantial equivalence.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The device's performance is primarily assessed against recognized international standards for medical electrical equipment and clinical thermometers. The acceptance criteria are implicitly defined by compliance with these standards, particularly regarding accuracy and safety.

Table of Acceptance Criteria and Reported Device Performance

Study Details Proving Device Meets Acceptance Criteria

The document describes both non-clinical (bench) data and clinical data collected to demonstrate product performance.

1. Sample sizes used for the test set and data provenance:

   • Clinical Data (Test Set): 150 subjects were involved in the clinical testing. 32 of these subjects were febrile.
   • Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective. Given the submitter's location (Shenzhen, China) and the nature of a 510(k) submission, it is highly probable the clinical study was conducted prospectively, but this is not explicitly confirmed.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The document does not provide details on the number or qualifications of experts used to establish ground truth for the clinical test set. The clinical testing was conducted "per ISO 80601-2-56 Clause 201.102," which is a standard for clinical thermometers. This standard itself outlines methods for clinical evaluation, including comparison to reference thermometers, but the specific details of the human expertise involved in the ground truth establishment for this specific study are not described in the provided summary.

3. Adjudication method for the test set:

   • The document does not specify an adjudication method. For a clinical thermometer study, ground truth is typically established by simultaneous measurement with a highly accurate reference thermometer (e.g., a rectal thermometer) under controlled conditions, rather than by human adjudication of readings.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and its effect size of how much human readers improve with AI vs without AI assistance:

   • No. This is a review of a basic medical device (a thermometer), not an AI-assisted diagnostic imaging device. Therefore, an MRMC study with human readers and AI assistance is not relevant and was not performed.

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

   • Yes, indirectly. The "Clinical data" and "Bench Testing" sections describe the device's performance in isolation. The compliance with ISO 80601-2-56 and ASTM E 1965-98 specifically evaluates the thermometer's direct measurement accuracy, which is its standalone performance. This device is not an algorithm in the sense of AI; it is a physical device that performs a measurement.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The ground truth for the clinical data (temperature measurement) is established by comparison to a reference temperature measurement method as defined by the standard ISO 80601-2-56. This standard typically involves using a highly accurate alternative method (e.g., a calibrated contact thermometer, such as a rectal or oral thermometer, serving as the "true" body temperature) against which the infrared thermometer's readings are compared. The summary does not explicitly state the exact reference method used, but compliance with the standard implies such a comparison.

7. The sample size for the training set:

   • This device is a physical thermometer, not a traditional machine learning model that undergoes a "training set" process in the AI sense. Therefore, there is no specific training set sample size as would be described for an AI/ML algorithm. Its "training" is in its design, calibration, and manufacturing processes, guided by engineering principles and adherence to standards.

8. How the ground truth for the training set was established:

   • As there is no "training set" in the AI/ML context, this question is not applicable. The device's calibration and design are based on established physics principles of infrared thermometry and validated against recognized metrology standards for temperature measurement.

Ask a specific question about this device

The Fingertip Pulse Oximeter is intended for spot-checking oxygen saturation and pulse rate, and the device is a reusable device and intended to be used with the finger of adults or children over three years old in healthcare environments. And it is not intended to be used under motion or low perfusion scenarios.

The oximeter consists of probe, electronic circuits, and display and plastic enclosures. And one side of probe is designed to locate light emitting diodes and a light detector (called a photo-detector). Red and Infrared lights are shone through the tissues from one side of the probe to the other. Then parts of the light emitted absorbed by blood and tissues. The light absorbed by the blood varies with the oxygen saturation of haemoglobin. After that, the photo-detector detects the light volume transmitted through the tissues which depends on blood pulse, Hereafter, the microprocessor calculates a value for the oxygen saturation (SpO2). The subject device is a reusable device, and need to reprocess as suggested in the user manual after each use. And the device is intended to be used on the finger, and powered by 2*1.5V AAA battery. The differences between different models only includes the color of the non-patient contacting shell part and the size. And the color display screen of BSX221/BSX223/BSX261/BSX263/BSX281/BSX283 is OLED, while that of BSX231/BSX233/BSX251/BSX253 is TFT.

The provided document describes the K202324 submission for "Fingertip Pulse Oximeter, Models BSX221, BSX223, BSX261, BSX263, BSX281, BSX283, BSX231, BSX233, BSX251, BSX253." The acceptance criteria and the study proving the device meets these criteria are detailed in the "510(k) Summary" section, particularly under "7. Predicate Device Comparison" and "8. Performance Testing."

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The regulatory document outlines the performance specifications, which serve as the acceptance criteria, and the reported performance of the proposed device.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document states that "Clinical testing is conducted per Annex EE Guideline for evaluating and documenting SpO2 ACCURACY in human subjects of ISO 80601-2-61:2011 Medical electrical equipment - Part 2-61: Particular requirements for basic safety and essential performance of pulse oximeter equipment."

However, the specific sample size (number of subjects/patients) used for this clinical test set, or the data provenance (country of origin, retrospective/prospective nature), is not explicitly mentioned in the provided 510(k) summary. ISO 80601-2-61:2011 Annex EE typically outlines requirements for such studies, including participant numbers, but the summary does not detail the results of the specific study performed.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

For pulse oximetry, the ground truth for SpO2 accuracy is typically established using a co-oximeter and arterial blood samples in a controlled desaturation study. This process usually does not involve "experts" establishing a subjective ground truth in the same way as, for example, image interpretation. Instead, it relies on objective laboratory measurements.

The document does not explicitly state the number or qualifications of "experts" involved in establishing the ground truth for the clinical accuracy testing, as the ground truth itself is derived from reference measurements (co-oximetry).

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The concept of an "adjudication method" (like 2+1 or 3+1) is typically relevant for studies where subjective interpretation is involved, such as reading medical images, and disagreements between multiple human readers need to be resolved to establish ground truth.

For a pulse oximeter's clinical accuracy study (desaturation study), the ground truth for SpO2 values is established by a reference co-oximeter and arterial blood gas analysis, which is an objective measurement without subjective interpretation or the need for adjudication among multiple human experts. Therefore, adjudication methods are not applicable in this context and are not mentioned.

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 device is a Fingertip Pulse Oximeter, a standalone measurement device, not an AI-assisted diagnostic tool that would involve human readers interpreting results. Therefore, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study is not relevant to this type of device and was not performed. The submission does not mention AI assistance or human reader improvement.

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

Yes, the primary performance evaluation for a pulse oximeter is based on its standalone (algorithm only) performance. The device directly measures and displays SpO2 and pulse rate. The "Clinical data" section explicitly states that "Clinical testing is conducted per Annex EE Guideline for evaluating and documenting SpO2 ACCURACY in human subjects of ISO 80601-2-61:2011," which refers to a desaturation study where the device's readings are compared against a co-oximeter, without human intervention in the device's measurement process.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

For the clinical accuracy testing mentioned, the ground truth for oxygen saturation (SpO2) and pulse rate would be established using reference medical devices and laboratory analyses. Specifically, for SpO2 accuracy, this involves:

• Co-oximetry: Measuring arterial oxygen saturation (SaO2) from arterial blood samples using a laboratory co-oximeter.
• Arterial blood gas analysis: Providing other relevant blood gas parameters.
  This is considered the gold standard for determining SpO2 accuracy in human subjects.

8. The sample size for the training set

The document does not mention the use of machine learning or AI models that would require a "training set" in the context of device development. The pulse oximeter operates based on established physical principles of light absorption by hemoglobin. Therefore, there is no mention of a training set in this 510(k) summary.

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

As there is no mention of a training set for this device, the question of how its ground truth was established is not applicable.

Ask a specific question about this device

The blood pressure monitor is a non-invasive blood pressure measurement system intended to measure the diastolic and systolic blood pressures and pulse rate of an adult individual by using a non-invasive oscillometric technique in which an inflatable CUFF is wrapped around the arm of which the circumference includes 22 cm-32 cm. It is intended to be used in hospital environment or at home.

The Arm-type Electronic Blood Pressure Monitor is a battery powered automatic non-invasive blood pressure monitor, of which BSX516, BSX525, BSX583, BSX593 and BSX595 are powered by 4x1.5V AAA Alkaline Battery, and BSX523 is powered by 3.7V 400mAh Li-ion Battery. It can automatically complete the inflation, deflation and measurement, which can measure systolic and diastolic blood pressure and pulse rate of the adult person at upper arm within its claimed range and accuracy via the oscillometric technique. User can select the unit of the measurement: mmHg or kPa. The difference between the six models include the battery type and the backlight indicator. BSX516, BSX525, BSX583, BSX593 and BSX595 are powered by 4x1.5V AAA Alkaline Battery, while BSX523 is powered by 3.7V 400mAh Li-ion Battery. Moreover, the subject device is equipped with backlight indicator except models BSX516 and BSX525. The device has the data storage function in order for data reviewing, including the systolic pressure, diastolic pressure, pulse rate and measurement time. The proposed Arm-type Electronic Blood Pressure Monitor share the similar software, measurement principle and NIBP algorithm. The proposed device is intended to be used in medical facilities or at home. And the effectiveness of this sphygmomanometer has not been established in pregnant (including pre-eclamptic) patients. The product is provided non-sterile, and not to be sterilized by the user prior to use.

The provided text describes the 510(k) premarket notification for an Arm-type Electronic Blood Pressure Monitor (K183058) from Shenzhen BSX Technology Electronics Co., Ltd. Here's an analysis of the acceptance criteria and study that proves the device meets them, based on the provided document:

1. Table of acceptance criteria and the reported device performance

The document references compliance with several international standards which inherently contain acceptance criteria for the respective tests. However, it does not explicitly present a table detailing specific numerical acceptance criteria and the device's reported performance against each. Instead, it states that "all testing passed pre-specified criteria."

The most directly comparable performance criteria mentioned are related to accuracy, in comparison to the predicate device:

Note: While the proposed device's measurement ranges differ, the document concludes that these are "minor differences, which do not raise different questions of safety or effectiveness," implying they still meet acceptable performance for the intended use. The critical accuracy metrics (static pressure and pulse) are identical to the predicate device.

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

• Test Set Sample Size: The document states that "Clinical testing is conducted per ISO 81060-2: 2013 Non-invasive sphygmomanometers - Part 2: Clinical validation of automated measurement type." This standard specifies requirements for the number of subjects (typically a minimum of 85 subjects with specific demographic distribution) for clinical validation of automated non-invasive sphygmomanometers. While the exact number of subjects tested for this specific submission is not explicitly stated, the reference to the standard implies adherence to its sample size requirements.
• Data Provenance: The document does not explicitly state the country of origin of the data or whether the study was retrospective or prospective. Given that this is a 510(k) submission for a medical device by a Chinese company (Shenzhen BSX Technology Electronics Co., Ltd.), it is highly probable that the data originated from studies conducted in China. Clinical validation studies according to ISO 81060-2 are typically prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not provide details on the number or qualifications of experts used to establish ground truth for the clinical test set. For a blood pressure monitor, ground truth is typically established by simultaneous auscultatory measurements performed by trained and certified observers according to specific protocols (e.g., those outlined in ISO 81060-2).

4. Adjudication method for the test set

The document does not explicitly mention the adjudication method. However, for a clinical validation study of an automated sphygmomanometer according to ISO 81060-2, the ground truth is established by simultaneous auscultatory measurements, typically by two independent observers blinded to each other's readings and ideally to the automated device's readings. If there's a discrepancy, a third observer might be involved, or a pre-defined adjudication process would be followed, but these specifics are not detailed in the provided text.

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 section is not applicable to the described device. The device is an "Arm-type Electronic Blood Pressure Monitor," which is an automated measurement system, not an AI-assisted diagnostic imaging or interpretation tool that would involve human readers. Therefore, an MRMC study and analysis of human reader improvement with AI assistance are not relevant to this type of device.

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

This section is applicable and describes the primary performance evaluation. The device is a standalone automated blood pressure monitor. Its performance, as evaluated against the ISO 81060-2 standard, inherently assesses the algorithm's (and the device's overall system's) ability to accurately measure blood pressure without human intervention other than proper placement and initiation of the measurement. The clinical data section confirms this: "Clinical testing is conducted per ISO 81060-2: 2013 Non-invasive sphygmomanometers - Part 2: Clinical validation of automated measurement type."

7. The type of ground truth used

For the clinical validation, the ground truth for blood pressure measurements is established through simultaneous auscultatory measurements performed by trained observers, as specified by the ISO 81060-2 standard. This is the universally accepted reference method for validating automated blood pressure monitors.

8. The sample size for the training set

This information is not provided. The document focuses on regulatory submission requirements for safety and effectiveness, not on the developmental aspects of the device's algorithm, which would involve a training set. For an oscillometric blood pressure monitor, the "training set" would refer to the data used to develop and refine the proprietary oscillometric algorithm. This data is part of the manufacturer's internal development process and is typically not disclosed in a 510(k) summary, which focuses on validation.

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

This information is not provided. Similar to the training set sample size, the specifics of algorithm development and the establishment of ground truth for that process are proprietary and not typically included in a public 510(k) summary. It would involve a similar process of comparing oscillometric waveforms to simultaneously obtained auscultatory or invasive blood pressure readings in a large and diverse patient population to train and validate the algorithm.

Ask a specific question about this device