Search Results

KD-721 and KD-723 Fully Automatic Electronic Blood Pressure Monitor is for use by medical professionals or at home and 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 technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 14cm-25cm.

KD-721 and KD-723 Fully Automatic Electronic Blood Pressure Monitor is designed and manufactured according to IEC 80601-2-30.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. It can calculate the systolic and diastolic blood pressure, and display the result on the LCD. The measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user.

The provided text describes the acceptance criteria and the study for the KD-721 and KD-723 Fully Automatic Electronic Blood Pressure Monitor.

1. Table of Acceptance Criteria and Reported Device Performance:

The document refers to compliance with particular standards, which implicitly define the acceptance criteria for certain performance aspects. The device characteristics are compared to those of a predicate device (iHealth View BP7S Wireless Blood Pressure Wrist Monitor, K152379) and a previous device (KD-972, K121470).

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

The document states that the clinical test report of KD-972 (cleared in 2012 as K121470) was used for evaluating KD-721/723. This implies retrospective use of clinical data.
The document states that KD-972 conformed to ANSI/AAMI/ISO 81060-2:2009 & 2013. These standards typically outline the requirements for clinical validation studies for automated sphygmomanometers, which involve a specific number of subjects. However, the exact sample size for the test set is not explicitly stated in the provided text. The data provenance is not specified beyond being from a previous device's clinical trial conforming to international standards (ANSI/AAMI/ISO 81060-2), which generally requires multi-center data from diverse populations.

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

The document does not specify the number or qualifications of experts used to establish the ground truth for the test set. Clinical validation studies for blood pressure monitors generally involve trained observers (often medical professionals) to perform reference measurements.

4. Adjudication method for the test set:

The document does not specify the adjudication method used for the test set.

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 fully automatic electronic blood pressure monitor, not an AI-assisted diagnostic tool that involves human readers interpreting output. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not applicable and was not done.

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

Yes, a standalone performance evaluation was done through the reference to the KD-972 clinical test report, which conformed to ANSI/AAMI/ISO 81060-2:2009 & 2013. This standard specifically outlines the requirements for evaluating the accuracy of automated sphygmomanometers, which inherently tests the algorithm's performance in measuring blood pressure values.

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

The ground truth for blood pressure monitors in clinical validation studies conforming to ANSI/AAMI/ISO 81060-2 is typically established through auscultatory measurements performed by trained observers using a mercury sphygmomanometer or an equivalent reference device, often in a double-blinded protocol to minimize bias. This is a form of expert reference measurement.

8. The sample size for the training set:

The document states that the algorithm version (BPM-WAU V2.0-201109) is the same for KD-721/723 and the previously cleared KD-972. This implies that the algorithm was trained prior to the KD-972 clearance (K121470 in 2012). The sample size for the training set is not provided in this document, as the focus is on the clinical validation of the device using an existing algorithm.

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

Given that the algorithm is based on "oscillometric and silicon integrates pressure sensor technology" and is a "fully automatic" device, the ground truth for its original training would have been established through a combination of simulated data and clinical data where reference blood pressure measurements (e.g., auscultatory method by trained experts) were used to optimize the algorithm's performance in detecting systolic, diastolic, and pulse rate. The specific details of the training data and ground truth establishment are not provided in this document.

Ask a specific question about this device

KD-926 Fully Automatic Electronic Blood Pressure Monitor is for use by medical professionals or at home and 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

KD-926 Fully Automatic Electronic Blood Pressure Monitor is designed and manufactured according to IEC 80601-2-30.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. It can calculate the systolic and diastolic blood pressure, and display the result on the LCD. The measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user.

Here's an analysis of the provided text regarding the acceptance criteria and study for the KD-926 Fully Automatic Electronic Blood Pressure Monitor:

No specific acceptance criteria or performance numbers are explicitly stated in the provided document. The document primarily focuses on the substantial equivalence argument, referencing standards and prior clearances.

However, based on the mentioned standards (IEC 80601-2-30), we can infer the implied performance criteria that the device must meet to conform to these standards.

Inferred Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria:

Given the nature of the submission (510(k) for a blood pressure monitor) and the referenced standards, the primary acceptance criteria would revolve around the accuracy of blood pressure and pulse rate measurements.

1. A table of acceptance criteria and the reported device performance

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

The document states: "The cuff and algorithm of KD-926 is the same as K102939 and K120672, so we use the clinical data of K102939 and K120672 as the clinical proof of the new device."

• Sample Size: The sample size for the clinical data used for K102939 and K120672 is not specified in the provided document.
• Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only indicates that "clinical data of K102939 and K120672" were used.

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

This information is not provided in the document. For blood pressure clinical trials, ground truth is typically established by trained observers using mercury sphygmomanometers as per recognized protocols (e.g., ANSI/AAMI/ISO 81060-2). The number and qualifications of these observers are not detailed here.

4. Adjudication method for the test set

This information is not provided in the document. For blood pressure clinical trials, multiple observers may be used, and their readings are often averaged or assessed for agreement, but the specific adjudication method is missing.

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, an MRMC comparative effectiveness study was not done. This device is a standalone blood pressure monitor, not an AI-assisted diagnostic tool for interpretation by human readers. Therefore, the concept of "human readers improve with AI vs without AI assistance" is not applicable here.

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

• Yes, a standalone (algorithm only) performance assessment was done. The clinical proof relies on the accuracy of the device itself (the "cuff and algorithm") against a reference standard, without human interpretation in the loop beyond initial application and reading of the reference. The device directly outputs blood pressure and pulse rate measurements.

7. The type of ground truth used

The type of ground truth used for validating blood pressure monitors is typically simultaneous measurements by trained observers using a reference standard device, such as a mercury sphygmomanometer or another validated oscillometric device, following an established protocol. While not explicitly stated, this is standard practice for devices conforming to IEC 80601-2-30.

8. The sample size for the training set

• Not applicable / Information not provided. As a standalone medical device measuring physiological parameters, it's unlikely to have a "training set" in the machine learning sense for the device's core function. The device's algorithm development involves calibration and validation against established physiological principles and clinical data, but not typically a "training set" for an AI model interpreting images or signals. The clinical data referenced (K102939 and K120672) serves as the validation/test set for the algorithm's accuracy.

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

• Not applicable / Information not provided. See the explanation for point 8.

Ask a specific question about this device

The BPM1 (Electronic Sphygmomanometer) is intended for use in a professional setting or at home and is a non-invasive blood pressure measurement system. It is designed to measure the systolic blood pressures and pulse rate of an adult individual by using a technique in which an inflatable cuff is wrapped around the upper arm. The measurement range of the cuff circumference is 8.6" to 18.9" (22cm-48cm)

iHealth BPM1 Wireless Blood Pressure Monitor is designed and manufactured according to IEC 80601-2-30. The operational principle is based on oscillometric and silicon integrates pressure sensor technology. It can calculate the systolic and diastolic blood pressure, the measurements results can also be classified by the function of blood pressure classification indicator. If any irreqular heartbeat is detected, it can be shown to the user. The new devices can connect to iOS or Andriod devices to show the results.

The provided text describes the iHealth Wireless Blood Pressure Monitor (BPM1) and its submission for 510(k) clearance. The document focuses on demonstrating substantial equivalence to predicate devices rather than providing a detailed study of its performance against specific acceptance criteria.

However, based on the information provided, we can infer some aspects relevant to acceptance criteria and the "study" that proves the device meets them, largely through adherence to international standards and comparison to predicate devices.

Acceptance Criteria and Reported Device Performance

Study Details:

The document describes pre-market notification (510(k)) and focuses on demonstrating substantial equivalence rather than a new standalone clinical study for accuracy.

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

   • The document states: "Clinical data have been transferred from the predicates."
   • This implies that no new clinical test set was used for the BPM1 specifically for primary accuracy evaluation. Instead, the clinical data and performance of the predicate devices (Andon Health Co., Ltd. KD-927, K141984, KD-936, K120672, and KD-931, K102939) are relied upon.
   • The provenance of the original clinical data for the predicate devices is not specified (e.g., country of origin, retrospective or prospective).

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

   • Since clinical data were "transferred from the predicates," this information would pertain to the original studies for the predicate devices. This detail is not provided in the current document. Typically, accuracy studies for blood pressure monitors involve simultaneous measurements by trained observers (experts) using a reference method (e.g., mercury sphygmomanometer) and the device under test.

3. Adjudication method for the test set:

   • As clinical data were transferred, the adjudication method (if any) used for the predicate device studies is not described in this document. Standard blood pressure monitor accuracy studies often involve multiple observers performing auscultation and comparing their readings to ensure consensus or inter-observer reliability in establishing ground truth.

4. 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, an MRMC comparative effectiveness study was not done. This device is a blood pressure monitor, which does not involve "human readers" interpreting images or data with or without "AI assistance" in the typical sense of MRMC studies. Its function is to provide direct measurements.

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

   • Yes, in essence, standalone performance was evaluated by adherence to IEC 80601-2-30. This standard specifically defines requirements for automated noninvasive sphygmomanometers, meaning the device's accuracy in measuring blood pressure is assessed independently of human interpretation of the measurement process itself. The device operates automatically to produce a reading.
   • The document mentions "Non-clinical Tests have been done as follows: ... c. Safety and performance characteristics of the test according to IEC 80601-2-30". This demonstrates standalone performance against established international standards.

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

   • For blood pressure monitors, the ground truth is typically established by simultaneous measurements by trained human observers using a validated reference method, such as a mercury sphygmomanometer, often following protocols like those outlined by the Association for the Advancement of Medical Instrumentation (AAMI) or the British Hypertension Society (BHS). This would be a form of expert reference measurement. As clinical data were transferred, this ground truth method would have been used for the predicate devices.

7. The sample size for the training set:

   • The document implies that the device's development and validation primarily relied on its similarity to predicate devices and adherence to standards. It does not explicitly mention a "training set" in the context of machine learning (AI) for this specific device's accuracy. The device uses an oscillometric principle, which is a well-established algorithm. Therefore, there isn't a "training set" in the typical AI sense to teach the device to measure blood pressure. The underlying algorithms are developed and refined based on extensive physiological and engineering data, but not a "training set" as one might see for image classification AI.

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

   • As there isn't a "training set" described for this device in the AI sense, this question is not directly applicable. The "ground truth" for the oscillometric method's development (which is the core of the device's function) would have been established through extensive research comparing oscillometric waveforms to directly measured intra-arterial pressures or auscultation by experts.

Ask a specific question about this device

The iHealth Align Gluco-Monitoring System consists of the iHealth Align Glucose meter (BG1), iHealth Blood Glucose Test Strips (AGS-1000), and the iHealth Gluco-Smart App mobile application as the display component of the iHealth Align Gluco-Monitoring System. The iHealth Align Gluco-Monitoring System is intended to be used for the quantitative measurement of glucose (sugar) in fresh capillary whole blood samples drawn from the fingertip, palm, forearm, upper arm, calf, or thigh. The iHealth Alian Gluco-Monitoring System is intended to be used by a single person and should not be shared.

The iHealth Align Gluco-Monitoring System is intended for self testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The iHealth Align Gluco-Monitoring System should not be used for the diagnosis of or screening of diabetes or for neonatal use. Alternative site testing should be done only during steady - state times (when glucose is not changing rapidly).

The iHealth BG5 wireless Smart Gluco-Monitoring System is intended to be used for the quantitative measurement of glucose (sugar) in fresh capillary whole blood samples drawn from the fingertip, palm, forearm, upper arm, calf or thigh. The iHealth BG5 wireless Smart Gluco-Monitoring System is intended to be used by a single person and should not be shared.

The iHealth BG5 wireless Smart Gluco-Monitoring System is intended for self testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The iHealth BG5 wireless Smart Gluco-Monitoring System should not be used for the diagnosis of or screening of diabetes or for neonatal use. Alternative site testing should be done only during steady state times (when glucose is not changing rapidly).

The AGS-1000I test strips are for use with the iHealth BG5 meter to quantitatively measure glucose (sugar) in fresh capillary whole blood samples drawn from the fingertips, palm, forearm, upper arm, calf or thigh.

The iHealth BG5L wireless Smart Gluco-Monitoring System is intended to be used for the quantitative measurement of glucose (sugar) in fresh capillary whole blood samples drawn from the fingertip, palm, forearm, upper arm, calf or thigh. The iHealth BG5L wireless Smart Gluco-Monitoring System is intended to be used by a single person and should not be shared.

The iHealth BG5L wireless Smart Gluco-Monitoring System is intended for self testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The iHealth BG5L wireless Smart Gluco-Monitoring System should not be used for the diagnosis of or screening of diabetes or for neonatal use. Alternative site testing should be done only during steady state times (when glucose is not changing rapidly).

The AGS-1000I test strips are for use with the iHealth BG5L meter to quantitatively measure glucose (sugar) in fresh capillary whole blood samples drawn from the fingertips, palm, forearm, upper arm, calf or thigh.

The iHealth Align Gluco-Monitoring System consists of a blood glucose meter, test strips, iHealth Gluco-Smart App, sterile lancets, lancing device and AGS-1000I Control Solutions (Level I. Level II and Level III). The iHealth Align Gluco-Monitoring System cannot display test results and must be used with an iPhone or iPod touch via an 3.5 mm auxiliary jack.

The iHealth BG5 wireless Smart and iHealth BG5L wireless Smart Gluco-Monitoring Systems consist of the BG5 and BG5L wireless Smart blood glucose meters, respectively, AGS-10001 Test Strips , sterile lancets, lancing device and the iHealth control solutions control solutions. (Control solutions provided are for Level 1, II, and III). iHealth BG5L uses Bluetooth 4.0 wireless radio technology; while iHealth BG5 uses Bluetooth 3.0 wireless radio technology. The iHealth BG5 and BG5L meters can display the test results and the test results can also be transmitted to an iPhone, iPod touch or iPad through blue tooth.

iHealth Gluco-Smart App is iOS- based software for use with the iHealth Align Glucose meter (BG1), iHealth BG5 meter, and iHealth BG5L meter. When used with these meters, iHealth Gluco-Smart App acts as a display and allows command and control of the meter. The App can transfer data from the device's memory, manage, and share the data.

Here's an analysis of the provided text, focusing on acceptance criteria and study details for the iHealth Gluco-Monitoring Systems:

The provided documents are a 510(k) premarket notification for the iHealth Align Gluco-Monitoring System, iHealth BG5 wireless Smart Gluco-Monitoring System, and iHealth BG5L wireless Smart Gluco-Monitoring System. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than undergoing extensive clinical trials typical of novel devices. Therefore, the "acceptance criteria" and "study" described are primarily focused on proving that the new devices perform comparably to the predicate device and meet relevant regulatory standards for glucose monitoring systems.

1. Table of Acceptance Criteria and Reported Device Performance

The documents do not explicitly state a table of "acceptance criteria" in the format of specific thresholds for metrics like sensitivity, specificity, or accuracy (e.g., within X% of a reference standard for Z% of readings). Instead, the acceptance criteria are implicitly tied to the performance characteristics of the predicate device and general regulatory expectations for glucose monitoring systems.

The performance is primarily summarized by stating that the new devices share key characteristics with the predicate and that "Software validation and user study has been performed to establish the performance, the functionality and the reliability characteristics of the new device."

Here's an attempt to infer and present the information in a table format based on the textual evidence:

2. Sample Size for the Test Set and Data Provenance

The document mentions "user study" but does not specify the sample size for any clinical or test set. It also does not explicitly state the country of origin of the data or whether it was retrospective or prospective. Given the nature of a 510(k) for a glucose monitoring system, user studies often involve a diverse cohort to assess performance across various glucose levels and user demographics. However, these specific details are absent from the provided text.

3. Number of Experts Used to Establish Ground Truth and Qualifications

The document does not mention the use of experts to establish ground truth for a test set. For glucose monitoring systems, "ground truth" is typically established by comparing the device's readings against a highly accurate laboratory reference method (e.g., YSI glucose analyzer), rather than expert adjudication of images or clinical reports. The general term "user study" is used, which implies participants used the device and its performance was evaluated against a reference.

4. Adjudication Method for the Test Set

As the document does not describe a process involving experts to establish ground truth for a test set in the traditional sense, there is no mention of an adjudication method like 2+1 or 3+1. Performance is likely assessed against a laboratory reference.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No. The provided text does not describe an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. This type of study is more common in diagnostic imaging or clinical decision support AI devices where human interpretation is a key component. The iHealth devices are standalone glucose meters; while an app is involved, it primarily acts as a display and data management tool, not an AI for interpretation.

6. Standalone (Algorithm Only) Performance Study

Yes, implicitly. The core performance of the glucose measurement algorithm itself (i.e., the meter and test strip system) is evaluated. The 510(k) process for glucose meters typically requires studies demonstrating the accuracy of the device's readings against a laboratory reference method. Although the document uses the broad term "performance summary," this usually entails standalone accuracy data. The phrase "Software validation and user study has been performed to establish the performance, the functionality and the reliability characteristics of the new device" suggests that the device's ability to accurately measure glucose without a human in the interpretative loop was a key part of the validation.

7. Type of Ground Truth Used

The document does not explicitly state the type of ground truth used. However, for glucose monitoring systems, the ground truth is almost universally established using a laboratory reference method (e.g., a YSI glucose analyzer) that is considered the gold standard for glucose measurement.

8. Sample Size for the Training Set

The document does not mention a "training set" sample size. This is expected because the iHealth Gluco-Monitoring Systems, as described, do not appear to be AI/Machine Learning devices that require a "training set" in the context of learning algorithms. They are likely electrochemical biosensors with pre-defined algorithms for glucose calculation. The app primarily handles data display and management.

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

As there is no mention of a training set, there is no information on how its ground truth was established. The device likely relies on established physical and chemical principles of glucose measurement rather than a trained AI model.

Ask a specific question about this device

iHealth BP3L Wireless Blood Pressure Monitor is for use by medical professionals or at home and 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

iHealth BP3L Wireless Blood Pressure Monitors are designed and manufactured according to IEC 80601-2-30.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. it can calculate the systolic and diastolic blood pressure, the measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user. The new devices achieves its function by an iOS or Andriod devices.

The provided document describes the iHealth BP3L Wireless Blood Pressure Monitor and its premarket notification to the FDA. The relevant information for acceptance criteria and the study proving the device meets them is scattered across several sections.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document primarily references the predicate device's (BP3, K102939) specifications as benchmarks for the subject device (BP3L). The key acceptance criteria for blood pressure monitors generally stem from standards like ISO 80601-2-30, which the device conforms to according to section 9.0.

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

The document does not explicitly state the sample size used for the clinical test set or the data provenance (e.g., country of origin, retrospective/prospective). It only mentions "Non-clinical and clinical test performed" and "The test in this submission provides demonstrates that these small differences do not raise any new questions of safety and effectiveness." (Paragraph 8.0, 10.0).

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

This information is not provided in the document.

4. Adjudication Method

This information is not provided in the document.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

A multi-reader multi-case (MRMC) comparative effectiveness study was not done based on the document. The document describes a substantial equivalence submission to the FDA, focusing on comparing the new device (BP3L) to its predicate device (BP3) and adherence to safety standards. It does not mention any studies involving human readers or AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

A standalone performance study focused on the algorithm only, without human-in-the-loop performance, was implicitly done as part of the "Safety and performance characteristics of the test according to IEC 80601-2-30" (Paragraph 8.0). This standard would assess the device's accuracy in measuring blood pressure values independently. The accuracy figures provided ($\pm 3$ mmHg for pressure, $\pm 5%$ for pulse) are measures of the device's standalone performance.

7. Type of Ground Truth Used

The ground truth for blood pressure monitors typically involves reference measurements from a calibrated clinical device (e.g., a mercury sphygmomanometer or another validated oscillometric device) taken concurrently by trained clinical professionals. While not explicitly stated as "ground truth," the testing against standards like ISO 80601-2-30 implies comparison to such reference methods.

8. Sample Size for the Training Set

The document does not provide information on a training set sample size. This type of device (blood pressure monitor) is typically calibrated and validated through engineering tests and clinical studies (test sets) rather than deep learning-style training sets.

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

As no training set is described for this type of device, the method for establishing its ground truth is not applicable and therefore not provided in the document.

Ask a specific question about this device

iHealth View BP7S Wireless Blood Pressure Wrist Monitor is for use by medical professionals or at home and is a noninvasive blood pressure measurement system intended to measure the diastolic blood pressures and pulse rate of an adult individual by using a non-invasive technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 13.5cm-22cm.

iHealth View BP7S Wireless Blood Pressure Monitors are designed and manufactured according to IEC 80601-2-30. The operational principle is based on oscillometric and silicon integrates pressure sensor technology. it can calculate the systolic and diastolic blood pressure, the measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user. The new devices achieves its function by an iOS or Andriod devices.

The provided document is a 510(k) summary for a medical device called the "iHealth View Wireless Blood Pressure Wrist Monitor (BP7S)". It primarily focuses on demonstrating substantial equivalence to a predicate device, rather than detailing a specific study proving the device meets acceptance criteria. As such, information on specific acceptance criteria and a study to prove them is limited.

However, I can extract the available information related to performance and testing:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present acceptance criteria in a tabular format alongside device performance for a specific study. Instead, it refers to performance standards that the device conforms to. The closest information is under "Accuracy" in the technological characteristics comparison table.

2. Sample Size and Data Provenance for Test Set

The document does not specify a sample size for a test set or the data provenance (country of origin, retrospective/prospective). The non-clinical tests mentioned are adherence to electrical safety and electromagnetic compatibility standards, and performance characteristics according to a blood pressure monitor standard. These are general compliance tests for the device, not a specific clinical performance study with a test set of patient data.

3. Number and Qualifications of Experts for Ground Truth

Not applicable. The document does not describe a study involving expert-established ground truth for a test set. The tests mentioned are compliance tests against established engineering and medical device standards.

4. Adjudication Method for Test Set

Not applicable. There is no mention of a test set requiring adjudication in the provided text.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No. The document makes no mention of an MRMC comparative effectiveness study, nor does it discuss human reader improvement with or without AI assistance. This device is a standalone blood pressure monitor, not an AI-assisted diagnostic tool for human readers.

6. Standalone Performance Study

Yes, implicitly. The "Non-clinical Tests" and "Performance summary" sections indicate that the device's performance was evaluated against recognized standards (IEC 80601-2-30 for "Safety and performance characteristics"). While not a dedicated "standalone performance study" in the context of AI algorithms, these tests assess the device's functionality and accuracy independently.

7. Type of Ground Truth Used

The ground truth for the device's accuracy claims (pressure $\pm$ 3mmHg, pulse $\pm$ 5%) would typically be based on reference measurements from a validated, calibrated standard or method, as outlined in the IEC 80601-2-30 standard for automated sphygmomanometers. This standard specifies clinical investigation requirements for blood pressure device accuracy. The document states the device "conforms to" this standard, implying that the ground truth methodology prescribed by the standard was followed for these accuracy claims.

8. Sample Size for Training Set

Not applicable. This device is a traditional medical device (blood pressure monitor) governed by engineering and performance standards, not an AI/machine learning algorithm requiring a "training set" in the computational sense.

9. How Ground Truth for Training Set Was Established

Not applicable, as there is no training set for this device.

Ask a specific question about this device

The AD-2129A TENS device is intended for temporary relief of pain associated with sore and aching muscles due to strain from exercise or normal household and work activities. It is also intended for symptomatic relief and management of chronic, intractable pain and relief of pain associated with arthritis.

The AD-2129A Transcutaneous Electrical Nerve Stimulator(TENS) is transcutaneous electrical nerve stimulator for relief of muscular pain and sold without prescription. The device consists of a microprocessor, buttons, electrical pads, and display. Keys can control the device to choose the operation modes, adjust pulse output strength, then the channel that effectively transfers your desired choice of programmed electrical pulses directly through electrode adhesive pads to the suggested area of the body where the electrodes are placed, causing minimal muscle stimulation. The LCD display can show user the mode and strength chosen and other information like date and time Self-adhesive electrodes are used in this devices, and they are intended for use as the disposable, conductive adhesive interface between the patient's skin and the Electrical Stimulator. The electrodes is for OTC use, and mainly consists of substrate and wire.

The provided document is a 510(k) Premarket Notification for a Transcutaneous Electrical Nerve Stimulator (TENS) device, AD-2129A. It focuses on demonstrating substantial equivalence to predicate devices, rather than establishing de novo acceptance criteria and proving performance against them through a clinical study.

Therefore, the document does not report on acceptance criteria or a study designed to prove the device meets these criteria in the way one would for a novel AI/ML medical device or a device requiring clinical performance validation against specific metrics.

Instead, the document details:

• Regulatory Substantial Equivalence: The primary goal is to show that the AD-2129A TENS device is substantially equivalent to legally marketed predicate TENS devices (Smart Relief K131159 and EasyStim TN28_OTC K140168).
• Safety and Performance to Standards: The "Performance Summary" and "Non-clinical Testing Summary" sections confirm that the device conforms to relevant electrical safety, electromagnetic compatibility (EMC), and biocompatibility standards (e.g., IEC 60601-1, IEC 60601-2-10, IEC 60601-1-2, ISO 10993). These are general safety and performance standards for the device type, not specific outcome-based acceptance criteria for a novel technology.
• Comparison Table: A detailed comparison table highlights similarities and differences between the subject device and the predicates regarding product name, regulatory information, intended use, physical characteristics, and electrical parameters.

To directly answer your request based on the provided document:

1. A table of acceptance criteria and the reported device performance:

The document does not present acceptance criteria in a quantitative, outcome-based manner for clinical efficacy or diagnostic accuracy, as would be expected for an AI/ML device. Instead, "acceptance criteria" are implied by adherence to recognized electrical, EMC, and biological safety standards.

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

• The document describes non-clinical bench testing (electrical safety, EMC, biocompatibility) rather than a clinical "test set" of patient data. Therefore, concepts like sample size for a test set and data provenance (country, retrospective/prospective) are not applicable in this context. The "sample" tested would be the physical device units and their components.

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

• Not applicable. Ground truth as typically understood for medical imaging or diagnostic AI (e.g., expert consensus on clinical findings) is not established here. The "ground truth" for the non-clinical tests is adherence to engineering and safety standards.

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

• Not applicable. There is no expert adjudication process described, as clinical interpretation is not being evaluated.

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. This is a TENS device, not an AI-assisted diagnostic tool. No MRMC study was conducted or is relevant to this submission type.

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

• Not applicable. This is a physical medical device, not a software algorithm.

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

• The "ground truth" for this device's performance evaluation against standards is defined by the technical specifications and limits set by the referenced IEC and ISO standards for electrical safety, EMC, and biocompatibility.

8. The sample size for the training set:

• Not applicable. This device does not involve machine learning or a "training set."

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

• Not applicable. There is no training set for this device.

Ask a specific question about this device

The PO3M Fingertip Pulse Oximeter is a non-invasive device intended for spot-checking of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. The portable fingertip device is indicated for adult patients in home and hospital environments (including clinical use in internist/surgery. anesthesia, intensive care, etc).

Our device PO3M Fingertip Pulse Oximeter is a fingertip device, which can measure the arterial SpO2 and pulse rate value and can display the results to the user.

It is a noninvasive measurement instrument with a pair of small light-emitting diodes (LEDs) facing a photodiode through a fingertip. One LED is red, with wavelength of 660 nm, and the other is infrared, 880 nm. The MCU calculates the ratio of these two wavelengths and get the results of the SPO2. At the same time, by examining only the varying part of the absorption spectrum, a monitor can ignore other tissues or nail, and discern only the absorption caused by arterial blood to detect the pulse rate.

The power source is Lithium-ion battery.

More over, the PO3M can transmit the measurement data to the iPhone, iPod Touch or iPad by wireless transmission.

The device is for prescription. It is neither for life-supporting nor for implanting. lt does not contain any drug or biological product and it does not need to be sterile.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

The document does not specify the sample size used for performance testing (e.g., test set for SpO2 and Pulse Rate accuracy). It states that the device was tested according to ISO 80601-2-61:2011, which likely involves human subject testing with controlled hypoxia. However, details of the number of subjects and their characteristics are not provided in this summary.

The provenance of the data (e.g., country of origin, retrospective or prospective) is not explicitly stated.

3. Number and Qualifications of Experts for Ground Truth

This information is not provided in the document. For pulse oximetry, the ground truth for SpO2 accuracy is typically established by arterial blood gas analysis, which does not require expert adjudication in the same way imaging studies might.

4. Adjudication Method

This information is not applicable and therefore not provided, as the ground truth for pulse oximetry accuracy is derived from direct physiological measurements (e.g., arterial blood gas analysis) rather than subjective expert interpretation requiring adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was done, as this type of study is typically performed for diagnostic imaging devices where human interpretation is a key component. This device is a direct measurement device (pulse oximeter), not an AI-assisted diagnostic tool for human readers.

6. Standalone Performance

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done for the device's main function. The performance testing section (4. Performance Testing) indicates that the "device was tested according to ISO 80601-2-61: 2011" and found to meet all applicable requirements. This standard specifies requirements for pulse oximeter equipment, including accuracy measurements against a reference standard. The reported accuracy metrics for SpO2 and pulse rate are based on the device's direct measurements.

7. Type of Ground Truth Used

The ground truth used for performance assessment (SpO2 and pulse rate accuracy) is based on direct comparison to a reference method, typically arterial blood gas analysis for oxygen saturation. The ISO 80601-2-61 standard outlines these methods.

8. Sample Size for the Training Set

This information is not provided. Pulse oximeters are typically based on well-established physical principles of light absorption by hemoglobin, and their algorithms are often derived from theoretical models and empirical calibrations rather than extensive machine learning training sets in the modern sense. If any machine learning or adaptive algorithms are used, the training set details are not disclosed in this summary.

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

This information is not provided. As mentioned above, the underlying principles of pulse oximetry are generally not based on "training sets" in the context of supervised machine learning. If any calibration or algorithm development involved data, the method for establishing its ground truth is not detailed here.

Ask a specific question about this device

KD-936 Fully Automatic Wireless Blood Pressure Monitor is for use by medical professionals or at home and 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

KD-936 Fully Automatic Wireless Blood Pressure Monitor is for use by medical professionals or at home and 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

KD-936 Fully Automatic Wireless Blood Pressure Monitor is designed and manufactured according to ANSI/AAMI SP10--manual, electronic or automated sphygmanometers.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. it can calculate the systolic and diastolic blood pressure, the measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user. More over, it also obtains the function of averaging the measurement results.

KD-936 Fully Automatic Wireless Blood Pressure Monitor achieves its function by integrate the device with an iPhone, ipod or ipad. For it does not contain an LCD or other display components, so It's necessary for the new device to connect to an iPhone, iPod or iPad containing a support software to constitute a complete blood pressure measurement system. And the new device connect iPhone, iPod or iPad through bluetooth,

Here's a breakdown of the acceptance criteria and the study details for the KD-936 Fully Automatic Wireless Blood Pressure Monitor, based on the provided FDA 510(k) files:

1. Table of Acceptance Criteria and Reported Device Performance

The core acceptance criteria for blood pressure monitors generally stem from the ANSI/AAMI SP10 standard. While the document doesn't explicitly list numerical thresholds in a table, it states that the device "met all applicable requirements of the standard." For context, ANSI/AAMI SP10 typically requires:

Explanation of "Met all applicable requirements of the standard" for accuracy:

While not explicitly stated in the document, ANSI/AAMI SP10 (and its derivatives, such as ISO 81060-2) typically requires the following for blood pressure measurement accuracy:

• Mean Difference: The average difference between the device's readings and a reference standard (e.g., auscultatory measurement) should be ±5 mmHg or less.
• Standard Deviation: The standard deviation of the differences should be 8 mmHg or less.

The statement "the device met all applicable requirements of the standard" implies that these numerical thresholds were achieved in the clinical test.

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

• Sample Size: The document does not explicitly state the sample size used for the clinical test. It only mentions, "a new clinical test is done in accordance with ANSI/AAMI SP10." ANSI/AAMI SP10 typically requires a minimum of 85 participants for clinical validation. This would likely be the sample size used, though it's not confirmed.
• Data Provenance: The document does not specify the country of origin of the data. It also does not explicitly state whether the study was retrospective or prospective, but clinical validation studies for device approval are almost always prospective.

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

• Number of Experts: The document does not explicitly state the number of experts used. However, for blood pressure monitor validation according to ANSI/AAMI SP10, it typically requires at least two independent trained observers to perform reference measurements (e.g., auscultatory method).
• Qualifications of Experts: The document does not specify the qualifications of the experts, but in clinical validation studies for blood pressure monitors, these would typically be clinicians or trained personnel (e.g., nurses, physicians) proficient in manual auscultatory blood pressure measurement.

4. Adjudication Method for the Test Set

• Adjudication Method: The document does not explicitly detail an adjudication method. In the context of ANSI/AAMI SP10 for blood pressure monitors, the "ground truth" (reference measurement) is typically established by simultaneous measurements by two independent observers, and their readings are averaged or compared for agreement. If disagreements exceed a certain threshold (e.g., 4 mmHg for systolic/diastolic readings), a third observer might be involved, or the readings might be discarded. This implies an implicit "2 (+1 if needed)" type of approach for establishing reference.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No MRMC study was done. This type of study is not typically applicable or required for the approval of a non-invasive blood pressure measurement system like the KD-936. MRMC studies are usually relevant for image-based diagnostic aids where human readers interpret medical images with and without AI assistance.

6. If a Standalone (Algorithm only without Human-in-the-Loop Performance) Was Done

• Yes, a standalone study was done. The clinical test performed "in accordance with ANSI/AAMI SP10" evaluates the device's performance directly against a reference standard, without human intervention in the measurement process (other than proper cuff placement and activation). The device itself (the algorithm for blood pressure determination) is being tested for its accuracy.

7. The Type of Ground Truth Used

• Expert Consensus/Reference Standard Measurement: The ground truth for the clinical test would have been established using a reference standard method, which for blood pressure monitors is typically auscultatory measurement performed by trained observers, potentially with a mercury sphygmomanometer or a validated electronic device used as the reference. This aligns with the requirements of ANSI/AAMI SP10.

8. The Sample Size for the Training Set

• The document does not provide information about a specific "training set" sample size. For traditional medical devices like blood pressure monitors, the concept of a distinct 'training set' and 'test set' in the machine learning sense is not always explicitly delineated. The development and internal validation (or "training and tuning") of the oscillometric algorithm would happen during the device's engineering phase, likely using proprietary data, before the formal clinical validation study (test set). The 510(k) summary focuses on the final validation.

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

• Since a specific "training set" is not detailed, the method for establishing its ground truth is also not provided. However, any internal development or optimization of the device's algorithm would have used reference blood pressure measurements, likely obtained through similar standard auscultatory methods, to "train" or refine its oscillometric algorithm.

Ask a specific question about this device

KD-557J, KD-5031NJ, KD-5963NGJ, KD-5963NUJ and KD-5971J Fully Automatic Electronic Blood Pressure Monitor are for use by medical professionals or at home and are 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

KD-557J, KD-5031NJ, KD-5963NGJ, KD-5963NUJ and KD-5971J Fully Automatic Electronic Blood Pressure Monitor are for use by medical professionals or at home and are 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 technique in which an inflatable cuff is wrapped around the upper arm. The cuff circumference is limited to 22cm-48cm.

They are designed and manufactured according to ANSI/AAMI SP10--manual, electronic or automated sphygmanometers.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. It can calculate the systolic and diastolic blood pressure, and display the result on the LCD. If any irregular heartbeat is detected, it can also be shown on the LCD. More over, it also calculates the average of the last three measurements.

The provided text is a 510(k) summary for a Fully Automatic Electronic Blood Pressure Monitor. It includes information about device descriptions, intended use, and comparisons to predicate devices, but it does not contain the detailed clinical study information typically required to fully address your request in the context of advanced AI/medical imaging devices.

Specifically, for a blood pressure monitor, the "acceptance criteria" generally refer to accuracy standards set by organizations like AAMI (Association for the Advancement of Medical Instrumentation) or ISO (International Organization for Standardization). The study that proves the device meets these criteria would involve comparative measurements against a reference standard.

Based on the provided text, here's what can be extracted and what cannot:

1. Table of acceptance criteria and the reported device performance

The document states the device conforms to AAMI SP10:2002 (and its amendments), which is the standard for manual, electronic, or automated sphygmomanometers. This standard defines the acceptance criteria for accuracy.

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

The document mentions clinical tests were done for predicate devices and that those reports are applicable to the subject devices due to identical or similar design principles and algorithms.

• "The clinical test report of KD-598(K083395) is applicable to our subject devices."
• "the clinical test report of KD-5961 is applicable to KD-5031NJ."

However, the document does NOT provide the following specific details for the test sets:

• Sample size: Not explicitly stated for any of the devices.
• Data provenance: Not specified (e.g., country of origin, retrospective or prospective).

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

This information is not provided in the document. For blood pressure monitors, the "ground truth" in clinical validation studies is typically established by trained observers using auscultatory methods with a mercury sphygmomanometer (or an equivalent reference standard) as per the AAMI SP10 protocol. The document does not detail how many observers were used or their qualifications for the underlying studies it references.

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

This information is not provided. In blood pressure validation studies following standards like AAMI SP10, often multiple trained observers measure blood pressure, and their readings are compared to ensure agreement, playing a role similar to an "adjudication method" in establishing the reference. However, the exact methodology is not detailed here.

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

N/A. This device is a fully automatic electronic blood pressure monitor, not an AI-powered diagnostic tool for human readers. Therefore, an MRMC comparative effectiveness study comparing human readers with and without AI assistance is not applicable to this type of device.

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

Yes, the device itself is a "Fully Automatic Electronic Blood Pressure Monitor," implying it operates in a standalone manner, providing measurements without direct human interpretation in the measurement process. The clinical tests mentioned (conforming to AAMI SP10) would evaluate this standalone performance against a reference standard.

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

For blood pressure monitors, the ground truth is typically established by simultaneous measurements using a recognized reference standard, usually a mercury sphygmomanometer with trained observers using auscultatory methods, as defined by protocols like AAMI SP10. The document states conformance to AAMI SP10, which implies this type of ground truth methodology.

8. The sample size for the training set

N/A / Not provided. Blood pressure monitors based on oscillometric technology generally do not employ machine learning models in the same way modern AI systems do, which require "training sets." Their algorithms are typically fixed based on established physiological principles and signal processing. Therefore, the concept of a "training set" in the AI sense is not applicable to this device, or at least not described in the provided regulatory document.

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

N/A / Not applicable for the reasons stated in point 8.

Ask a specific question about this device