Search Results

CSI Model 9K Managed Health System Kiosk is an automated non invasive screening device intended for voluntary use by the general public. The device measures systolic and diastolic blood pressure, pulse and if optionally equipped, weight and temperature. Users may also manually enter or download blood glucose level. Data from the Model 9K may be stored by the user for tracking purposes. It is not a diagnostic device, and only furnishes data so users can consult their personal physicians.

The CSI Model 9K Managed Health System Kiosk provides an unsupervised means for measuring and tracking an individual's blood pressure (both systolic and diastolic) and pulse rate. The kiosk can typically be installed in corporate lobbies and can be part of corporate wellness programs to track changes over time.

The device has a touch screen for user interface. The user may select from a menu of items. For instance, touching the button "Blood Pressure" on the touch screen will result in a sub menu that will direct the user to insert the arm in the cuff mechanism before pressing the "Start" button on the touch screen. The unit also consists of a "Release" push button that is separate from the touch screen. This "Release" button would result in the immediate deflation of the cuff and the aborting of the test. This well marked red button is meant for use in the event of an emergency. Other buttons on the main menu of the touch screen display would result in the user receiving the blood pressure (systolic and diastolic), heart rate, weight and temperature readings.

In addition to measuring the user's blood pressure, weight and temperature, the 9K may also be capable of accepting uploaded data from a One Touch Ultra Glucometer and playing videos on health topics. Data measured by the 9K or input into the 9K can be stored for tracking purposes. The 9K may also have the ability to display websites like WebMD, MayoClinic and corporate portals. Videos may present medical information and present symptoms but not diagnoses. The 9K may also be equipped with a scanner, printer, finger print reader and signature pad.

The provided text describes the CSI Model 9K Managed Health System, but it is a 510(k) summary for regulatory clearance, not a detailed study report. Therefore, much of the requested information regarding acceptance criteria, specific study design, and performance metrics (especially for AI/algorithm performance) is not explicitly detailed in the document.

However, I can extract the information that is present and indicate where details are missing.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the device was subjected to clinical evaluation and bench testing and "meets the requirements of AAMI/ANSI SP10:2002." This standard is for "Manual, automated, and the requirements for non-invasive sphygmomanometers," and specifies accuracy requirements for blood pressure measurements.

Specific quantitative acceptance criteria and the reported device performance against these criteria are not explicitly stated in a detailed table format within this document.

The document implies that the device achieved compliance with the following standards:

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

• Sample Size: The document does not specify the sample size used for the clinical evaluation (test set).
• Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only states "clinical evaluation."

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, as it pertains to a clinical study design that is not detailed here. For blood pressure monitors, ground truth typically involves reference measurements taken by trained personnel using a validated method.

4. Adjudication method for the test set

This information is not provided in the document.

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

The CSI Model 9K Managed Health System is described as an "automated non-invasive screening device" that measures vital signs. It does not appear to be an AI-driven diagnostic device that assists human readers/clinicians in interpreting medical images or data. Therefore, an MRMC comparative effectiveness study comparing human readers with and without AI assistance is not applicable to this device in the context of the information provided. The "AI" in this context refers to the automation of measurement, not interpretive assistance.

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

The device itself is a "standalone" automated measurement kiosk. The document states, "The CSI Model 9K Managed Health System Kiosk provides an unsupervised means for measuring and tracking an individual's blood pressure (both systolic and diastolic) and pulse rate." And "It is not a diagnostic device, and only furnishes data so users can consult their personal physicians." This implies it operates independently to produce measurements. However, the performance evaluation would have been against a human-obtained reference.

7. The type of ground truth used

For blood pressure, the ground truth in clinical evaluations is typically established by simultaneous or near-simultaneous measurements using a recognized reference standard (e.g., auscultatory method with a mercury sphygmomanometer or another validated oscillometric device) performed by trained operators. This document does not explicitly state the method for ground truth, but it is implied by the adherence to AAMI/ANSI SP10:2002.

8. The sample size for the training set

The document refers to "the blood pressure, weight and pulse measurement systems used in Model 9K is exactly the same as the one used in the CSI Model 5K." This suggests a reliance on a previously cleared device. However, this is a hardware and core measurement technology statement, not a 'training set' in the context of machine learning. Since the device is not described as having an AI component that requires a training set, this information is not applicable in the AI/ML sense.

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

As there is no mention of an AI/ML component requiring a training set in this summary, this information is not applicable.

Ask a specific question about this device

The CSI Model 5K Managed Health System Kiosk is intended for use by the general public to measure blood pressure, pulse and weight. It is not intended to be a diagnostic device; it only provides data on blood pressure, heart rate and weight and users are advised to consult a physician.

The CSI Model 5K Managed Health System Kiosk provides an unsupervised means for measuring and tracking an individual's blood pressure (both systolic and diastolic) and pulse rate. The kiosk can typically be installed in retail establishments and drug stores and may or may not be part of the pharmacy. The device has push buttons for user interface. Such buttons include "Start" button to start the test after the user has inserted the arm into the cuff mechanism, a "Release" button to deflate the cuff mechanism in the event of an emergency, a "Weight" button to start the process of measuring the weight of the user. The output of the machine includes displays to indicate the blood pressure (systolic and diastolic), heart rate and weight. To start the process, the user inserts her arm into the cuff and pushes a button. The machine then proceeds to inflate the cuff and measure the blood pressure using oscillometric method. Once measured, the blood pressure (both systolic and diastolic) and the heart rate are output to the display mounted on the front of the device.

This looks like a 510(k) summary for a medical device called the CSI Model 5K Managed Health System Kiosk, which is an automated noninvasive blood pressure monitor. However, the provided text does not contain a detailed study report with specific acceptance criteria, device performance, sample sizes, or ground truth information in the format requested.

The document discusses that the device has been "subjected to clinical evaluation and bench testing" and "meets the requirements of AAMI/ANSI SP10:2002," along with other IEC standards. AAMI/ANSI SP10:2002 is a standard that outlines requirements for automated sphygmomanometers, including accuracy specifications. Therefore, the acceptance criteria are implicitly those defined by AAMI/ANSI SP10:2002.

Since the detailed study information is missing, I cannot fill in most of the requested table and sections. I will indicate where the information is not provided in the document.

Here's an attempt to answer based only on the provided text, with clear indications of missing information:

1. Table of Acceptance Criteria and Reported Device Performance

Explanation of AAMI/ANSI SP10:2002 (Implicit Acceptance Criteria):
The AAMI/ANSI SP10:2002 standard for automated sphygmomanometers typically requires the following for blood pressure accuracy validation in clinical studies:

• Mean Difference (Device vs. Reference): The mean difference between the test device readings and reference (auscultatory) readings should be within ±5 mmHg.
• Standard Deviation (Difference): The standard deviation of the differences should be 8 mmHg or less.
• A minimum of 85 subjects is usually recommended for the validation study, balanced across age and blood pressure ranges.

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

• Test Set Sample Size: Not specified in the provided text.
• Data Provenance: Not specified in the provided text (e.g., country of origin, retrospective or prospective). The text only states "CSI Model 5K Managed Health System Kiosk has been subjected to clinical evaluation and bench testing."

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. For blood pressure device validation, the "experts" typically refer to trained observers using a reference auscultatory method (e.g., two trained observers blinded to each other's readings, using a mercury sphygmomanometer or validated equivalent).

4. Adjudication method for the test set

• Adjudication Method: Not specified. For blood pressure device validation, and specifically for ground truth establishment, the method often involves two trained observers taking readings and a third adjudicator if their readings differ significantly. This is typically part of the AAMI/ANSI SP10 validation protocol, but the specifics are not 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

• MRMC Study: No, this is not applicable. The device is an automated blood pressure monitor, not an AI-assisted diagnostic imaging or interpretation system that would involve human readers.

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

• Standalone Performance: Yes, the entire device (CSI Model 5K Kiosk) operates as a standalone system. Its performance, as implicitly indicated by "meets the requirements of AAMI/ANSI SP10:2002," refers to its automated measurement capability without human intervention for the measurement itself.

7. The type of ground truth used

• Type of Ground Truth: For blood pressure measurement device validation according to standards like AAMI/ANSI SP10, the ground truth is typically established by simultaneous or
  sequential auscultatory measurements performed by trained observers using a calibrated reference sphygmomanometer (e.g., mercury sphygmomanometer).

8. The sample size for the training set

• Training Set Sample Size: Not applicable/Not specified. For a purely oscillometric blood pressure device, the "training set" doesn't typically exist in the same way it would for a machine learning model. The device's algorithm is based on physiological principles and calibrated, rather than "trained" on a large dataset in the AI sense. If there was an internal dataset used during algorithm development, it is not mentioned.

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

• Ground Truth for Training Set: Not applicable/Not specified, for the reasons mentioned above.

Ask a specific question about this device