Search Results

The ARGUS PB-3000 is a vital data acquisition unit intended to be used within or connected to a medical device or a medical system (Host System) for acquiring, analysing, and transmission of patient vitals and other pertinent clinical data of following vital data of a patient.

Indicated for the following applications:

ECG monitoring and diagnostic - The ECG monitoring function provide a conventional information about the patient's ECG rhythm, heart rate, and may be used for the diagnostic measurements, interpretation and arrhythmias detection in a medical device or medical system (Host System).

Respiration rate and apnea monitoring is indicated for pneumatic issues.

IBP - Invasive blood pressure monitoring is indicated for use in patients who require continuous monitoring of physiological pressures in order to rapidly assess changes in the patient's condition or response to therapy. It may also be used to aid in medical diagnosis.

NIBP - NIBP measurement is indicated in patients who have a risk of developing high or low blood pressure.

SpO2 - These measurements are indicated for use in patients who are at risk of developing hypoxemia, carboxyhemoglobinemia, or methemoglobinemia. This monitoring may be used during no motion conditions, and in patients who are well or poorly perfused.

CO2 - The CO2 measurement is used to detect trends in the level of expired CO2. It is used for monitoring breathing efficacy and treatment effectiveness in acute cardiopulmonary care, for example, to determine if adequate compressions are being performed during CPR or to rapidly detect whether an endotracheal tube has been placed successfully.

Respiration rate and apnea monitoring is indicated for pneumatic issues.

Cardiac Output (CO) - Cardiac Output measurement is indicated for use in patients who require a non-continuous measurement of the stroke volume and 1/min volume of the heart.

Temperature - Temperature measurement is indicated in any patient that has a risk of high or low temperature.

The ARGUS PB-3000 is a vital data acquisition unit intended to be used within or connected to a medical device or a medical system (Host System) for acquiring, and transmission of patient vitals and other pertinent clinical data. It receives vital signals from the patient through external sensors and communicates with the Host System. Data is transmitted to the Host System via network connection and without storing vital data and patient demographic data on the PB-3000. Depending on the variant of the PB-3000, the device has different modules allowing measurement of the vital parameter for ECG (monitoring and diagnostic mode, and respiration), IBP, temperature, cardiac output (CO), Sp02, CO2, and/or NIBP measurements.

The Host System is designed by a 3rd party host system manufacturer who chooses the PB-3000 variant to be implemented in their Host System. The PB-3000 communication interface allows the Host System Manufacturer to setup and use the provided functions.

The provided FDA 510(k) summary for the ARGUS PB-3000 device does not explicitly provide a table of acceptance criteria and reported device performance values in a quantifiable manner that is typically requested for AI/ML device submissions. This document is a premarket notification for a traditional medical device (a vital data acquisition unit), not a software as a medical device (SaMD) with an AI/ML component requiring a detailed performance study with ground truth and expert adjudication.

However, based on the non-clinical performance data section, we can infer some of the testing performed and the standards met, which serve as the implicit acceptance criteria for this type of device. The study described focuses on demonstrating substantial equivalence to a predicate device (ARGUS PB-1000 System, K012226) through compliance with recognized electrical safety, EMC, and performance standards for physiological monitoring equipment.

Here's an attempt to structure the available information regarding acceptance criteria and the "study" (non-clinical testing) that proves the device meets them, while acknowledging the limitations of the provided document in the context of typical AI/ML device performance reporting:

1. Table of Acceptance Criteria and Reported Device Performance

Since specific numerical acceptance criteria and "reported device performance" (e.g., sensitivity, specificity, accuracy metrics as would be seen for an AI algorithm) are not presented in this document for the overall device, the table below reflects the standards that the device met. Compliance with these standards is the "reported performance" and the fulfillment of the "acceptance criteria" in this context.

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

• Test Set Sample Size: Not explicitly stated in terms of patient data. The testing referenced are primarily benchmarking against recognized standards using test equipment, simulators, and potentially some limited physiological setups, rather than a "test set" of patient data in the way an AI/ML model would use it. For physical device performance, compliance with standards usually involves predefined test methods and specific numbers of readings or operational cycles, but not a "sample size" of diverse patient cases as would be relevant for an algorithm's performance.
• Data Provenance: Not applicable in the context of this type of non-clinical, standards-based testing. The testing is laboratory-based and simulated, focusing on hardware and software functionality and safety according to engineering standards. There is no mention of country of origin for patient data or whether it was retrospective or prospective, as no clinical data was used for direct performance evaluation for this 510(k) submission.

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

• Number of Experts: Not applicable. For standards-based testing of a vital signs acquisition unit, the "ground truth" is defined by the reference values generated by calibrated test equipment or physiological simulators as specified in the relevant international or national standards (e.g., a known heart rate from an ECG simulator, a known pressure from a pressure calibrator).
• Qualifications of Experts: Not applicable in this context. The testing would be performed by qualified engineers and technicians, not clinical experts establishing medical ground truth from patient data.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. The "adjudication" is compliance with engineering standards and predefined test procedures. The results are compared against the specified limits or expected behaviors detailed in these standards (e.g., "within X% deviation," "detects QRS within Y ms").

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 device is a vital data acquisition unit, not an AI-assisted diagnostic tool involving human readers or interpretation of complex medical imagery/signals by AI.
• Effect Size: Not applicable.

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

• Standalone Performance: The device's performance, as evaluated against the listed standards, is inherently "standalone" in the sense that the device itself (hardware and embedded software) is tested to acquire, analyze (e.g., heart rate, respiration rate), and transmit vital signs. However, it's crucial to note its intended use: "to be used within or connected to a medical device or a medical system (Host System)." The PB-3000 acquires the data, and the Host System handles aspects like display, further analysis (e.g., arrhythmia or ST segments), and alarms. So, while its data acquisition is standalone, its full clinical function relies on integration with a Host System. No specific "algorithm only" performance metric (like for an AI model) is provided beyond general compliance with the standards for ECG, NIBP, etc.

7. The Type of Ground Truth Used

• Type of Ground Truth: Reference values from calibrated test equipment and physiological simulators as defined by the referenced national and international performance standards (e.g., electrical safety standards, specific performance standards for ECG, NIBP, SpO2 modules).

8. The Sample Size for the Training Set

• Training Set Sample Size: Not applicable. Traditional medical devices like this typically do not have "training sets" in the AI/ML sense. The embedded software and algorithms are developed using traditional engineering methods and validated against specifications and standards, not through training on large datasets.

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

• Ground Truth for Training Set: Not applicable. As there's no "training set" in the AI/ML context, there's no corresponding process for establishing ground truth for training. Development and validation rely on established engineering principles and adherence to standards.

Ask a specific question about this device

The CARDIOVIT AT-102 G2 is a 12-channel ECG unit used for the recording, analysis, viewing, storage and transmission of ECG waveforms. The CARDIOVIT AT-102 G2 is designed for indoor use and can be used for all patient populations. The CARDIOVIT AT-102 G2 is used to diagnose cardiac abnormalities, and detect acute myocardial ischemia and infarctions in chest pain patients. The CARDIOVIT AT-102 G2 is intended for use in hospitals, cardiology units, outpatient clinical units and general physician's offices.

The CARDIOVIT AT-102 G2 is a 12-channel ECG unit used for the recording, analysis, viewing, storage and transmission of ECG waveforms.

The provided text is a 510(k) clearance letter from the FDA for a device called "Cardiovit AT-102 G2." This document primarily covers the FDA's determination of substantial equivalence to a predicate device for marketing purposes.

It does NOT contain information about acceptance criteria, device performance results, sample sizes for testing, expert qualifications for ground truth, adjudication methods, MRMC studies, standalone algorithm performance, or ground truth establishment for training sets.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based on the provided input. The document is a regulatory approval letter, not a study report or technical documentation.

Ask a specific question about this device

The CARDIOVIT F - 1 is a 12-channel ECG unit used for the recording, viewing, storage and transmission of ECG waveforms.

The CARDIOVIT FT-1 is designed for indoor use and can be used for all patient populations.

The CARDIOVIT FT-1 is used to diagnose cardiac abnormalities, and detect acute myocardial ischemia and infarctions in chest pain patients.

The CARDIOVIT FT-1 is intended for use in hospitals, cardiology units, out-patient clinical units and general physician's offices.

The CARDIOVIT FT-1 is a 12-lead ECG (Electrocardiograph) device used in the recording, analysis, viewing, storage and transmission of ECG waveforms.

The CARDIOVIT FT-1 does not provide a patient monitoring capability with alarm annunciation.

The CARDIOVIT FT-1 has a color display. It accepts user input via a touch panel or barcode scanner. It can generate a variety of reports that can be viewed on the display or printed on a strip chart recorder that is built into the device.

The CARDIOVIT FT-1 is mains- or battery- powered and uses sensors that come in contact with the patient.

The CARDIOVIT FT-1 is intended to function in the patient vicinity alongside other medical devices. It can operate as a stand-alone device or can be connected to the SCHILLER SEMA3 Data Management System via Ethernet (land-line or WiFi) in order to store reports and retrieve work orders for a given patient.

The provided FDA 510(k) summary for the CARDIOVIT FT-1 states that the device is substantially equivalent to predicate devices, but it does not include a study or specific acceptance criteria for the device's diagnostic performance (e.g., accuracy in diagnosing cardiac abnormalities or detecting myocardial ischemia/infarctions).

Instead, the performance data provided focuses on:

• Electrical safety, essential performance, and electromagnetic compatibility (EMC) testing: This confirms compliance with various IEC standards (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-6, IEC 60601-2-25, IEC 62366).
• Software Verification and Validation Testing: This confirms the software's compliance with FDA guidance for "moderate" level of concern software.

Therefore, many of the requested details about acceptance criteria for diagnostic accuracy, sample sizes for test sets, ground truth establishment, expert qualifications, and MRMC studies are not present in this document.

Here's a breakdown of the information that can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

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

Not applicable for diagnostic performance. The document only references compliance with general engineering and software standards, not a specific clinical test set for diagnostic accuracy.

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

Not applicable for diagnostic performance. This information is not provided as there is no diagnostic performance study detailed.

4. Adjudication method for the test set

Not applicable for diagnostic performance. This information is not provided as there is no diagnostic performance study detailed.

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. The document describes a traditional ECG device, not an AI-assisted diagnostic tool. Therefore, an MRMC study related to AI assistance would not be applicable and is not mentioned.

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

No. The device is an electrocardiograph, which directly records and analyzes ECG waveforms. The "analysis" component is likely based on established algorithms for ECG interpretation, but there is no mention of a separate standalone algorithmic performance study in the context of AI or machine learning for diagnostic accuracy. The performance is tied to its measurement and interpretation capabilities as part of a medical device, which is primarily assessed through its adherence to standards for electrocardiographs (e.g., IEC 60601-2-25) and its equivalence to predicate devices.

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

Not applicable for diagnostic performance. This information is not provided as there is no diagnostic performance study detailed. The device records ECG waveforms, and its "diagnosis" capabilities would generally rely on internal algorithms that interpret these waveforms based on established cardiology principles. The substantial equivalence argument relies on comparing this interpretation to that of predicate devices, which implicitly assumes the predicate devices have an acceptable "ground truth" performance.

8. The sample size for the training set

Not applicable. This device is an electrocardiograph, and while it performs "analysis," the document does not indicate that this analysis is based on machine learning or AI that would require a "training set" in the modern sense (e.g., for deep learning). Its algorithms are based on established signal processing and diagnostic rules for ECG interpretation.

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

Not applicable. As above, there is no mention of a "training set" in the context of machine learning.

Ask a specific question about this device

The Diagnostic Station DS20 is a 12-lead EGG device used for the recording, analysis and evaluation of ECG waveforms. Recordings made with the DS20 can be used as a diagnostic aid for heart function and heart conditions.

The DS20 also measures the following patient vital information to further assessment: pulmonary lung function (spirometry), blood pressure, functional oxygen saturation of arterial hemoglobin (SpO2), carboxyhemoglobin saturation (SpCO), respiration, temperature, and weight.

The DS20 is intended for data collection only. It is not intended for continuous momitoring use and does not provide an alarm function.

The DS20 is indicated for use in hospital and clinic settings, on adult and pediatric patients.

The Diagnostic Station DS20 is a 12-lead EGG (Electrocardiograph) device used for the recording, analysis and evaluation of ECG waveforms. It also measures the following patient vital information to further aid in patient assessment: pulmonary lung function (spirometry), blood pressure, functional oxygen saturation of arterial hemoglobin (SpO>), carboxyhemoglobin saturation (SpCO), respiration, temperature and weight. It also supports a 5-lead ECG measurement of heart rate when 12-lead ECG analysis is not needed.

The DS20 does not provide a patient monitoring capability with alarm annunciation.

The DS20 has a color display. It accepts user input via a touch panel, barcode scanner or keyboard. It can generate a variety of reports that can be viewed on the display or printed on a strip chart recorder or laser printer.

The DS20 is mains- or battery-powered and uses sensors that come in contact with the patient.

The DS20 is intended to function in the patient vicinity alongside other medical devices. It can operate as a stand-alone device or can be connected to the SCHILLER SEMA3 Data Management System via Ethernet (land-line or WiFi) in order to store reports and retrieve work orders for a given patient.

This document describes the Diagnostic Station DS20, a medical device for recording and analyzing ECG waveforms, along with other vital signs. The provided text outlines the device's indications for use and performance data, but it does not contain specific acceptance criteria, detailed study designs for clinical performance, or a comparative effectiveness study with human readers.

Based on the provided text, here's a breakdown of the information requested, with "N/A" indicating information not explicitly found:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on compliance with established regulatory standards for electrical safety, essential performance, and electromagnetic compatibility (EMC), as well as software verification and validation. It does not provide numerical acceptance criteria for specific diagnostic performance metrics (e.g., sensitivity, specificity for ECG interpretation) nor does it report those metrics.

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

• Sample Size for Test Set: N/A (The document primarily details compliance with regulatory standards through successful testing, not a specific clinical test set for diagnostic performance.)
• Data Provenance (e.g., country of origin, retrospective/prospective): N/A (Clinical study data for performance evaluation is not detailed in this submission summary.)

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

• N/A (The document does not describe a test set with expert-established ground truth for diagnostic performance.)

4. Adjudication Method for the Test Set

• N/A (No specific test set or adjudication method is described.)

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

• Was it done? No. The document does not mention any MRMC comparative effectiveness study or any studies involving human readers, with or without AI assistance.
• Effect size of human reader improvement: N/A (Not applicable as no such study was performed/reported.)

6. Standalone (Algorithm Only) Performance Study

• The Diagnostic Station DS20 is described as a device that records, analyzes, and evaluates ECG waveforms and measures vital information. It supports a 5-lead ECG measurement of heart rate. The document mentions "analysis and evaluation of ECG waveforms" which implies an algorithmic component. However, it does not describe a standalone performance study comparing its algorithmic output against ground truth for specific diagnostic accuracy metrics (e.g., automated ECG interpretation accuracy). The performance data section focuses on general safety, performance, and software standards compliance rather than diagnostic performance of its analytical features.

7. Type of Ground Truth Used

• N/A (For the aspects related to diagnostic performance of ECG interpretation or vital signs analysis, specific ground truth methods are not detailed. The "successful testing" refers to compliance with performance standards rather than clinical accuracy against a gold standard.)

8. Sample Size for the Training Set

• N/A (The document does not provide information about a training set for any algorithmic components within the device.)

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

• N/A (No training set is mentioned in the provided text.)

Ask a specific question about this device

The Welch Allyn® 1500 Patient Monitor patient monitoring unit is designed for the monitoring of vital parameters such as ECG, SpO2, etCO2, non invasive blood pressure (NIBP), invasive blood pressure (IBP), temperature and respiration of a patient.
The device is intended to be used by qualified doctors or trained medical personnel.
The device is not suitable for transport.
There is no danger for patients with pacemaker.
The device is intended for the monitoring of one patient at a time.
The device is not designed for sterile use nor is it designed for outdoor use.
Do not use this monitor in areas where there is any danger of explosion or in the presence of flammable gases.
The device is classified CF. It is defibrillation protected when the original accessories are used. However, as a safety precaution when possible, remove the electrodes before defibrillation.
This product is not designed for direct cardiac application.
The arrhythmia module is not intended for use with neonatal patients.
The ST-analysis module is not intended for use with neonatal patients.

The Welch Allyn 1500 Patient Monitor is an ultra-flat patient monitor designed for neonates, children, adult and paediatric use. It has a LCD screen for comprehensive vital data monitoring. Mains power supply is used for stationary use. The Welch Allyn 1500 Patient Monitor also provides full vital data monitoring during transport with the built-in battery.

The SCHILLER Welch Allyn 1500 Patient Monitor is a patient monitoring unit designed for monitoring vital parameters such as ECG, SpO2, etCO2, non-invasive blood pressure (NIBP), invasive blood pressure (IBP), temperature, and respiration of a patient.

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly state quantitative acceptance criteria or performance metrics for the Welch Allyn 1500 Patient Monitor. Instead, it relies on demonstrating substantial equivalence to previously FDA-cleared predicate devices. The "performance" is implicitly tied to compliance with various medical device standards, indicating that the device meets the safety and performance levels expected under those standards.

The study described is primarily a substantial equivalence demonstration to predicate devices for each specific parameter. This means the performance of the Welch Allyn 1500 Patient Monitor's individual components (e.g., ECG analysis, SpO2 sensor) is considered acceptable because they utilize algorithms and circuitry that have previously received FDA clearance in other devices.

General safety and performance acceptance criteria for the entire device assembly are met through compliance with various national and international performance, safety, and electromagnetic compatibility standards, as listed in the "Non-Clinical Tests B1" section.

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

The document does not explicitly state a specific sample size for a test set used to evaluate the overall Welch Allyn 1500 Patient Monitor. Instead, it relies on the pre-existing FDA clearances of the embedded components and their respective studies.

For the predicate devices/algorithms:

• Data Provenance: Not explicitly stated for each predicate device's original clearance, but these devices would have undergone their own testing, likely including both clinical and non-clinical studies. Given the context of medical devices, data would generally originate from diverse patient populations to ensure broad applicability. The submitting company (SCHILLER AG) is based in Switzerland.
• Retrospective or Prospective: Not specified.

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

This information is not provided in the document as it describes a substantial equivalence submission relying on previously cleared components and adherence to standards, rather than a de novo clinical study with new ground truth establishment for the combined device. For the individual predicate devices, this information would have been part of their original 510(k) submissions.

4. Adjudication Method for the Test Set

Since a specific test set and ground truth establishment for the Welch Allyn 1500 Patient Monitor itself (beyond component equivalence and standard compliance) are not detailed, an adjudication method is not mentioned.

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

There is no mention of an MRMC comparative effectiveness study being performed for the Welch Allyn 1500 Patient Monitor. The submission focuses on device parameters being substantially equivalent to existing FDA-cleared devices, meaning it's not comparing human readers with and without AI assistance specific to this new integrated monitor.

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

The submission details that the algorithms for 12-lead Rest-ECG Analysis, Patient Temperature, Respiration, NIBP, IBP, SpO2, ECG Arrhythmia/ST-segment Analysis, and etCO2 are the same as those present in previously FDA-cleared devices. This implies that the standalone performance of these algorithms would have been established during the original clearance of those predicate devices. The current submission focuses on the integration and overall safety/effectiveness of the combined unit.

• For instance, the ECG Arrhythmia and ST-segment analysis algorithm is the "Mortara ECG Arrhythmia and ST-segment analysis algorithm used in the 1500 Patient Monitor has been FDA-cleared in the Datascope Passport 2 Vital Signs Monitor (K020550)." This indicates a standalone performance study (without human in the loop) for that algorithm would have been conducted as part of the K020550 submission.

7. Type of Ground Truth Used

The type of ground truth used for the underlying algorithms in the predicate devices is not explicitly stated in this document. However, for physiological monitoring devices, ground truth for parameters like ECG interpretation, arrhythmia detection, blood pressure, SpO2, and CO2 typically involves:

• Expert Consensus: For ECG and arrhythmia interpretation by cardiologists.
• Reference Standards/Devices: Calibrated reference instruments for parameters like blood pressure, temperature, SpO2, and CO2.
• Pathology/Clinical Outcomes Data: Less direct for these specific vital signs but could be relevant for validating the clinical significance of detected arrhythmias or ST changes.

8. Sample Size for the Training Set

The document does not provide information regarding the sample size of training sets for any of the algorithms. This information would have been part of the original 510(k) submissions for the predicate devices where these algorithms were first cleared.

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

Similar to point 8, the document does not provide information on how the ground truth for the training sets of the constituent algorithms was established. This would have been detailed in the respective 510(k) submissions for the predicate devices.

Ask a specific question about this device

The BP-200 plus is intended to be used as an adjunct to exercise stress testing devices. It is intended to measure and display diastolic and systolic blood pressure, heart rate, percentage of oxygen saturation in arterial blood (SpO2) and pulse rate in adult or adolescent patients during stress tests. The measurement cuff of the BP-200 plus in intended to be placed on the upper right arm of the patient. The BP-200 plus can be used for patients of both sexes and all races. The BP-200 plus should not be used with neonates.

The BP-200 plus, a microprocessor based non invasive blood pressure monitor and oxygen saturation measurement system intended to be used with stress-test systems, uses Korotkoff sounds to determine blood pressure and an optical ear sensor for oxygen saturation. An internal electric pump is used to inflate the cuff, and deflation is controlled by a valve. The BP-200 plus has the ability to make blood pressure at predetermined intervals (normally from a schedule determined by the physician), or on demand. Saturation measurements are updated once per second.

The BP-200 plus is powered by an external power supply (input: 230/110 V; output: 9V dc), and as an option by using four "AA" rechargeable batteries (≥ 2500 mAh). The batteries must be recharged with an external battery charger.

The SCHILLER BP-200 plus is an automated non-invasive blood pressure monitor system with an oxygen saturation measurement option, intended for use as an adjunct to exercise stress testing devices. It measures and displays diastolic and systolic blood pressure, heart rate, percentage of oxygen saturation in arterial blood (SpO2), and pulse rate in adult or adolescent patients during stress tests. It is not to be used with neonates.

Here's a breakdown of the acceptance criteria and study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the BP-200 plus has satisfactorily passed all tests according to the listed standards. While quantitative acceptance criteria (e.g., specific error margins for blood pressure measurements) are not explicitly stated in the provided text, the reference to these standards implies that the device achieved compliance with their respective requirements.

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

The document does not explicitly state the sample size (number of patients) used for the clinical test set. The provenance of the data is implied to be clinical studies conducted in adherence to international standards. The country of origin of the data is not specified directly, but the device manufacturer is SCHILLER AG in Switzerland, and the standards are international (ANSI/AAMI, EN, ISO, European Society of Hypertension). The studies are clinical tests, and based on the context of premarket notification for a new device, they would be considered prospective in nature.

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

The document states that the measurements of the BP-200 plus were "compared with manual auscultatory measurements." This implies that human experts (e.g., trained medical professionals) performed the manual auscultatory measurements, which served as the ground truth. However, the number of experts, their qualifications, or any specific details about the individuals establishing the ground truth are not provided.

4. Adjudication Method for the Test Set

The document indicates that the BP-200 plus measurements were "compared with manual auscultatory measurements." This likely means that the manual measurements served as the reference standard. However, the specific adjudication method (e.g., if multiple human readers took manual measurements and how discrepancies were resolved, such as 2+1, 3+1, or none) is not described.

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

A MRMC comparative effectiveness study, particularly one involving AI assistance, is not described in the provided text. The device is a blood pressure monitor, not an AI-assisted diagnostic tool for image interpretation or similar tasks that would typically involve MRMC studies in this context. The comparison is between the device's automated measurements and traditional manual measurements.

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

Yes, the primary clinical test described is a standalone performance evaluation of the BP-200 plus device. The device's measurements (algorithm only, as it's an automated monitor) are compared against the gold standard of manual auscultatory measurements. There is no indication of a human-in-the-loop interaction where an operator's performance is 'assisted' by the device in the way an AI would assist a radiologist.

7. The Type of Ground Truth Used

The ground truth used for the clinical tests was manual auscultatory measurements. This is a well-established clinical standard for blood pressure measurement.

8. The Sample Size for the Training Set

The document does not provide information about a separate "training set" or its sample size. As this device is a medical monitoring instrument and not an AI/machine learning algorithm that requires extensive data for model training in the conventional sense, the concept of a training set as understood in AI/ML is not directly applicable. The device's internal algorithms and calibration would have been developed and refined through engineering and validation processes, but these details are not specified as a "training set" in this context.

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

Since a "training set" in the context of AI/ML is not mentioned or implied for this device, information on how its ground truth was established is not applicable/provided. The development and calibration of the device's algorithms would have relied on engineering principles and potentially internal testing, but not explicitly on an external "training set" with established ground truth as described for AI models.

Ask a specific question about this device

The Monitoring System ARGUS LCM is for the monitoring of vital parameters such as:

• ECG: Heartrate, Respiration Rate ・
• Invasive Blood Pressure: systolic, diastolic and mean pressure -
• Temperature: temperature ー
• Non Invasive Blood Pressure: systolic, diastolic and mean pressure -
• CO2, etCO2 and CO2ins -
• SpO2: SpO2 and pulse rate -

There is alarm handling for all parameters except temperature.

The ARGUS LCM is powered via the normal mains connection 230V/110V, and using an internal battery and an external power input.

The system is inteded for use in the Intensive Care Unit, in the Recovery Room, in the Operation Room and during hospital internal transport.

The Monitoring System ARGUS LCM is for the monitoring of vital parameters such as: ECG, Invasive Blood Pressure, Temperature, Non Invasive Blood Pressure, CO2, etCO2, CO2ins, SpO2, and pulse rate. There is alarm handling for all parameters except temperature. The ARGUS LCM is powered via the normal mains connection 230V/110V, and using an internal battery and an external power input. The system is intended for use in the Intensive Care Unit, in the Recovery Room, in the Operation Room and during hospital internal transport.

The provided document is a 510(k) summary for the SCHILLER AG Argus LCM Monitoring System, comparing it to predicate devices. It states that the device is "as safe and effective as" the predicate devices and passed relevant electrical safety and software quality tests. However, it does not contain the specific information requested about acceptance criteria and a study proving those criteria are met in the format of the output.

Specifically:

• Acceptance Criteria and Reported Device Performance Table: The document lists standards passed for various components (e.g., IEC 60601-1 for System, IEC 60601-2-2 for ECG). However, it does not provide specific acceptance criteria values (e.g., accuracy +/- X%) or numerical reported device performance against those criteria. Instead, it generally states "All tests are passed" or refers to compliance with standards.
• Sample size and data provenance for test set: Not available. The document states "B2 Clinical Tests: n.a." (not applicable), indicating no clinical tests were performed for this submission. The non-clinical tests mentioned are electrical safety and software quality.
• Number of experts and qualifications for ground truth: Not applicable, as no clinical study with ground truth established by experts is described.
• Adjudication method for test set: Not applicable.
• MRMC comparative effectiveness study: Not applicable.
• Standalone (algorithm-only) performance: Not applicable, as the device is a monitoring system and the performance evaluation focuses on hardware components and electrical safety, not an algorithm's standalone diagnostic performance.
• Type of ground truth used: Not applicable, as no clinical study is described. The "ground truth" for the non-clinical tests would be the specifications and requirements of the standards themselves.
• Sample size for training set: Not applicable, as no machine learning algorithm development is described in detail that would require a 'training set'. The software quality section refers to software requirements, development, verification, validation, and testing, but not in the context of a machine learning model.
• How ground truth for training set was established: Not applicable.

Therefore, since the document pertains to a medical device submission primarily focused on demonstrating substantial equivalence through non-clinical testing and comparison to predicate devices, the requested clinical study-centric details are not present.

Ask a specific question about this device

The BR-102 plus is a non-invasive ambulatory blood pressure monitor. It uses auscultatoric and oscillometric signals to measure the blood pressure of human beings, or uses purely the oscillometric signals. Systolic, mean arterial pressure and the heart rate are measured. The BR-102 plus is intended for use as an aid or adjunct to diagnosis and treatment when it is necessary to measure an adult or adolescent patient's blood pressure over an extended period of time (up to 48h). The BR-102 plus can be used for patients of both sexes and all races.

The BR-102 plus should not be used with neonates.

The BR-102 plus is a portable, compact, lightweight, microprocessor based ambulatory blood pressure monitor. Two versions are available:

• Using auscultatoric and oscillometric signals. During cuff delfation auscultatoric and . oscillometric signals are analysed by the microprocessor to determine the blood pressure, where the oscillometric measurement is used as a backup.
• Purely oscillometric method to use the device without a microphone. The oscillometric . signals are analysed by the microprocessor to determine the blood pressure.

The device is worn or carried by the patient. The cuff is borne on the upper arm. An electrical pump inside the device generates the pressure in the cuff. The BR-102 plus is powered from two AA size recharchable NiMH batteries. The BR-102 plus initialises blood pressure measurements depending on a predetermined shedule (normally predetermined by a physician), or on demand (by using the start key). Each reading is stored in memory, allowing the physician to download all the results obtained during the study period after the study has concluded, to be analysed by the PC software. The readings are displayed on the display for a short time.

The associated MT-300 PC software provides the setup of the system. A measurement shedule can be defined with the MT-300 program and up-loaded into the BR-102 plus. All the settings can also be made on the device. After the ambulatory blood pressure study has been completed (up to 48h) the stored readings in the BR-102 plus are downloaded to the PC using the MT-300 program. The MT-300 programm provides the data in tabular and graphic form, as well as a patient report and statistical values.

Here's an analysis of the provided text to extract the requested information about the BR-102 plus NIBP Holter System's acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the BR-102 plus has "satisfactory passed all tests" according to specific standards but does not provide a table of numerical acceptance criteria or the reported device performance against those criteria. It refers to:

• Standards Met: ANSI/AAMI SP10, EN 60601-1, EN 60601-1-2, EN 60601-2-30, EN 1060-1, EN 1060-3.
• Clinical Test Protocol: "International Test Protocol for validation of blood pressure measuring devices in adults" of the European Society of Hypertension.
• Performance Claim: "The BR-102 plus has satisfactory passed all tests."

Without a direct table of acceptance criteria and performance from the document, I cannot create one as specifically requested. The document primarily asserts compliance with established standards. ANSI/AAMI SP10 and the ESH protocol contain specific accuracy requirements for blood pressure devices (e.g., mean difference and standard deviation between device and reference measurements), but these values are not explicitly stated in the provided text as the device's acceptable performance or actual performance.

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. It mentions the "International Test Protocol for validation of blood pressure measuring devices in adults" by the European Society of Hypertension, which typically specifies sample sizes (e.g., usually 33 subjects) for validation studies, but this specific detail is not present in the provided text regarding the BR-102 plus study.

The country of origin for the data is not explicitly stated in relation to the clinical tests, but the submitter (SCHILLER AG) is located in Switzerland. The study type (retrospective or prospective) is also not explicitly stated.

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

The document mentions that the BR-102 plus measurements are compared with "manual auscultatory measurements as described in the SP10." The SP10 standard itself outlines requirements for expert observers (e.g., two trained observers) for auscultatory reference measurements. However, the exact number of experts used for this specific study and their qualifications (e.g., radiologist with 10 years of experience) are not explicitly stated in the provided text.

4. Adjudication Method for the Test Set

The document states that the comparison is made against "manual auscultatory measurements as described in the SP10." The SP10 standard generally prescribes comparison to two trained observers with specific disagreement criteria for valid measurements. However, the specific adjudication method (e.g., 2+1, 3+1, none) used in the BR-102 plus study, beyond referencing the SP10 method, is not explicitly detailed in the text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not conducted or reported in this document. The device is a standalone blood pressure monitor, not an AI-assisted diagnostic tool for human readers.

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

Yes, a standalone study was performed. The clinical tests involve comparing the device's measurements (algorithm only) to a reference standard (manual auscultation). The description of the device as a "microprocessor based ambulatory blood pressure monitor" that "determines the blood pressure" indicates its standalone function without human interpretation of raw signals for diagnosis.

7. The Type of Ground Truth Used

The ground truth used for comparison in the clinical tests was manual auscultatory measurements. This is explicitly stated: "To verify the overall system efficiency the measurments of BR-102 plus are compared with manual auscultatory measurements as discribed in the SP10."

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This type of device (a blood pressure monitor) based on established measurement principles (auscultation and oscillometry) typically would not have a "training set" in the sense of a machine learning algorithm that requires extensive labelled data for supervised learning. Its algorithms are usually pre-programmed based on physiological models and engineering principles, then validated against clinical standards.

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

As no training set is described or implied for this device in the context of machine learning, the question of how its ground truth was established is not applicable based on the provided text. The device's functioning is based on physical measurement principles, not a data-driven training process in the AI sense.

Ask a specific question about this device

The AT-10Plus is a 12-channel, ECG Device used for the recording, analysis and evaluation of ECG recordings. Recordings made with the AT-10Plus can be used as a diagnostic aid for heart function and heart conditions. The AT-10Plus is designed for indoor use. The device provide an optional interface to the SP-250 for pulmonary function data.

The AT-10Plus is a 12-channel, ECG device used for the recording, analysis and evaluation of ECG recordings. It has dimensions of 348x288x87mm and weighs 4.2 Kg. It operates in temperatures from +10° - 40° C and storage temperatures from -10° - +50° C, with relative humidity between 25% - 95% (non condensing). It supports Standard / Cabrera leads and has a battery capacity of 2 hrs of normal use. The frequency range of the digital recorder is 0 to 150Hz. It has an Alphanumerics, LCD Display 800x600dots. The Myogram Filter is 25Hz or 35Hz programmable. Paper speeds are 5/10/12.5/25/50 mm/s. The printing process uses a High resolution thermal printhead 8dots per mm 200dots per inch(amplitude axes) 40dots per mm / 1000 dots per inch time axes, 25mm/s. It uses Thermoreactive, Z-folded, 210mm chart paper and has 6 recording tracks, positioned at optimal with on 80 mm / 3.2 inch automatic baseline adjustement. It has 6 channel representation of 12 simultaneously acquired standard leads automatic lead programs. It also provides an optional interface to the SP-250 for spirometry.

This 510(k) summary describes a device, the CARDIOVIT AT-10Plus, that is an Electrocardiographie Device. The submission focuses on demonstrating substantial equivalence to a predicate device (CARDIOVIT AT-102, K031557) through non-clinical testing and comparison of technical specifications, rather than clinical performance studies with specific acceptance criteria that are typically seen for novel diagnostic algorithms.

Therefore, the requested information regarding acceptance criteria, study details, sample sizes, expert involvement, and ground truth establishment, as they relate to clinical performance, is largely not applicable (N/A) in the context of this 510(k) submission.

Here's a breakdown based on the provided document:

Acceptance Criteria and Device Performance

The core "acceptance criteria" in this 510(k) are related to safety, effectiveness, and technical specifications, demonstrating substantial equivalence to the predicate device.

• Dimensions: 348x288x87mm (vs 380x328x100mm)
• Weight: 4.2 Kg (vs 5.0 kg)
• Control panel: Alphanumerics, LCD Display 800x600dots (vs LCD Display)
• Paper speed: 5/10/12.5/25/50 (vs 5/10/25/50mm/s direct) |

Study Details Based on the Provided Document:

1. A table of acceptance criteria and the reported device performance: See table above. The primary acceptance criterion here is meeting relevant electrical safety standards and demonstrating equivalent technical specifications and intended use to the predicate device.

2. Sample size used for the test set and the data provenance: N/A. This 510(k) relies on non-clinical engineering and software testing, and a comparison of technical specifications, not a clinical "test set" of patient data for performance evaluation.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: N/A. Ground truth establishment for a patient-data test set is not described as part of this submission. The "experts" involved would be those assessing compliance with electrical safety standards and reviewing software documentation.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: N/A. No clinical test set requiring adjudication is described.

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 an electrocardiograph, not an AI-assisted diagnostic tool that would involve human readers and a comparative effectiveness study of this nature.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: N/A. The submission does not describe a standalone algorithm performance study. The device's "analysis" function is intrinsic to its role as an ECG device, and its safety and effectiveness are established through reference to the predicate and compliance with standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): N/A for clinical performance. The "ground truth" for the non-clinical tests is regulatory standards (e.g., EN60601-1, IEC 601-2-25) and engineering specifications of the predicate device.

8. The sample size for the training set: N/A. This is not a machine learning or AI device that would have a "training set" in the typical sense.

9. How the ground truth for the training set was established: N/A. Not applicable for this device type and submission.

Ask a specific question about this device

The monitoring system ARGUS PB-2200 is for the monitoring of vital parameters such as:

Invasive blood pressure: systolic, diastolic and mean pressure
s and controller Brings and/or sidestream Invasive blood pressure. Systems, main and/or sidestream FIO2

lt will extend the functionality of the existing Argus PB-1000 system (K0122Z6).
The function and the promoter her PB-1000 and the visualisation unit AR It will extend the functionality of the existing Algust PB-1000 (PB-100) (PB-100)
The system comprises the parameter box PB-1000 and the visualisation unit ARGUS
(PBS) and th

The system compilses the parcined via a serial interface. PRO. The two units are connected via a serial intenated and calculated in the PB-2200. This All vital parameters and evaluations are registered and calouaced manager generally used
data is then transmitted to the visualisation unit ARGUS PRO or another generally us data is then transmitted to the visuallsation und monitored on the ARGUS PRO.
PC via the serial interface. All data can be shown and monitored on the ARGUS PRO. PC via the serial interface. All data can be snown and monecessed power input (RS
The PB-2200 is operated using an internal battery and an external power input (RS
e and the The PB-2200 is operated using an internal battery alle an and the manate from the 232/12V), which is, like the data transmission, completely sop
visualisation unit. The ARGUS PRO is powered via the normal mains connection

230V/110V.
The system is intended for use in the intensive care unit, in the recovery room, in the The system is intended for ass internal transports.

The system comprises the Parameter Box PB-1000 and the Visualisation Unit AR-GUS PRO. The two units are connected via a serial interface. All vital parameters and evaluations are registered and calculated in the PB-1000. This data is then transmitted to the visualisation unit ARGUS PRO or another generally used PC via the serial interface. All data can be shown and monitored on the ARGUS PRO. The PB-1000 operated using an internal battery and an external power input (RS 232/12V), which is, like the data transmission, completely separate from the visualisation unit. The ARGUS PRO is powered via the normal mains connection 230V/110V.

The provided 510(k) summary for the ARGUS PB-2200 Monitoring System indicates that no specific acceptance criteria or a dedicated study proving performance against such criteria were explicitly presented in the document. Instead, the submission relies on demonstrating substantial equivalence to a predicate device (ARGUS PB-1000 System, K012226) by showing that the ARGUS PB-2200 meets or exceeds various established safety and electromagnetic compatibility standards.

The key takeaway is that for this device, the "acceptance criteria" are the compliance with recognized medical device standards, and the "study" is the non-clinical testing performed against those standards.

Here's a breakdown of the requested information based on the provided text:

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

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 relates to non-clinical testing of the device against standards. There is no mention of a "test set" in the context of patient data or clinical performance. Therefore, sample size for a test set is not applicable (N/A) for this type of submission. The data provenance is related to in-house or contracted laboratory testing for compliance with international standards, likely performed in Switzerland (country of origin of SCHILLER AG). The testing is prospective in the sense that the device was actively tested against the standards.

3. 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. This submission focuses on engineering and safety standards compliance, not on clinical performance evaluated by medical experts establishing ground truth from patient data.

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

Not applicable. There was no "test set" in the context of clinical data requiring adjudication.

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. This device is a vital signs monitor, not an AI-assisted diagnostic tool for interpretation by human readers.

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

The device is a monitoring system for vital parameters. Its "performance" is its ability to accurately measure and display these parameters and comply with safety standards. The non-clinical tests described are essentially "standalone" performance evaluations against specified engineering and safety criteria. There is no mention of an algorithm in the sense of a diagnostic or interpretive AI, therefore, no standalone algorithm performance study as typically understood in AI/ML medical devices.

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

For the non-clinical tests, the "ground truth" is established by the defined parameters and tolerances within the referenced international standards (e.g., specific voltage levels for ESD, frequency ranges for emitted radiation, and safety requirements for medical electrical equipment). The device's performance is compared directly against these established standard requirements.

8. The sample size for the training set

The document does not describe a "training set" as it is commonly understood for AI/ML models. This device is a hardware monitoring system, not an AI/ML product that undergoes a training phase with a dataset.

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

Not applicable. No training set for an AI/ML model was used or described.

Ask a specific question about this device