Search Results

Central Station is a network device, intended to display, record and print monitored physiological data from Nihon Kohden bedside monitors, telemetry receiver and/or transmitters.

Central Station does not perform any data processing on the data received from the Nihon Kohden compatible devices. When Central Station is connected with the Nihon Kohden bedside monitors and telemetry receivers/transmitters the Central Station can:
• Admit and discharge patients on the Nihon Kohden network.
• Display and manage compatible devices' real-time patient clinical data, vital signs, alarms and waveforms.
• Review and trend data calculated by connected Nihon Kohden devices.
• Store and transfer historical clinical data for the connected systems.
• Print patient data.

Central Station is intended for use in professional medical facilities by trained medical personnel.

Central Station is software only product that is installed on a Commercial Off the Shelf (COTS) Computer.

Central Station displays waveforms data and numerical data from a connected bedside monitor, vital sign telemeter, or multiple patient receiver unit on the screen.

Central Station is a network device, intended to provide remote patient monitoring to medical personnel. Central Station displays a list of measured values and a trend graph. Numerical data and various waveforms are color-coded for each parameter. Central Station also has the function of displaying an alarm.

Alarm indication in Central Station is displayed as a result of a judgment by the bedside monitor, vital sign telemeter, or multiple patient receiver units connected to the Central Station. Central Station itself does not have the function to perform alarm indication judgment.

The provided document is a 510(k) clearance letter for the "Central Station" device. This type of document primarily focuses on establishing substantial equivalence to a legally marketed predicate device rather than detailing specific performance acceptance criteria and study results in the same way as a full clinical trial report or a detailed design validation report would.

The document states:

• "Central Station does not perform any data processing on the data received from the Nihon Kohden compatible devices."
• "Alarm indication in Central Station is displayed as a result of a judgment by the bedside monitor, vital sign telemeter, or multiple patient receiver units connected to the Central Station. Central Station itself does not have the function to perform alarm indication judgment."
• "The results of the substantial equivalence assessment, taken together with non-clinical bench testing, software verification, and validation demonstrate that the Central station does not raise concerns regarding its safety and effectiveness compared to its predicate device and operates in accordance with claimed indications for use."

Given these statements, the "Central Station" device is essentially a display, recording, and communication hub. It does not perform diagnostic algorithms or make independent judgments that would typically necessitate the kinds of detailed performance metrics (like sensitivity, specificity, or reader agreement) that are usually established through extensive multi-reader, multi-case (MRMC) studies with expert ground truth. Its primary function is to accurately display and relay data processed by other Nihon Kohden devices.

Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" for this specific device (Central Station) would primarily revolve around:

• Software Verification and Validation (V&V): Ensuring the software correctly displays, records, and transmits data as designed, and that all features (admit/discharge, trend display, printing, network communication) function as intended without errors.
• Non-Clinical Bench Testing: Confirming interoperability with compatible devices, accuracy of data display, alarm relay, and network functionality.
• Cybersecurity Compliance: Meeting regulatory requirements for cybersecurity.

The document explicitly states that "The software documentation was prepared following the FDA's 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices' (released June 14, 2023), specifically for an Enhanced Documentation Level." and "Verification testing was conducted at the system integration level to confirm that the device software fulfills its requirements and that safety and security risk mitigations, where applicable, were effective. Additionally, system-level testing was carried out to show that the software addresses user needs. All unit, integration, and system-level tests successfully met the test protocols."

Based on the provided text, it is not possible to extract the specific quantitative performance metrics (like sensitivity, specificity, or effect sizes for human readers) that would be relevant for a device performing complex data processing or diagnostic functions. The document emphasizes substantial equivalence and basic functional verification, not advanced AI/diagnostic performance validation.

However, I can infer the spirit of typical acceptance criteria and how a device like this would be proven to meet them, guided by the information provided.

Inferred Acceptance Criteria and Device Performance for "Central Station"

Given the device's stated function (display, record, print, and relay data without processing it for diagnosis or alarm judgment), the acceptance criteria would focus on functional correctness, data integrity, interoperability, and system reliability, rather than diagnostic accuracy metrics.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Test Set Sample Size: Not explicitly stated as a "sample size" in the context of patient data for diagnostic algorithms, because the device doesn't perform diagnostic processing. The "test set" for this device would be a collection of test cases covering all functional requirements, interoperability scenarios with different compatible devices, alarm conditions (relayed), data storage limits, network loads, and user interaction flows. The document mentions "system integration level" and "system-level testing" and that "all unit, integration, and system-level tests successfully met the test protocols." This implies a comprehensive set of non-clinical, bench-level tests.
• Data Provenance: Not applicable in the sense of clinical patient data (e.g., from specific countries, retrospective/prospective studies), as the device does not process primary patient data for diagnosis. The data used for testing would be simulated, generated, or derived from compatible Nihon Kohden monitor outputs in a lab setting to verify the Central Station's display and communication functions.

3. Number of Experts and Qualifications for Ground Truth

• Not Applicable in the traditional sense for diagnostic AI. The ground truth for this device's performance would be the expected output based on its functional specifications and the known inputs from the connected Nihon Kohden devices. For example, if a connected monitor transmits an HR of 70 bpm, the ground truth is that the Central Station must display 70 bpm. These "ground truths" are established by engineering design specifications, not human expert consensus on clinical findings.
• Experts Involved: Software engineers, quality assurance engineers, subject matter experts on the physiological monitoring systems, and potentially clinical users for usability and workflow testing. Their qualifications would be in device design, software development, testing, and clinical application.

4. Adjudication Method for the Test Set

• Not Applicable in the context of clinical interpretation adjudication (e.g., 2+1 radiologist consensus). Adjudication in this context would be internal to the software development and testing process:
  • Test Pass/Fail Criteria: Predetermined pass/fail criteria for each test case.
  • Bug/Defect Resolution: Issues found during testing are logged as bugs, investigated by engineers, and resolved, followed by retesting.
  • Verification Sign-off: Test leads or design engineers review test results and formally sign off on the successful completion of verification.

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

• No, not performed for this device. An MRMC study is relevant for AI systems that assist human readers in making diagnostic decisions (e.g., radiologists reading X-rays with AI assistance). The Central Station device does not perform any such diagnostic assistance; it merely displays data from other (likely already cleared) devices. Its function is analogous to a monitor or a remote display unit, not a diagnostic AI.

6. Standalone (Algorithm Only) Performance

• Not Applicable. This device does not have a "standalone algorithm" that performs diagnostic or data processing functions independently. Its function is entirely dependent on receiving data from other compatible Nihon Kohden devices.

7. Type of Ground Truth Used

• Functional Specifications and Truth from Connected Devices: The ground truth for this device is based on its functional design specifications (e.g., "display received data," "store data for X hours," "print Y parameters") and the verified output from the connected Nihon Kohden bedside monitors and telemetry systems. It's about data integrity and display accuracy, not clinical outcomes or pathology.

8. Sample Size for the Training Set

• Not Applicable. This device is described as "software only product" that "does not perform any data processing on the data received," and "Central Station itself does not have the function to perform alarm indication judgment." This strongly implies it is a rule-based or deterministic system, not a machine learning/AI system that requires a "training set" in the common sense (i.e., for learning patterns from data for prediction or classification). Therefore, there is no training set.

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

• Not Applicable. As there is no training set for an AI algorithm, there is no corresponding ground truth establishment process for a training set.

Ask a specific question about this device

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-Lead ECG, heart rate, respiratory rate, pulse rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure (NIBP) continuously, and patient posture and activity. VMS allows for the input of non-invasive blood pressure and body temperature and can display data from peripheral devices. VMS can generate alerts when rate-based cardiac arrhythmias are detected and when physiological vital signs fall outside of selected parameters.

The non-invasive Blood Pressure Tracking feature is based on Pulse Arrival Time (PAT), which is obtained utilizing ECG and PPG signals following a calibration process using an FDA-cleared oscillometric blood pressure monitor. This feature is not intended for use in critical care environment.

The Vios Central Station Monitor (CSM) and Central Server (CS) Software (SW) is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSM SW and CS SW receives, stores, manages, and displays patient physiological and waveform data and alarms generated by Vios proprietary patient vitals monitoring software.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals.

The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station.

The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices.

The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use, and rechargeable sensor that acquires 3-channel ECG, bioimpedance, 2-channel pulse oximetry, and tri-axial accelerometer data. The sensor contains signal acquisition firmware (embedded software) and wirelessly communicates acquired data via standard communication protocols (Bluetooth™) to the BSM SW for analysis and display. The Chest Sensor has a button that, when pressed, sends a patient call alert to the BSM SW.

VMS Chest Sensor Adapter Models L2050F (Pulse Ox Finger Adapter) are plastic, non-sterile, patient-worn, multiple use pulse oxygenation sensors that connect to the Vios Chest Sensor and are secured to the patient via medical grade ECG electrodes.

The provided text describes a 510(k) clearance for the Vios Monitoring System Model 2050, focusing on the addition of a blood pressure tracking feature. Here's an analysis of the acceptance criteria and the study details based solely on the provided document:

Missing Information: It's important to note that the provided FDA 510(k) clearance letter is a summary document and does not contain the detailed clinical study report or the specific acceptance criteria with numerical performance targets. It states that the device meets "all consensus standards requirement" and that "results were within the acceptance criteria," but it does not define those criteria or present detailed performance data in a table format. Therefore, I will have to make assumptions about the typical acceptance criteria for Non-Invasive Blood Pressure (NIBP) devices based on the mentioned standards (ISO 81060-2, IEEE 1708, ISO 81060-3) and then state the general reported outcome from the document.

1. Table of Acceptance Criteria and Reported Device Performance

Given the lack of specific numerical acceptance criteria and performance data in the provided document, the table below will broadly reflect typical NIBP acceptance criteria based on the mentioned standards and the general statement of performance from the text.

• Mean difference $\le \text{5 mmHg}$
• Standard deviation $\le \text{8 mmHg}$
  (Requirements per ISO 81060-2) | "The results were within the acceptance criteria, similar to the predicate device." |

Explanation of Assumption: The document explicitly states that "The clinical testing and analysis is performed according to applicable clauses from ISO 81060-2, IEEE 1708, and ISO 81060-3 for validation using reference invasive blood pressure measurement on the radial artery." ISO 81060-2 is the primary standard for non-invasive sphygmomanometers, which outlines specific statistical accuracy requirements (mean difference and standard deviation). Therefore, the acceptance criteria are assumed to be those specified in ISO 81060-2. The document does not provide numerical results for the Vios Monitoring System.

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

• Sample Size for Test Set: Not explicitly stated in the provided document. The text mentions "a range of subjects, representative of the intended population."
• Data Provenance: Not explicitly stated. The document indicates a "clinical study" was performed, but does not specify the country of origin of the data or whether it was retrospective or prospective. Given it's a clinical study for validation, it is most likely prospective.

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

This information is not provided in the document. The ground truth was established by "reference invasive blood pressure measurement on the radial artery," which is a direct, objective medical measurement, not typically requiring a panel of experts for interpretation in the same way as, for example, image interpretation.

4. Adjudication Method for the Test Set

This information is not applicable/provided as the ground truth for blood pressure measurement (invasive arterial line) is an objective, quantitative measurement that does not require expert adjudication in the same manner as subjective or qualitative assessments.

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

No, an MRMC comparative effectiveness study was not done. This type of study (comparing human reader performance with and without AI assistance) is typically performed for diagnostic imaging or similar interpretation tasks where human perception and decision-making are aided by AI. For a vital signs monitor, the primary assessment is of the device's accuracy against a known reference, not its ability to assist human readers in interpretation.

6. If a Standalone (Algorithm Only) Performance Study Was Done

Yes, a standalone performance study was done. The clinical testing described for "Blood Pressure Tracking" assesses the algorithm's accuracy in autonomously generating blood pressure values from PAT (Pulse Arrival Time) against an invasive blood pressure reference. This is an assessment of the algorithm's standalone performance.

7. The Type of Ground Truth Used

The ground truth used for the blood pressure tracking feature was invasive blood pressure measurement on the radial artery. This is considered a gold standard and highly accurate method for blood pressure determination.

8. The Sample Size for the Training Set

The document does not provide information regarding the sample size for a training set. The descriptions focus on the validation study for the blood pressure tracking feature. It is implied that the algorithm was developed (trained) prior to this validation, but the details of that training are not included in this summary.

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

The document does not provide information on how the ground truth for any training set was established. It only describes the ground truth for the clinical validation study (invasive blood pressure measurement on the radial artery) and the calibration process. The "calibration (initialization)" step uses an "FDA-cleared oscillometric blood pressure monitor" for initial coefficient determination, which is distinct from establishing ground truth for a large-scale training set.

Ask a specific question about this device

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when the physiological vital signs fall outside of selected parameters.

VMS can also generate alerts when cardias arrhythmias (Tachycardia, Asystole, Ventricular Fibrillation and Atrial Fibrillation/ Atrial Flutter) are detected.

The ECG rhythm analysis is intended for use by medified professionals in the identification of arrhythmia events and to aid in clinical review of arrhythmias and medical interventions.

The Vos CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSMCS SW receives, stores, and displays patient physiological and waveform data and alams generated by Vios proprietary patient vitals monitoring software.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use,

The Vios Monitoring System (VMS) Model 2050 was evaluated for its arrhythmia detection features, specifically assessing its performance against the ANSI/AAMI EC57:2012 standard and additional database records.

Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily references compliance with the ANSI/AAMI EC57:2012 standard for cardiac rhythm and ST-segment measurement algorithms. While specific numerical acceptance criteria (e.g., minimum sensitivity, positive predictivity) for each arrhythmia are not explicitly listed in the provided summary, the study's conclusion of meeting "performance requirements as outlined in the consensus standard ANSI/AAMI EC57:2012" implies that the device achieved the performance thresholds defined within that standard for the tested arrhythmias.

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

The document states that the device's performance was evaluated using:

• Records from the ANSI/AAMI EC57 standard. This standard often utilizes a combination of standard ECG databases (e.g., MIT-BIH Arrhythmia Database).
• Additional records from LTAF, AAEL, and VFDB databases.

The specific sample sizes (number of patients or ECG recordings) for each arrhythmia or for the combined test set are not provided in the summary. The provenance of LTAF, AAEL, and VFDB databases is not detailed; however, these are generally recognized public databases of ECG recordings used for algorithm testing, often comprising retrospective data.

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

The document does not state the number of experts used or their specific qualifications for establishing the ground truth of the test set. For publicly available and widely used databases like those mentioned (MIT-BIH, LTAF, AAEL, VFDB), the ground truth labels are typically established by multiple expert cardiologists or electrophysiologists using established criteria, often after multiple review rounds. However, this specific information is not in the provided text.

4. Adjudication Method for the Test Set:

The document does not specify the adjudication method used (e.g., 2+1, 3+1). For standard ECG databases, ground truth is usually established via expert consensus, which inherently involves an adjudication process, but the specific mechanics are not described here.

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

The document does not indicate that a multi-reader multi-case (MRMC) comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The testing described is focused on the standalone performance of the device's arrhythmia detection algorithm.

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

Yes, a standalone performance evaluation was done. The summary explicitly states: "The non-clinical tests for evaluation of performance of Vios system with the addition of arrhythmia alarms is based on ANSI/AAMI EC57, showing substantial equivalence to the predicate (K180472). The subject device's performance was also evaluated using additional records from LTAF, AAEL, and VFDB database..." This describes the algorithm's performance without direct human intervention as part of the detection process.

7. Type of Ground Truth Used:

The ground truth for the test was established through expert consensus/annotations from well-known ECG databases (ANSI/AAMI EC57, LTAF, AAEL, and VFDB). These databases contain ECG recordings that have been meticulously reviewed and annotated by medical experts (typically cardiologists or electrophysiologists) to identify and label different cardiac events and arrhythmias,
Pathology and outcomes data are not mentioned as sources for ground truth in this context.

8. Sample Size for the Training Set:

The document does not specify the sample size used for the training set of the Vios Monitoring System's arrhythmia detection algorithm.

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

The document does not specify how the ground truth for the training set was established. However, it is common practice for such algorithms to be trained on large, expertly annotated ECG datasets, similar to those used for testing (expert consensus/annotations).

Ask a specific question about this device

The Connex Central Station is intended to be used by clinicians for the central monitoring of neonatal, pediatric and adult patients in health care facilities. In addition to the central monitoring of patient data and alarms, the Connex software can include optional modules to provide extended recording of patient data, including full disclosure.

Both the Welch Allyn primary predicate and subject Connex Central Station devices are software devices for a Windows-based operating system that provide clinicians with a means to remotely monitor the health of several patients simultaneously.

This document is a 510(k) summary for the Welch Allyn Connex Central Station (v.1.8.5). It primarily focuses on demonstrating substantial equivalence to a predicate device, not on presenting a detailed study proving performance against specific acceptance criteria for a new AI/ML device.

Therefore, many of the requested details regarding acceptance criteria, study design, expert qualifications, and ground truth establishment for an AI/ML model are not present in this document. The document states "No clinical studies were utilized for the purpose of obtaining safety and effectiveness data." and refers to software verification and validation, and adherence to various medical device standards.

However, based on the provided text, I can infer and extract some relevant information as best as possible, particularly regarding the non-clinical testing performed and the nature of the device.

Here's an attempt to answer your questions based on the provided text, noting where information is explicitly not available for an AI/ML context:

Acceptance Criteria and Device Performance (Inferred)

Since this is a submission for substantial equivalence based on a predicate device and not a new AI/ML algorithm requiring performance metrics like sensitivity/specificity against a ground truth, the "acceptance criteria" here are primarily met through software verification and validation testing and adherence to recognized medical device standards. The performance is not reported as specific clinical metrics but rather as meeting the functional and safety requirements for a central patient monitoring station.

The key change is the addition of ECG parameter display from another cleared device (Welch Allyn CVSM, K171621), and the acceptance is that this integration does not introduce new safety or effectiveness concerns.

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

• Test Set: Not applicable in the context of an AI/ML test set with patient data. The "testing" here refers to software verification and validation activities and compliance with standards. There's no mention of a "test set" of patient data for performance evaluation in the way an AI/ML algorithm would use it.
• Data Provenance: Not applicable. The document refers to "well-established, scientific methods" for evaluating new ECG parameter features, but this is about the display of parameters already collected by another cleared device (CVSM, K171621), not new data analysis or inference from a patient data set by the Connex Central Station itself.

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

• Not applicable. This submission does not involve establishing ground truth for an AI/ML algorithm's clinical performance. The ground truth for the ECG parameters themselves would have been established during the clearance of the Welch Allyn CVSM (K171621), but that's not detailed here.

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

• Not applicable. This is not an AI/ML study involving human readers and adjudicated ground truth.

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 explicitly states: "No clinical studies were utilized for the purpose of obtaining safety and effectiveness data."

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

• Not applicable. This device integrates and displays data from other cleared devices; it's a central monitoring station, not an AI/ML algorithm that operates "standalone" to produce a diagnostic or prognostic output from raw data. Its "performance" is based on its ability to accurately receive, process, and display parameters from connected devices and manage alarms, complying with relevant standards.

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

• Not applicable in the context of an AI/ML performance study for this submission. The "ground truth" for the displayed ECG parameters originates from the cleared Welch Allyn CVSM device (K171621), which would have undergone its own validation. For the central station itself, the "ground truth" lies in its adherence to functional specifications, risk management, and the standards listed (e.g., IEC 62304 for software, IEC 60601-2-27 for ECG monitoring equipment safety aspects relevant to its display).

8. The sample size for the training set:

• Not applicable. This device is not an AI/ML algorithm that undergoes a training phase with a dataset.

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

• Not applicable. (See point 8).

Summary of what the document DOES tell us about the "study":

The "study" or evaluation performed was primarily:

• Software Verification and Validation (V&V): This involved testing the software against its design requirements and functional specifications. The "level of concern" for the software was "Major" (meaning a failure could result in serious injury or death).
• Compliance with Recognized Standards: The device was tested to evaluate its performance based on various international standards for medical devices, specifically:
  • IEC 62366-1:2015 (Usability Engineering)
  • IEC 60601-1-8:2012 (Basic Safety and Essential Performance)
  • IEC 62304:2015 (Medical Device Software - Software Life Cycle Processes)
  • IEC 60601-2-27:2011 (Electrocardiographic Monitoring Equipment Safety)
  • ISO 14971:2019 (Risk Management)
  • AAMI 80001-1:2010 (Risk Management for IT networks with medical devices)
  • ISO 15223-1:2016 (Symbols for labeling)
  • FDA Special Controls Guidance for Arrhythmia Detector and Alarm (October 28, 2003).

The key finding from this "study" or evaluation was that even with the new feature (displaying ECG parameters), the device continues to meet these standards and its design requirements, and therefore remains substantially equivalent to its predicate, raising no new questions of safety or effectiveness.

Ask a specific question about this device

The Vios CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSM/CS SW receives, stores, manages, and displays patient physiological and waveform data and alarms generated by Vios proprietary patient vitals monitoring software.

The Vios CS SW enables the Vios Monitoring System to be used in networked mode within a healthcare IT network and runs on commercial IT equipment. The Vios CS SW operates as a communications hub that can pass the data generated by Vios proprietary vitals monitoring software to one or more remote viewing software applications, without modifying the data. The Vios CSM SW is the remote viewing software of the Model 2050 system. It allows up to 16 devices to be displayed on one screen and runs on a commercial IT device that satisfies defined Vios-defined technical specifications.

The provided text does not contain information about the acceptance criteria and study proving device performance for Vios Central Station Monitor/Central Server Software Model 2050. The document is an FDA 510(k) clearance letter and summary, which confirms substantial equivalence to a predicate device but does not detail specific performance studies with acceptance criteria, sample sizes, ground truth establishment, or expert involvement.

Therefore, I cannot fulfill your request for the detailed performance information based on the provided input.

Ask a specific question about this device

The CARESCAPE Central Station is intended for use under the direct supervision of a licensed healthcare practitioner. The intended use is to provide clinicians with adult, pediatric and neonatal patient data within a hospital or clinical environment.

The CARESCAPE Central Station is intended to collect, display and print information from a network, including patient demographics, physiological parameters and waveforms, alarm annunciation and/or other non-medical information from monitors and telemetry systems. Physiological parameters and waveforms include electrocardiograph (ECG), pulse oximetry (SPO2), invasive blood pressures (IBP), non-invasive blood pressure (NIBP), respiration (RR), ventilator (VNT), carbon dioxide (CO2), oxygen (O2), mass spectrometry (Gas), temperature (Temp) and bispectral index (BIS). Beat to beat patient information for parameters and waveforms from the bedside and telemetry systems can be displayed. Patient monitor and telemetry system settings can be adjusted. Parameter values derived from patient data can be calculated, displayed, and printed.

The CARESCAPE Central Station supports the ability to access information from GE products and hospital intranet in a web browser format. Additionally, CARESCAPE Central Station supports the ability to access patient information collected from the CARESCAPE network and stored on a network server.

The CARESCAPE Central Station (CSCS) is based on a PC technology platform and is user friendly for easy operation using a simple logical screen menu. The interactive controls include the use of a computer mouse, keyboard and touch screen. Optional writers for the purpose of graphing waveforms and printing patient information include a 2-inch Direct Digital Writer and/or a laser printer. Internal speakers provide alarm audio indication.
The CSCS provides centralized monitoring of patients connected to GE Medical Systems Information Technologies, Inc.'s monitors and telemetry transmitters. It may be configured to display up to four real-time waveforms per patient for up to 16 patients and up to 9 waveforms for a single selected patient. Waveforms include ECG, SPO2, respiration ventilation flow and pressure, invasive blood pressure and CO2.
The device acts as a (1) viewing station, (2) reviewing station and (3) live monitoring station by obtaining its information from acquisition devices off the CARESCAPE network.
Patients may be admitted to and discharged from monitors and telemetry devices from the central location. The central station is also the control and display device for telemetry monitoring.
The CSCS provides secondary annunciation of alarms from primary bedside monitoring devices and primary annunciation of alarms from wireless telemetry devices.
The display window for each patient shows waveforms and vital information including: patient name, bed number, arrhythmia and alarm visual indicators, system messages, audio pause indicator, audio alarm indicator, alarm message line, heart rate, PVC count, transmitter number, ECG lead label, pacemaker status, ST measurement, and graph status. Physiological parameter values and waveforms from the GE Medical Systems Information Technologies, Inc.s' monitors can be displayed and printed from the CSCS.
Non-real time patient information available for reviewing and printing includes: Graphic Trends, Tabular Numeric Vital SignsTrends, Event HistoryReview, Full Disclosure, Calipers, and ST Review. Data can be printed to a networked laser printer. In the case of Event Review, data can also be printed to a PDF file.
The CARESCAPE Central Station also provides remote control of patient monitor and telemetry device configuration settings that includes:

• Admitted patient demographics like name and medical record number;
• Alarm Settings like high/low limit values and alarm priority levels:
• Printing settings like selection of which waveforms to print on graphs and the printed output destinations;
• ECG settings like primary lead selection, ST analysis on/off and pace maker detection on/off;
  Initiate and terminate combination monitoring where a bedside patient monitor accepts ECG data from a telemetry transmitter:
• Non-ECG parameter settings like respiration lead selection and NBP cuff size selection.
  The Full Disclosure option provides up to 144 hours of beat-tobeat patient information from the bedside or telemetry system for parameters and waveforms. Full Disclosure also stores resting ECGs from 16 patients once per minute for 144 hours and up to 2000 alarm histories with waveform snippets for each patient. This information can be displayed at the CSCS in detailed and summary mode formats.

The provided document (K162012) describes the CARESCAPE Central Station v2, a medical device intended for collecting, displaying, and printing patient data. However, the document does not contain specific acceptance criteria, study data, or performance metrics for the device's functionality in a format that would allow the completion of the requested table and detailed study information.

This document is a 510(k) premarket notification letter from the FDA, confirming substantial equivalence based on a review of submitted information. It primarily focuses on the device's intended use, classification, and a high-level comparison to predicate devices, along with a summary of non-clinical testing. It explicitly states: "The subject of this premarket submission, CARESCAPE Central Station, did not require clinical studies to support substantial equivalence."

Therefore, I cannot provide the requested information. The document does not include data like precision, recall, or other performance metrics, nor does it detail how ground truth was established for a testing or training set, or mention any MRMC studies.

However, I can extract the information that is present in the document:

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

This information is not present in the document. The document lists general testing activities but no specific performance metrics or acceptance criteria in a quantitative format.

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

This information is not present in the document. The document mentions "Testing on unit level," "Integration testing," "Performance testing," "Safety testing," and "Simulated use testing," but does not provide details on sample sizes, data provenance, or the nature of the test sets used.

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)

This information is not present in the document. As no clinical studies were deemed necessary, there is no mention of expert-established ground truth for a test set.

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

This information is not present 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

This information is not present in the document. The device description does not indicate the presence of AI, and no MRMC study is mentioned.

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

This information is not present in the document. The device is described as a "central station," a viewing, reviewing, and live monitoring station with human-in-the-loop interaction.

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

This information is not present in the document.

8. The sample size for the training set

This information is not present in the document. The device is a "software driven device running on a PC platform" and primarily serves to display and manage data from other medical devices; it is not described as involving machine learning or AI models developed through training sets.

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

This information is not present in the document.

Summary of what can be found regarding testing:

The document states:

• Non-Clinical Tests: "The CARESCAPE Central Station and its applications were tested to, and comply with, applicable voluntary standards. The CARESCAPE Central Station was tested to assure that the device meets its design specifications."
• Quality Assurance Measures applied to development and testing:
  • Risk Analysis
  • Requirements Reviews
  • Design Reviews
  • Testing on unit level (Module verification)
  • Integration testing (System verification)
  • Performance testing (Verification)
  • Safety testing (Verification)
  • Simulated use testing (Validation)
• Clinical Studies: "The subject of this premarket submission, CARESCAPE Central Station, did not require clinical studies to support substantial equivalence."

Based on the nature of the device (a central monitoring station for physiological data) and the fact that no clinical studies were required, the testing likely focused on functional verification, system integration, software validation, and adherence to safety and performance standards for displaying and managing data, rather than on diagnostic accuracy or AI-driven interpretations.

Ask a specific question about this device

The CARESCAPE Central Station is intended for use under the direct supervision of a licensed healthcare practitioner. The intended use is to provide clinicians with adult, pediatric and neonatal patient data within a hospital or clinical environment.

The CARESCAPE Central Station is intended to collect, display and print information from a network, including patient demographics, physiological parameters and waveforms, alarm annunciation and/or other non-medical information from monitors and telemetry systems. Physiological parameters and waveforms include electrocardiograph (ECG), pulse oximetry (SPO2), invasive blood pressures (IBP), non-invasive blood pressure (NIBP), respiration (RR), ventilator (VNT), carbon dioxide (CO2), oxygen (O2), mass spectrometry (Gas), temperature (Temp) and bispectral index (BIS). Beat to beat patient information for parameters and waveforms from the bedside and telemetry systems can be displayed. Patient monitor and telemetry system settings can be adjusted. Parameter values derived from patient data can be calculated, displayed, and printed.

The CARESCAPE Central Station supports the ability to access information from GE products and hospital intranet in a web browser format. Additionally, CARESCAPE Central Station supports the ability to access patient information collected from the CARESCAPE network and stored on a network server.

The CARESCAPE Central Station (CSCS) is based on a PC technology platform and is user friendly for easy operation using a simple logical screen menu. The interactive controls include the use of a computer mouse and keyboard and optional touch screen. Optional writers for the purpose of graphing waveforms and printing patient information include a 2-inch Direct Digital Writer and/or a laser printer. Internal and external speakers provide alarm audio indication.

The CSCS provides centralized monitoring of patients connected to GE Medical Systems Information Technologies' monitors and telemetry transmitters. It may be configured to display up to four real-time waveforms per patient for up to 16 patients and up to 9 waveforms for a single selected patient. Waveforms include ECG, SPO2, respiration ventilation flow and pressure, invasive blood pressure and CO2.

Patients may be admitted to and discharged from monitors and telemetry devices from the central location. The central station is also the control and display device for telemetry monitoring. Patient demographic information, including medical record number and patient name made be entered and modified.

The display window for each patient shows waveforms and vital information including: patient name, bed number, arrhythmia and alarm visual indicators, system messages, audio pause indicator, audio alarm indicator, alarm message line, heart rate, PVC count, transmitter number, ECG lead label, pacemaker status, ST measurement, and graph status. Physiological parameters and waveforms from the GE Medical Systems Information Technologies' monitors can be displayed and printed from the CSCS.

Non-real time patient information available for reviewing and printing includes: Graphic Trends, Tabular Numeric Vital SignsTrends, Event HistoryReview, Full Disclosure, Calipers, and ST Review. Data can be printed to a networked laser printer. In the case of Event Review, data can also be printed to a PDF file.

The CARESCAPE Central Station also provides remote control of patient monitor and telemetry device configuration settings that includes:

• . Admitted patient demographics like name and medical record number;
• . Alarm Settings like high/low limit values and alarm priority levels;
• Printing settings like selection of which waveforms to . print on graphs and the printed output destinations;
• ECG settings like primary lead selection, ST analysis ● on/off and pace maker detection on/off;
• Initiate and terminate combination monitoring where a . bedside patient monitor accepts ECG data from a telemetry transmitter;
• Non-ECG parameter settings like respiration lead ● selection and NBP cuff size selection.

The CSCS provides secondary annunciation of alarms from primary bedside monitoring devices and primary annunciation of alarms from wireless telemetry devices.

The Full Disclosure option provides up to 144 hours of beat-to-beat patient information from the bedside or telemetry system for parameters and waveforms. Full Disclosure also stores resting ECGs from 16 patients once per minute for 144 hours and up to 2000 alarm histories with waveform snippets for each patient. This information can be displayed at the CSCS in detailed and summary mode formats.

Here's a summary of the acceptance criteria and study information for the CARESCAPE Central Station, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document primarily focuses on non-clinical testing and comparison to predicate devices, rather than explicit numerical acceptance criteria for performance metrics like sensitivity, specificity, or accuracy for a medical AI device.

2. Sample Size for Test Set and Data Provenance

• Sample Size for Test Set: Not explicitly stated as this was a non-clinical study. The "test set" here refers to the system and its functions during various testing phases (unit, integration, performance, safety, simulated use).
• Data Provenance: Not applicable in the context of clinical data for an AI model. The testing was focused on the device's functionality and compliance with standards.

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

• Number of Experts: Not applicable. The "ground truth" for this device's functionality and compliance was based on design specifications, voluntary standards, and quality assurance processes, rather than expert medical interpretation of data.
• Qualifications of Experts: Not applicable in the context of clinical ground truth. The development and testing would have involved engineers, quality assurance personnel, and regulatory affairs experts.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. This was a non-clinical study focused on device functionality and compliance, not on clinical interpretations requiring adjudication.

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

• Study Performed? No. The document explicitly states: "The subject of this premarket submission, CARESCAPE Central Station, did not require clinical studies to support substantial equivalence." This type of study would typically be conducted for diagnostic or interpretive AI devices.
• Effect Size of Human Readers Improvement with AI: Not applicable, as no MRMC study was conducted.

6. Standalone (Algorithm Only) Performance Study

• Study Performed? No. The device is a "Central Station" software application running on PC technology to collect, display, and manage patient data and alarms from other medical devices. It is not an algorithm designed for standalone diagnostic or interpretive performance.

7. Type of Ground Truth Used

• Type of Ground Truth: For the non-clinical tests, the "ground truth" was established by the device's design specifications, established engineering principles, and compliance with applicable voluntary standards (e.g., IEC 60601-1-8:2006 for alarm tones).

8. Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. The CARESCAPE Central Station is a software-driven device for data management and display, not a machine learning or AI model that requires a "training set" of data in the conventional sense. The "training" here refers to the software development and testing phases.

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

• Ground Truth Establishment for Training Set: Not applicable. As described above, this device does not use a "training set" in the context of machine learning. The development and verification processes followed standard software engineering and quality assurance practices, ensuring the system met its intended specifications and safety requirements.

Ask a specific question about this device

The Connex Central Station (CS) is intended to be used by clinicians for the central monitoring of neonatal, pediatric, and adult patients in health care facilities. In addition to the central monitoring of patient data and alarms, the Connex software can include optional modules to provide extended recording of patient data, including full disclosure.

Connex Central Station, also known as Monitoring Station, is a Windows-based product that provides clinicians with a means to remotely monitor the health of several patients simultaneously. The Monitoring Station receives patient vital signs and alarm data from patient monitors and spot check devices over a network, then displays the data and sounds audio alarms in a centralized location.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Welch Allyn Monitoring Station (Connex Central Station), K132807.

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It primarily details non-clinical verification and validation testing, rather than a traditional clinical study with defined acceptance criteria and detailed performance metrics as one might see for a diagnostic AI device. Therefore, some of the requested information (like specific performance metrics, sample sizes for test/training sets with provenance, expert qualifications for ground truth, adjudication methods, MRMC studies, or standalone performance) is not explicitly present or isn't applicable in the context of this type of submission for a patient monitoring central station.

1. Table of Acceptance Criteria and Reported Device Performance

For each "Test Objective" below, the implicit acceptance criteria is that the test objective is met and the explicit reported performance is "Pass".

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

• Sample Size: Not specified in terms of number of patients or specific data points. The testing describes functional, performance, and usability tests on the device and its various new features.
• Data Provenance: The document does not mention specific clinical data or patient data being used for these non-clinical tests. It implies simulated environments or direct device-to-device communication for testing functionalities like alarm delivery or data display. The tests are "Non-Clinical Tests."

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

• Number of Experts: Not applicable. The "ground truth" for these tests relates to the expected functional behavior of the software and hardware according to design specifications and standards.
• Qualifications of Experts: Not applicable. These were verification and validation tests against pre-defined specifications rather than expert interpretation of clinical data.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. The tests are pass/fail based on whether the system performs as expected, not on subjective interpretations requiring adjudication.

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

• Was it done? No. The document explicitly states: "No clinical studies were utilized for the purpose of obtaining safety or effectiveness data." This submission is for a central monitoring station, not a diagnostic AI device requiring MRMC studies.

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

• Was it done? In a sense, yes, for specific functionalities. The tests described are primarily standalone device performance tests, verifying the software and hardware functions as designed, independent of human interaction within the test (though human users were involved in usability testing). However, this is not a "standalone algorithm" in the context of typical AI device evaluation. The device itself is designed for human-in-the-loop operation by clinicians.

7. Type of Ground Truth Used

• Type of Ground Truth: The ground truth for these non-clinical tests is established by the device's design specifications, relevant industry standards (IEC, ISO), and functional requirements for the software and hardware features. For usability testing, it would be adherence to pre-defined usability requirements.

8. Sample Size for the Training Set

• Sample Size: Not applicable. This is a traditional software/hardware medical device, not an AI/ML device that requires a training set in the typical sense.

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

• Ground Truth Establishment: Not applicable, as there is no "training set." The device's functionality is based on deterministic programming and hardware design, not machine learning from a data set.

Ask a specific question about this device

The Surveyor Central Station system is intended for monitoring of physiological waveforms, including cardiac and vital signs, for multiple patients within a medical facility. The system can receive, display and store data from multi-parameter patient monitors and/or telemetry systems. The system can support patient monitoring and telemetry monitoring modes simultaneously. Patient monitors can be the Surveyor S12 and S19 patient monitoring systems (K12356) or other compatible patient monitors. Ambulatory telemetry transmitter sources can be the X12+ (K974149) and T12/T12S (K022618) systems or other compatible telemetry transmitters.

In palient monitoring mode, the patient monitors will provide primary monitonality while the Surveyor Central Station system provides continuous secondary monitoring of patients including alarm reception and management, display and storage of parameters and waveforms including full-disclosure, automatic and ondemand generation of various printed reports using a network-attached printer.

In telemetry monitoring mode, the Surveyor Central Station will provide primary monitoring of patients including display of values and waveforms, alarm generation and management, data storage, patient management and report printing functionality. Patients are monitored through telemetry, when moving in a defined area, of a variable size depending on system layout. In order to provide proper coverage, an antenna network can be installed according to customer needs.

The data and analysis provided by the Surveyor Central Station is reviewed, confirmed, and used by trained medical personnel in the diagnosis of patients with various conditions.

The Mortara Surveyor Central Station is indicated for use:

• In a clinical setting, by qualified medical professionals, properly trained for patient monitoring and use of the system. Continuous analysis is provided for all patients. The personnel must be experienced in cardiovascular problematic situations and emergency procedures or pathologies related to cardiac involvements.
• Centralized monitoring through a network of patients in Coronary Care Units, Intensive Care Units, Ambulatory Care Units (Telemetry Units), Step-Down Units, Operating Rooms, Emergency Departments and Surgical Centers. Evaluation of adult and pediatric patients with symptoms suggesting arrhythmia. Detected arrhythmias create an audiovisual alarm according to the alarm profile.
• Chest Pain Evaluation.
• Evaluation of patients with pacemakers.
• Evaluation of a patient's response after resuming occupational activities (e.g., after M.I. or cardiac surgery.)
• Evaluation of monitored parameters documenting therapeutic interventions in individual patients or groups of patients.
• Clinical and epidemiological research studies.

The system architecture of the Surveyor Central Station system is flexible and can be supported on a single workstation computer or multiple workstation computers along with a separate optional storage server. Each workstation can display information for a variable number of patients. Multiple workstations can be combined to expand the system capacity. All data received for all patients is stored and available for review.

Cardiac parameters and functions supported through interface with patient monitors include 3 or 5 lead ECG as well as 12-lead ECG along with interpretation plus continuous monitoring and management of arrhythmia and ST alarms generated by the patient monitor. Cardiac parameters and functions supported through interface with telemetry systems include 12-lead ECG along with interpretation plus continuous monitoring, alaming and management of arrhythmia and ST generated by the Surveyor Central.

Other parameters received from patient monitors or telemetry systems can include invasive pressures, noninvasive blood pressure, pulse oximetry, CO2 capnography, respiration, temperature, cardiac output and hemodynamic calculations including relevant values, indices and waveforms.

This document is primarily a 510(k) summary for the Mortara Surveyor Central Station system, focusing on demonstrating substantial equivalence to predicate devices rather than deeply detailing performance studies with specific acceptance criteria and statistical results for an AI/algorithm.

Based on the provided text, the device in question, the Mortara Surveyor Central Station, is a physiological patient monitor and central station system. It is not an AI-driven device or an algorithm in itself, but rather a system that receives and displays data from patient monitors and telemetry systems, including cardiac parameters and arrhythmia/ST alarms that may involve interpretation by other connected devices.

Therefore, the requested information regarding AI/algorithm performance (e.g., sample sizes for test/training sets, number of experts for ground truth, MRMC studies, standalone performance) is largely not applicable to this specific submission.

Here's a breakdown of what is available and why other details are missing:

Description of Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria

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

The document states:

• "Software for the Mortara Surveyor Central Station was designed and developed according to a robust software development process, and was rigorously verified and validated. Test results indicated that the Mortara Surveyor Central Station complies with its predetermined specification."
• "The Mortara Surveyor Central Station was tested in accordance with internal requirements and procedures, and test results indicated that the device complies with the predetermined requirements. This testing includes performance and functional."
• "The Mortara Surveyor Central Station was evaluated for patient safety in accordance with applicable Standards."
• "The Mortara Surveyor Central Station was tested for EMC in accordance with applicable Standards. Test results indicated that the Mortara Surveyor Central Station complies with its predetermined specification."

Acceptance Criteria & Performance Table (Based on provided text):

Missing Information: The document does not provide specific quantitative acceptance criteria (e.g., specific alarm accuracy percentages, display refresh rates, data throughput) or the numerical results from these tests. It only states that the device "complies" or "was evaluated in accordance with."

The following points are mostly not applicable to this 510(k) submission, as it concerns a central monitoring station for displaying data from other devices, not an independent AI/algorithmic diagnostic tool.

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

• Not applicable / Not specified for an AI algorithm. The testing mentioned (software, functional, electrical safety, EMC) is bench testing of the system itself, not performance evaluation against a clinical dataset for an AI model.
• The document states: "Performance Testing - Clinical: Clinical performance testing was not performed and is not necessary to demonstrate safety and effectiveness of the Mortara Surveyor Central Station."

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. No ground truth from expert consensus or clinical data was established for the central station system's performance in this submission, as there was no clinical performance testing the central station's diagnostic capabilities. The system displays interpretations from other devices.

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

• Not applicable. No clinical test set requiring adjudication was used for the central station in this 510(k).

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 study was not done. The device is a central station for displaying data, not an AI assistant intended to improve human reader performance.

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

• Not applicable. This device is a central station system, not a standalone algorithm. While it performs functions like alarm management, its primary role highlighted in this document is receiving, displaying, and storing data from other patient monitors/telemetry systems. The statement "The patients monitors will provide primary monitorality while the Surveyor Central Station system provides continuous secondary monitoring" (in patient monitoring mode) further reinforces this. In telemetry mode, it does provide primary monitoring, alarm generation, and data storage, but the functions are related to the system's own components and data handling, not a diagnostic algorithm.

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

• Not applicable. No clinical ground truth was established or used for the performance evaluation of the central station in this 510(k). The system relies on data and interpretations generated by the connected patient monitors and telemetry systems.

8. The sample size for the training set:

• Not applicable. This device is not an AI/ML algorithm that requires a training set in the conventional sense. Its software development followed a "robust software development process" which implies standard software engineering verification and validation, not machine learning training.

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

• Not applicable. As there is no training set for an AI/ML algorithm for this central station, no ground truth needed to be established for it.

Ask a specific question about this device

The Spacelabs Healthcare Xhibit Central Station, Model 96102 intended use is to provide clinicians with central monitoring of adult, pediatric and neonatal patient data of patients connected to networked Spacelabs Healthcare patient monitors and telemetry transmitters. Data includes physiological waveforms and calculations, cardiac arrhythmia and ST data, and patient demographic information to monitor adequacy of treatment or to exclude causes of symptoms. The Spacelabs Healthcare Xhibit Central Station, Model 96102 is a prescription device intended for use under the direct supervision of a licensed healthcare professional.

The Spacelabs Healthcare (Spacelabs) Xhibit Central Station, Model 96102 (Xhibit), is a new version of currently marketed Spacelabs product. Xhibit offers remote surveillance of patient data for those patients connected to a Spacelabs Healthcare Ultraview, Ultraview SL bedside monitor, or telemetry system. Xhibit provides for data communication using the TCP/IP network protocol employed in the Spacelabs Patient Care Management network of hardwired and/or telemetry monitored patients. Xhibit is not the primary alarming device for the Ultraview or Ultraview SL telemetry system.

The provided 510(k) summary (K122146) details the Spacelabs Healthcare Xhibit Central Station, Model 96102. The document describes various performance tests conducted to establish its safety and effectiveness.

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

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly present a table of quantitative acceptance criteria with corresponding performance metrics for the device's clinical efficacy (e.g., arrhythmia detection accuracy). Instead, the performance testing focuses on compliance with established standards and internal requirements.

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

The document does not provide information regarding a specific "test set" in the context of clinical performance data, such as a dataset of patient physiological waveforms for evaluating alarm accuracy or arrhythmia detection. The testing described is primarily focused on engineering and software validation. Therefore, there is no information on sample size or data provenance (country of origin, retrospective/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. Since there's no mention of a clinical test set requiring expert ground truthing, this detail is absent.

4. Adjudication method for the test set

This information is not provided. As no clinical test set requiring ground truth is mentioned, an adjudication method is not applicable in the documented testing.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not described or referenced in the provided text.

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

The device is a "Central Station Remote Monitor" that displays physiological data and alarms. Its function is to facilitate human monitoring, not to operate as a standalone diagnostic algorithm. Therefore, a standalone algorithmic performance study, as typically understood for AI-based diagnostic devices, was not reported. The performance testing focuses on the system's compliance with safety and operational standards.

7. The type of ground truth used

For the engineering and software testing described, the "ground truth" would be the specifications and requirements defined by the manufacturer and the relevant national and international standards (e.g., IEC 62304, IEC 60601-1-2, IEC 60601-1-8, IEC 62366). There's no mention of clinical ground truth derived from expert consensus, pathology, or outcomes data for assessing diagnostic accuracy.

8. The sample size for the training set

This information is not provided. The document describes a traditional medical device submission, not one for an AI/ML-based device that would typically involve a separate training set. The "software development process" mentioned refers to conventional software engineering, not machine learning model training.

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

This information is not provided, as no training set for an AI/ML model is mentioned.

Summary of Device and Study Focus:

The K122146 submission for the Spacelabs Healthcare Xhibit Central Station, Model 96102, primarily focuses on demonstrating substantial equivalence to a predicate device (Philips Medical Systems Intellivue M3290A). The studies cited are primarily engineering validation and verification tests ensuring compliance with established medical device safety, software development, electromagnetic compatibility, and alarm system standards. The document does not present a clinical performance study with defined acceptance criteria for diagnostic accuracy, sensitivity, or specificity, nor does it involve clinical ground truth, expert readers, or AI/ML components requiring training and test sets in the context of this summary. The "performance testing" referenced is about the system's operational adherence to standards, not a clinical trial of its diagnostic capabilities.

Ask a specific question about this device