(169 days)
AirStrip ONE Web Client with ACM is intended to allow clinicians to capture and display waveforms (such as ECG, SpO2, ART), discrete parameters, patient demographics, alarms, and other information from medical devices on a desktop device. This software is intended as a diagnostic aid to provide access for professional staff to view patient clinical data when the professional cannot observe the source system directly. AirStrip ONE Web Client with ACM does not store Protected Healthcare Information on the device accessing the data. Data available on the web viewer is in "near real time" and is displayed to show a full range of clinical data available, even when the data sources are obtained from different devices.
AirStrip ONE Web Client with ACM gathers data from the medical devices that are connected to the patient. AirStrip ONE Web Client with ACM is not directly connected to the individual, but to a networked medical device receiving data, and connects that data to individuals by medical record number or defined patient ID. AirStrip ONE Web Client with ACM is intended to be used by clinicians for the following purposes:
• To visualize physiological data using a web viewer to assess clinical status of a patient when the source system cannot be observed directly by the clinician.
- · To view the near real-time and historic waveforms.
· To view other near real-time patient data from a monitored system.
· To provide a request for remote consultation regarding a patient's waveform or other data.
- · To send electronic images of the cardiac rhythm to the medical record.
- · To allow clinicians to manage secondary alarm transmission by suppressing non-critical alarms.
AirStrip ONE Web Client with ACM is appropriate for use in pediatric (0-21 years), adult and geriations, as the networked medical devices AirStrip collects data from are already cleared for these populations. AirStrip ONE Web Client with ACM software can display the following physiologic parameters and waveforms captured by other cleared medical devices:
- · ECG Waveform
- · Heart Rate
- · Respiratory Rate
- · Oxygen Saturation
- Intracranial Pressure
- · Central Venous Pressure
- Pulmonary Capillary Wedge Pressure
- Pulmonary Artery Pressure
- Cardiac Index
- Cardiac Output
- · Cerebral Perfusion Pressure
- · Temperature
- · Temperature Source o Bispectral index (BIS) o Umbilical Artery
- o Body Weight
- Systolic Blood Pressure Invasive
- · Mean Arterial Pressure Invasive
- Diastolic Blood Pressure Invasive
- · Systolic Blood Pressure Cuff
- · Mean Arterial Pressure Cuff
- · Diastolic Blood Pressure Cuff
- Vasoactive Infusions
- Ventilators
- · Allergies
- IV Fluid Delivery Rate
- IV Medication Dose
- Pulse Rate
- Bispectral Parameters
- Monitored Events
- Right Atrial Pressure
- · Left Atrial Pressure
- · Laboratory Data, including
- o Blood Gas
- o Chemistry
- o Hematology
- o Coagulation
- · Hemodynamic Calculated Values
- · Medications
- IV Volume Infused
- · ETCO2
- · Fractional Inspired Concentration O2, CO2
- Case Consumption Liquid Medications
- · Case Consumption Respiratory Gas
The AirStrip Technologies, Inc. (AirStrip) ONE Web Client, the predicate device being modified to include the AirStrip Alarm Communication Management (ACM), provides visualization of monitoring data, waveforms, and events for clinicians who are away from the bedside to support and enhance their collaboration with other care team members who are with the patient.
All data, waveforms and events displayed by AirStrip ONE Web Client are generated by primary monitors, not by AirStrip ONE Web Client. Events that triggered alarms by the primary monitor system populate in AirStrip ONE Web Client in near real time so a remote (i.e. not at bedside) clinician can review these items while they are collaborating with other care team members.
The AirStrip ONE Web Client remote patient monitoring is a visualization and collaboration aid. It allows for the display of waveform, monitoring data, and events that triggered primary patient monitor alarms without itself originating alarms. The clinical use of AirStrip ONE Web Client presupposes nurses or other clinicians will be at the hospital, either at the bedside or a near-by monitoring station.
The AirStrip ONE Web Client with Alarm Communication Management (ACM) module is a "rules engine" module that, when used in conjunction with, and as a part of, the existing AirStrip ONE Web Client to gather alarms from various alarm sources, processes the alarms through a rules configuration tool (the proposed device) using clinical rules established by the customer, typically a healthcare institution, to filter and distribute those alarms to a third-party server connected to mobile devices carried by healthcare providers. The display device stays in a notification state until the healthcare provider dispositions the alarm.
The provided text describes the regulatory clearance of a medical device, the AirStrip ONE Web Client with Alarm Communication Management (ACM), and highlights its substantial equivalence to a predicate device. However, it does not contain the specific details required to answer the prompt regarding acceptance criteria and a study proving the device meets those criteria, particularly in the context of an AI/algorithm-driven diagnostic aid.
The device described is primarily a visualization and communication system for existing physiological monitoring data, with an added "rules engine" for alarm management. It does not appear to be an AI/algorithm for diagnostic purposes, nor does it conduct standalone diagnostic assessments. Therefore, detailed information about acceptance criteria for diagnostic performance (like sensitivity, specificity, AUC), ground truth establishment by experts, MRMC studies, or training/test set sample sizes for an AI model are not present in this document because they are likely not applicable to the device's function.
The "Summary of Performance Testing" section focuses on software development processes, risk management, and cybersecurity, not on clinical performance metrics typically associated with AI/diagnostic algorithms.
Given the information provided, here's what can be inferred and what cannot be answered:
What Can Be Inferred/Answered (based on the document's content):
- 1. A table of acceptance criteria and the reported device performance: Not explicitly provided in terms of diagnostic performance metrics. The performance testing section mentions "complies with its predetermined specifications" and "complies with internal requirements" related to software development, risk control, and cybersecurity (e.g., ISO/IEC 27001 certification, code analysis, network test scan, interoperability verification). These are acceptance criteria for software quality and security, not for diagnostic accuracy.
- 2. Sample sized used for the test set and the data provenance: Not mentioned, as it's not a diagnostic performance study. The data provenance (country, retrospective/prospective) is also not specified for any testing.
- 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable and not mentioned, as there's no diagnostic ground truth being established by experts for algorithmic performance.
- 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable and not mentioned for the same reasons as above.
- 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: Not applicable and not mentioned. The device is not an AI assistance for human reader interpretation. It's a data visualization and alarm management tool.
- 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable and not mentioned. The device is explicitly stated as an "adjunct to and not a replacement for direct viewing of the monitoring medical device(s)." Its purpose is to display data from other devices.
- 7. The type of ground truth used: Not applicable in the context of algorithmic diagnostic performance. For software validation, the "ground truth" would be compliance with specifications, which is verified through testing like "Risk Control Measure Verification," "Dynamic Code Analysis," etc.
- 8. The sample size for the training set: Not applicable and not mentioned, as this is not an AI/ML device that requires a training set of data.
- 9. How the ground truth for the training set was established: Not applicable and not mentioned.
Conclusion:
The provided FDA 510(k) clearance document for the AirStrip ONE Web Client with ACM describes a medical device focused on data display and alarm communication management, not a diagnostic AI/algorithm. Therefore, the detailed information requested regarding diagnostic acceptance criteria, expert-established ground truth, MRMC studies, and training/test set specifics for AI performance are not present in this document as they are not relevant to the device's function and regulatory review. The "performance testing" mentioned relates to software validation, cybersecurity, and adherence to internal specifications and relevant guidance documents (e.g., IEC 62304, ISO 14971, ISO/IEC 27001).
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).