(22 days)
AirStrip RPM is software capable of displaying physiologic and other patient information is generated by other medical devices and patient information system, and not by AirStrip RPM captures this information from these other systems and displays it for clinicians.
AirStrip RPM is intended to be used by clinicians for the following purposes:
· By using a cellular telephone or other device on which AirStrip RPM is installed, to review physiologic data of a patient when the clinician is not at the hospital
- · To view the near real-time waveforms remotely
- · To remotely review other standard or critical near real-lime patient data from the monitored system
- · To provide a request for remote consultation regarding a patient's waveform or other data
The AirStrip RPM software can display the physiologic data captured by other medical devices:
- · ECG Waveform
- · Heart Rate Monitored
- · Respiratory Rate
- · Oxygen Saturation
- · Intracranial Pressure
- · Central Venous Pressure
- · Pulmonary Capillary Wedge Pressure
- Cardiac Index
- · Cardiac Output
- · Cerebral Perfusion Pressure
- · Urine Output
- · Urine/Stool Mix Output
- · 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
- · Antiarrhvthmics
- · Sedation
- · Paralvtics
- · Laboratory Data including
- Blood Gas
- Chemistry
- Hematology
- Coagulation
- · Allergies
- · Medications
AirStrip RPM is software capable of displaying physiologic and other patient information is generated by other medical devices and patient information system, and not by AirStrip RPM captures this information from these other systems and displays it for clinicians.
Based on the provided document, the device is the AirStrip Remote Patient Monitor (RPM) Remote Data Viewing software (K112235). The document is an FDA 510(k) clearance letter, which primarily focuses on substantial equivalence to a predicate device rather than detailing extensive clinical trials with acceptance criteria and performance metrics described as one might find for a PMA.
Therefore, much of the requested information regarding specific acceptance criteria and detailed study results as typically presented for AI/ML device performance is not available in this document. The FDA 510(k) summary for this type of device typically relies on verification and validation testing to demonstrate functional equivalence and safety, rather than a clinical effectiveness study with performance metrics like sensitivity/specificity against ground truth.
However, I can extract the available relevant information:
1. Table of acceptance criteria and the reported device performance:
This document does not explicitly state specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) or provide a table of reported device performance metrics against such criteria. The FDA 510(k) typically relies on a comparison to a predicate device and verification/validation testing to demonstrate proper functionality.
The "performance" described here is functional: the ability to accurately display various types of patient data from other medical devices.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
This information is not provided in the document. The document refers to the data as being generated by "other medical devices and patient information system" and "captured from these other systems."
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 provided in the document. Given the nature of the device (a remote viewing software for existing patient data), the "ground truth" would likely be the data as presented by the original monitoring devices. Testing would focus on the fidelity of the data display.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
This information is not provided in the document.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
This information is not provided in the document. The device is a "Remote Data Viewing software" and is explicitly described as a "diagnostic aid, and not as a replacement for direct viewing of any of the monitoring devices from which it obtains its data." It is not an AI-assisted diagnostic tool in the sense of providing automated interpretations or improving human reader performance, but rather a system for displaying existing patient data remotely.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The device itself is essentially "standalone" in its function of data display, as it presents data from other systems. However, its stated "Indications for Use" clearly state it is "intended to be used by clinicians" and "by clinicians as a diagnostic aid." Therefore, while the software performs its display function independently, its intended use always involves a human clinician in the loop. The document does not describe "standalone" performance in the context of an algorithm providing a definitive diagnosis or interpretation without human oversight.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
The implied "ground truth" for this device would be the accurate and faithful representation of the data generated by the original medical devices (e.g., ECG monitors, blood pressure cuffs, laboratory systems). The software's performance would be assessed on its ability to correctly transmit and display this data without alteration or corruption, not against an independent clinical ground truth like pathology or patient outcomes.
8. The sample size for the training set:
This information is not provided in the document. The device is a data display software, not a machine learning algorithm that typically requires a "training set" in the conventional sense.
9. How the ground truth for the training set was established:
This information is not provided in the document. As mentioned, the concept of a "training set" and its associated ground truth establishment is not directly applicable to this type of device based on the provided clearance letter.
§ 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).