K Number
K034033
Device Name
RESCAN
Manufacturer
Date Cleared
2004-05-05

(128 days)

Product Code
Regulation Number
868.5905
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The ResScan software is intended to be used by clinicians with ResMed flow generators that have software incorporating ResMed's proprietary communication protocol. ResScan is used to download and view therapy data, as well as store therapy information and print reports.

Device Description

The ResScan software with its capabilities of data collection and display of patient information provides an adjunct for patient compliance management. ResScan allows the clinician to download and view data from a ResMed CPAP or Bilevel device. The data displayed will depend on the ventilator used. Parameters displayed may include one or more of the following: usage (hrs: min); respiratory rate (breaths/min); tidal volume (L/min); leak (L/min); minute ventilation (L/min); apnea and hypopnea index including apnea index (AI), hypopnea index (HI) and AHI (events/hr); oxygen saturation SpO2 (%); pulse rate (bpm);. The software allows the creation of reports on patient details, and downloaded treatment data. ResScan displays data as retrieved. Data processing in ResScan is limited to computing the statistics (e.g., median) on retrieved data. The software operates under Windows 98SE, Windows 2000 SP2, Windows NT4 SP6, Windows XP, and is available on CD-ROM.

AI/ML Overview

Here's an analysis of the provided text, focusing on the acceptance criteria and study information for the ResScan device:

1. Table of Acceptance Criteria and Reported Device Performance:

The provided document does not explicitly list quantitative acceptance criteria for the ResScan software. Instead, the performance data section states that the software was tested in accordance with FDA guidance documents and "passed all tests." This implies that the acceptance criteria were met, but the specific metrics are not detailed.

Given the device's function as data download and display software, the implied "performance" likely relates to:

  • Accuracy of Data Display: The displayed data (usage, respiratory rate, tidal volume, leak, minute ventilation, AHI, SpO2, pulse rate) should accurately reflect the data downloaded from the ResMed CPAP or Bilevel device.
  • Functionality: The software should reliably perform its stated functions: downloading data, viewing data, storing data, and printing reports.
  • Compatibility: The software should operate correctly on the specified Windows operating systems and be compatible with ResMed flow generators using their proprietary communication protocol.
  • Security/Integrity: Data downloaded and stored should not be corrupted or altered by the software.
Acceptance Criteria (Implied)Reported Device Performance
Accurate display of downloaded therapy data"The ResScan software passed all tests."
Reliable data download from ResMed flow generators"The ResScan software passed all tests."
Correct functionality of viewing, storing, and printing reports"The ResScan software passed all tests."
Compatibility with specified operating systems and devices"The ResScan software passed all tests."
Data integrity during download, display, and storage"The ResScan software passed all tests."
Substantial equivalence to predicate device (AutoScan™ software)"it is substantially equivalent to the predicate device"
Compliance with FDA Software Guidance"tested in accordance with the recommendations of the FDA
Guidance... and the General Principles of Software
Validation."

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

The document provides no specific information regarding the sample size used for the test set or the provenance of the data (e.g., country of origin, retrospective/prospective). The statement "The ResScan software passed all tests" is a high-level summary without granular details.

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

The document provides no information on the use of experts or the establishment of ground truth in the context of typical clinical validation studies for diagnostic or AI devices. Given that ResScan is primarily data download and display software, the "ground truth" would likely be the data as logged by the ventilator, and testing would focus on the software's ability to accurately retrieve and present that data, rather than clinical interpretation by experts.

4. Adjudication Method:

The document provides no information on any adjudication methods.

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

The document provides no information on an MRMC comparative effectiveness study, nor would it be expected for this type of device. The device's function is to display data, not to assist human readers in making a diagnosis or interpretation in a way that would require an MRMC study to measure improved effectiveness.

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

For the ResScan software, the concept of "standalone" performance is inherent to its function. The software is designed to operate without human intervention during the data download and display process itself. Tests would assess if the software accurately processes and presents the data as designed, without a human "in the loop" for that specific function. However, the document does not describe the methodology or results of such a standalone study in detail, beyond stating that "all tests" were passed and it's substantially equivalent.

7. Type of Ground Truth Used:

The fundamental "ground truth" for this device would be the raw therapy data generated and logged by the ResMed CPAP or Bilevel flow generators. The software's performance is measured against its ability to accurately download, display, and store this pre-existing data. It's not a diagnostic device that interprets signals to establish a medical ground truth (like a pathology report or clinical outcome).

8. Sample Size for the Training Set:

The concept of a "training set" is typically relevant for machine learning or AI-driven devices. The ResScan software, as described, appears to be a rule-based or algorithmic data processing and display tool, not a machine learning model. Therefore, no "training set" information is provided or would be expected.

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

As there is no mention or indication of a training set, the question of how ground truth for it was established is not applicable.

§ 868.5905 Noncontinuous ventilator (IPPB).

(a)
Identification. A noncontinuous ventilator (intermittent positive pressure breathing-IPPB) is a device intended to deliver intermittently an aerosol to a patient's lungs or to assist a patient's breathing.(b)
Classification. Class II (performance standards).