Search Results
Found 2 results
510(k) Data Aggregation
(95 days)
ResScan is intended to augment the standard follow-up care of patients by providing transfer of machine and therapeutic information, including the ability to remotely change settings. It is intended to be used by Clinicians in conjunction with ResMed compatible flow generators, using ResMed's proprietary communications protocol.
The performance and functional characteristics of ResScan includes all the user friendly features of the predicate device. ResScan allows the clinician to: Download and view patient and machine data from ResMed flow generators, Store patient details, Set machine parameters (Using Removal Media or PC direct connection), Create and print reports, Uses Removal Media or PC direct connection as the interface between the flow generator and ResScan, Support for Data Card Reader. Summary of additional features from the ResScan (K050775): ResMed compatible flow generators include, S8 series flow generators (73 BZD), VPAP Bilevel devices (73 MNS) and Stellar (73 MNT). Display/reporting of additional modes such as S, ST, ASV, iVAPS & PAC. Additional Windows Vista (64 bit) and Windows 7 (32 & 64 bit), and added support for remote settings via removable media - SD cards and USB sticks. Added support for display of alarm events. Added the capability to generate patient compliance reports based on US CMS guidelines both on a per patient basis and across all patient data.
This document describes the regulatory submission for the ResScan device, an adjunct to patient care that allows clinicians to transfer machine and therapeutic information and remotely change settings on ResMed compatible flow generators.
Here's an analysis of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a quantitative format for the ResScan device. Instead, it describes a more general approach to verification.
Acceptance Criteria Category | Description/Reported Performance |
---|---|
Functional Verification | End-to-end testing confirmed that settings were successfully transferred between the flow generator and ResScan, and data captured by the flow generator was sent to ResScan. All tests confirmed the product met the predetermined acceptance criteria. |
Design Input Specifications | Performance testing of ResScan has been conducted using End bench testing methodology to demonstrate that the modified ResScan performs to design input specifications. ResScan device met the predetermined pass/fail criteria as defined in the ResScan System Verification Report. |
Safety and Effectiveness | The modified ResScan has not altered the safety and effectiveness when used for patient compliance management as an adjunct with ResMed flow generators. The inclusion of new features was assessed within the risk analysis, and no additional safety risks were found. |
Regulatory Compliance | Complies with FDA Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 11, 2005) and FDA Off-the-Shelf Software Use in Medical Devices (September 9, 1999). |
Substantial Equivalence | Demonstrated substantial equivalence to the predicate device (ResScan, K050775) based on similar intended use, same operating principle, same technologies, and same manufacturing process. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated. The document refers to "End bench testing methodology" and "testing activities" performed as a result of risk analysis and design requirements. This suggests a rigorous internal testing process, but the specific number of test cases or "samples" is not quantified.
- Data Provenance: The testing appears to be internal "bench testing" and "Verification activities" conducted by ResMed Ltd, Australia. There is no mention of external data, clinical data, or country of origin for a specific "test set" in the context of patient data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- The document describes a "Non-Clinical Testing" approach involving "predetermined pass/fail criteria" and "design input specifications." This implies that the ground truth for testing was established by the design and engineering teams at ResMed based on the device's functional requirements.
- The document does not mention the use of external "experts" (e.g., radiologists, clinicians) to establish ground truth for a test set, as this was not a clinical study involving interpretation of patient data. The ground truth was based on the device's technical specifications and expected performance.
4. Adjudication Method for the Test Set
- An adjudication method is not applicable or mentioned. The testing described is verification testing against predetermined design inputs and pass/fail criteria, not a study involving human reviewers assessing output and requiring a consensus mechanism.
5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study
- No MRMC study was done. The document explicitly states: "Clinical testing was not deemed necessary as identified in the Risk Analysis, as ResScan only obtains patient and machine information from therapeutic devices for which clinical trials have already been conducted, or compared with previous predicate comparison test results. Accordingly no clinical testing is required." Therefore, there is no effect size reported for human readers improving with AI vs. without AI assistance.
6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop)
- Yes, a standalone performance study was done for the device's functionality. The described "End bench testing methodology" and "Verification activities" represent a standalone evaluation of the ResScan software's ability to:
- Successfully transfer settings between flow generators and ResScan.
- Receive data captured by the flow generator.
- Perform to design input specifications.
- Meet predetermined pass/fail criteria.
- The "algorithm" here refers to the software's functionality in handling data transfer and settings, rather than an AI-driven interpretive algorithm.
7. Type of Ground Truth Used
- The ground truth used for the non-clinical testing was design input specifications and predetermined pass/fail criteria. This refers to the functional requirements and expected behavior of the software, not clinical outcomes, pathology, or expert consensus on patient data.
8. Sample Size for the Training Set
- The concept of a "training set" is not applicable here. ResScan is a software device for data transfer and settings management, not a machine learning or AI algorithm that requires a training set in the conventional sense. The development likely involved standard software engineering practices (coding, unit testing, integration testing, system testing) rather than data-driven machine learning model training.
9. How the Ground Truth for the Training Set Was Established
- Not applicable, as there was no training set for a machine learning model. The "ground truth" for the device's development and verification was its design specifications and functional requirements as established by ResMed's engineering and product development teams.
Ask a specific question about this device
(88 days)
ResScan-Pro is intended to augment the standard follow-up care of patients by providing transfer of machine and therapeutic information, including the ability to remotely change settings. It is intended to be used by Clinicians in conjunction with ResMed compatible flow generators.
The performance and functional characteristics of ResScan-Pro includes all the user friendly features of the predicate device.
ResScan-Pro allows the clinician to:
- Download, view and store patient and machine details from a ResMed Flow Generator
- Create and print reports on patient and machine details
- Transfer treatment parameters to a ResMed Flow Generator
The ResScan-Pro 510(k) summary does not contain sufficient information to answer your request.
Here's why and what information is missing:
-
Acceptance Criteria and Reported Device Performance: The document states, "All tests confirmed the product met the predetermined acceptance criteria," but it does not list what those acceptance criteria were or what the specific performance metrics were that met them. Without these criteria and corresponding performance data, the table cannot be created.
-
Sample Size for Test Set and Data Provenance: The document mentions "Design and Verification activities were performed," but it does not specify the sample size of any test set used for these activities, nor does it provide details about the data's origin (country, retrospective/prospective). This information is crucial for understanding the rigor of the testing.
-
Number of Experts and Qualifications: There is no mention of experts being used to establish ground truth for a test set. The device appears to be data management software, not a diagnostic AI device requiring expert consensus for ground truth.
-
Adjudication Method: Since there's no indication of experts or complex diagnostic interpretations, an adjudication method is not applicable or mentioned.
-
MRMC Comparative Effectiveness Study: The document does not describe any Multi-Reader Multi-Case (MRMC) comparative effectiveness study. The device's function is to transfer and manage data/settings, not to assist human readers in interpretation.
-
Standalone Performance: The 510(k) summary focuses on the device's functionality in transferring and managing data/settings. While "performance" is mentioned in a general sense, there's no specific "standalone" performance study detailed in the way one would expect for an AI diagnostic algorithm (e.g., sensitivity, specificity for a particular condition). The device's performance is tied to its ability to correctly transfer information, which is a functional test, not a diagnostic one.
-
Type of Ground Truth: Given the device's nature (data transfer and settings management), the concept of "ground truth" as typically applied to diagnostic algorithms (expert consensus, pathology, outcomes data) is not directly relevant or discussed. The performance would likely be validated against successful data transfer and accurate setting changes.
-
Sample Size for Training Set and Ground Truth Establishment for Training Set: The document does not refer to a "training set" because this device is not an AI/ML algorithm that learns from data in that manner. It's software for managing and transferring existing machine and therapeutic information.
In summary, the provided 510(k) summary for ResScan-Pro describes a device for data transfer and settings management for non-continuous ventilators, not a diagnostic AI/ML device. Therefore, many of the typical questions regarding acceptance criteria, study design, and ground truth for AI algorithms are not applicable or the information is not present in this type of submission.
Ask a specific question about this device
Page 1 of 1