(88 days)
Philips IntelliSpace Portal Platform is a software medical device that allows multiple users clinical applications from compatible computers on a network.
The system allows networking, selection, processing and filming of multimodality DICOM images.
This software is for use with off-the-shelf PC computer technology that meets defined minimum specifications .
Philips IntelliSpace Portal Platform is intended to be used by trained professionals, including but not limited to physicians and medical technicians.
This medical device is not to be used for mammography.
The device is not intended for diagnosis of lossy compressed images.
Philips IntelliSpace Portal Platform is a software medical device that allows multiple users to remotely access clinical applications from compatible computers on a network. The system allows networking, selection, processing and filming of multimodality DICOM images. This software is for use with offthe-shelf PC computer technology that meets defined minimum specifications.
The IntelliSpace Portal Platform communicates with imaging systems of different modalities using the DICOM-3 standard.
Here's an analysis of the provided text regarding the acceptance criteria and study for the IntelliSpace Portal Platform (K162025):
The submitted document is a 510(k) Premarket Notification for the Philips IntelliSpace Portal Platform. This submission aims to demonstrate substantial equivalence to a legally marketed predicate device (GE AW Server K081985).
Important Note: The document focuses on demonstrating substantial equivalence for a Picture Archiving and Communications System (PACS) and related functionalities. Unlike AI/ML-driven diagnostic devices, the information provided here does not detail performance metrics like sensitivity, specificity, or AUC against a specific clinical condition using a test set of images with established ground truth from a clinical study. Instead, the acceptance criteria and "study" refer to engineering and functional verification and validation testing to ensure the software performs as intended and safely, consistent with a PACS system.
Here's the breakdown based on your requested information:
-
A table of acceptance criteria and the reported device performance
The document does not provide a table with specific quantitative acceptance criteria or reported performance results in the classical sense (e.g., sensitivity, specificity, accuracy percentages) because it's for a PACS platform, not a diagnostic AI algorithm for a specific clinical task.
Instead, the "acceptance criteria" for a PACS platform primarily relate to its functional performance, compliance with standards, and safety. The reported "performance" is a successful demonstration of these aspects.
Acceptance Criteria (Inferred from regulatory requirements and description) Reported Device Performance (as stated in the submission) Compliance with ISO 14971 (Risk Management) Demonstrated compliance with ISO 14971. (p. 9) Compliance with IEC 62304 (Medical Device Software Lifecycle Processes) Demonstrated compliance with IEC 623304. (p. 9) Compliance with NEMA-PS 3.1-PS 3.20 (DICOM Standard) Demonstrated compliance with NEMA-PS 3.1-PS 3.20 (DICOM). (p. 9) Compliance with FDA Guidance for Content of Premarket Submissions for Software Contained in Medical Devices Demonstrated compliance with relevant FDA guidance document. (p. 9) Meeting defined functionality requirements and performance claims (e.g., networking, selection, processing, filming of multimodality DICOM images, multi-user access, various viewing/manipulation tools as listed in comparison tables) Verification and Validation tests performed to address intended use, technological characteristics, requirement specifications, and risk management results. Tests demonstrated the system meets all defined functionality requirements and performance claims. (p. 9) Safety and Effectiveness equivalent to predicate device Demonstrated substantial equivalence in terms of safety and effectiveness, confirming no new safety or effectiveness concerns. (p. 9, 10) -
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This type of information is not provided in this document. Since the submission is for a PACS platform and not a diagnostic AI algorithm, there is no mention of a "test set" of clinical cases or patient data in the context of diagnostic performance evaluation. The "testing" refers to software verification and validation, which would involve testing functionalities rather than analyzing a dataset of medical images.
-
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 applicable/not provided. As explained above, there is no "test set" of clinical cases with ground truth established by medical experts for diagnostic performance.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not applicable/not provided. There is no clinical "test set" requiring adjudication for diagnostic performance.
-
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, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. This device is a PACS platform, not an AI-assisted diagnostic tool designed to improve human reader performance for a specific clinical task. The submission explicitly states: "The subject of this premarket submission, ISPP does not require clinical studies to support equivalence." (p. 9).
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
No, a standalone performance study (in the context of an AI algorithm performing a diagnostic task) was not done. This device is a software platform for image management and processing, intended for use by trained professionals (humans-in-the-loop) for visualization and administrative functions.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc)
This information is not applicable/not provided. There is no ground truth data in the context of diagnostic accuracy for this PACS platform submission. The "ground truth" for its functionality would be defined by its requirement specifications, and testing would verify if those specifications are met.
-
The sample size for the training set
This information is not applicable/not provided. This device is a PACS platform, not an AI/ML algorithm that requires a "training set" of data in the machine learning sense. The software development process involves design and implementation, followed by verification and validation, but not training on a dataset of images to learn a specific task.
-
How the ground truth for the training set was established
This information is not applicable/not provided. As there is no "training set," there is no ground truth establishment for it.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).