(284 days)
FORUM is a software system intended for use in management, processing of patient, diagnostic, video and image data and measurement from computerized diagnostic instruments or documentation systems through networks. It is intended to work with other FORUM applications (including but not limited to Retina Workplace, Glaucoma Workplace).
FORUM is intended for use in review of patient, diagnostic and image data and measurement by trained healthcare professionals.
FORUM and its accessories are a computer software system designed for management, processing, and display of patient diagnostic, video and image data and measurement from computerized diagnostic instruments or documentation systems through networks. It is intended to work with other FORUM applications.
FORUM receives data via DICOM protocol from a variety of ophthalmic diagnostic instruments (such as CIRRUS, CLARUS, and 3rd Party systems), allows central data storage and remote access to patient data. This version of FORUM allows the user to access their data in the cloud via ZEISS developed non-medical device accessories. FORUM is an ophthalmic data management solution. FORUM provides basic viewing functionalities and is able to connect all DICOM compliant instruments.
This version of FORUM provides additional device functions such as review and annotation functionality of fundus images/movies, display of OCT image stacks, bidirectional data exchange between FORUM Workplaces, customization of document viewing abilities, user interface improvements, and user management updates.
This version of FORUM has additional non-medical device functions that are performed by non-medical device accessories, such as documentation storage, export of data in various formats, export to the cloud, improved IT integration capability into the existing IT network, image sorting, EMR log in improvements, numerous backend improvements with the purpose of streamlining clinical workflow.
Here's an analysis of the provided text regarding the acceptance criteria and study for the device:
Important Note: The provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It usually doesn't contain a detailed breakdown of a separate clinical study with acceptance criteria, sample sizes, and expert adjudication in the same way an AI/ML device would. Instead, it relies on extensive software verification and validation to demonstrate safety and effectiveness.
Based on the provided text, a direct answer to all your questions in the typical format for a clinical study is not explicitly available for this specific type of device (a medical image management and processing system). However, I can extract the relevant information and infer what's implied.
Acceptance Criteria and Device Performance Study for FORUM (K213527)
This submission for FORUM (K213527) is a 510(k) Pre-market Notification for a medical image management and processing system. The acceptance criteria and "study" are primarily focused on demonstrating substantial equivalence to a predicate device (FORUM Archive and Viewer, K122938) through software verification and validation, rather than a traditional multi-reader multi-case clinical study for a diagnostic AI algorithm.
1. Table of Acceptance Criteria and Reported Device Performance
Since this is a software system intended for managing and processing existing image data, not generating new diagnostic conclusions, the "acceptance criteria" are related to its functional performance, safety, and equivalence to its predicate.
| Acceptance Criteria Category/Area | Specific Criteria (Implied/Demonstrated) | Reported Device Performance (Demonstrated by Verification & Validation) |
|---|---|---|
| Indications for Use | Equivalence to predicate's IFU; no new risks associated with the updated IFU. | The IFU is "equivalent" to the predicate, with a minor textual change ("removal of the word 'storage' and display... due to an updated definition of MIMS") not constituting a substantial change. |
| Functionality (Medical Device Features) | Performance of core functions for patient data management, processing, and review as intended. | All new and/or modified medical device functions (e.g., fundus image processing, image annotations, bidirectional data exchange) were demonstrated through risk analysis and testing to not impact the safety, equivalence, risk profile, and technical specifications as compared to the predicate device. |
| Safety and Risk Profile | Risks associated with new/modified functions are mitigated and do not introduce new substantial concerns. | Appropriate risk analysis and testing documentation were provided to demonstrate that modifications do not impact substantial equivalence. The device was considered a "Moderate" level of concern, and verification/validation confirmed no indirect minor injury to patient or operator. |
| Technical Specifications | Updated platform/OS and other backend improvements maintain or enhance performance without adverse impact. | Backend improvements (e.g., updated Windows Server/Client versions, addition of Apple OS X BigSur support) were deemed equivalent as they do not impact indications for use, device risk profile, or technical specifications, as demonstrated by risk documentation and testing. |
| Non-Medical Device Functions | New non-medical accessories and functions (e.g., cloud connection, documentation storage) do not impact the core medical device functionality or safety. | The addition of non-medical accessories (e.g., for cloud connectivity) and non-medical functions does not impact the functionality or safety of the medical device, as demonstrated by appropriate risk assessments and testing information. |
| Software Verification & Validation | All requirements for proposed changes must be met, and testing must be performed according to FDA guidance. | "FORUM (version 4.3) has successfully undergone extensive software verification and validation testing to ensure that all requirements for proposed changes have been met." Documentation provided as recommended by FDA's "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." All testing followed internally approved procedures. |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not explicitly stated as a number of cases or patients. The "test set" here refers to the software verification and validation activities. These typically involve diverse test cases covering various functionalities, edge cases, and potential failure points, rather than a "patient test set" in a clinical study.
- Data Provenance: Not specified. For software verification and validation, the "data" would be test data (simulated or real but de-identified) used to exercise the software's functions.
3. Number of Experts Used to Establish Ground Truth and Qualifications
- Number of Experts: Not applicable or specified. For this type of software, "ground truth" relates to the expected behavior of the software according to its design specifications. It doesn't involve medical experts adjudicating diagnoses in a test set.
- Qualifications of Experts: N/A for establishing "ground truth" in this context. Experts would be software engineers, quality assurance personnel, and potentially clinical subject matter experts for reviewing the functional requirements and outputs.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable. The "ground truth" for software verification is the expected output according to the design specification and requirements. Verification and validation are performed against these predetermined requirements.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was it done? No. This type of study is typically performed for AI-powered diagnostic devices where human readers' performance with and without AI assistance is compared. FORUM is a management and processing system, not an AI diagnostic algorithm that provides assistance to human readers in the diagnostic task itself.
- Effect Size of Human Readers' Improvement: Not applicable.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Was it done? No, not in the sense of a standalone diagnostic algorithm's performance. The "standalone" performance for this device would refer to its ability to perform its specified functions (managing, processing, displaying data) correctly and reliably, which was assessed through software verification and validation. It's not a diagnostic algorithm.
7. Type of Ground Truth Used
- Type of Ground Truth: Software functional specifications and requirements documents. The "truth" is whether the software behaves as designed and meets its technical and safety requirements.
8. Sample Size for the Training Set
- Training Set Sample Size: Not applicable. FORUM is a medical image management and processing system, not a machine learning model that requires a "training set."
9. How the Ground Truth for the Training Set Was Established
- How Ground Truth Established: Not applicable, as there is no training set for this type of device.
§ 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).