(52 days)
The Syntermed Live™ software program should be used for the transfer of medical images and data to a secure server for storage where it can subsequently be accessed, displayed, and processed on any PC connected to the Internet using either proprietary software applications, a DICOM Viewer, or a Web Browser.
Syntermed Live™ is an Internet based system used to securely access, transfer, display, archive, and process medical images and data generated from a hospital or clinic. The Syntermed Live™ project is involved with the transmission and retrieval of output data files from either Syntermed proprietary applications, DICOM image files, or other medical digital data files to a Syntermed web server so that they can be archived and delivered to Syntermed customers for remote storage and review.
The provided text describes a 510(k) submission for the Syntermed Live™ software program, which is an internet-based system for accessing, transferring, displaying, archiving, and processing medical images and data.
However, the document does not contain specific acceptance criteria, a detailed study description with a table of reported performance against acceptance criteria, or most of the other requested information for a typical medical device study that would establish such criteria.
Here's a breakdown of what can be gleaned and what is missing, based on the provided text:
1. A table of acceptance criteria and the reported device performance
- Missing. The document states that "The expected accuracy of the program can be found in our initial 510(k) submission of the Emory Cardiac Toolbox, K980914." However, these specific acceptance criteria and performance metrics are not included in the provided text.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size for Test Set: 30 patient studies.
- Data Provenance: Not specified (country of origin, retrospective/prospective).
- Study Design: The validation "compared the visual interpretation of 30 patient studies using the previous analysis to visual interpretation of the Syntermed Live generated images." This suggests a comparative study against a previous method of displaying these images.
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)
- Missing. The document mentions "visual interpretation of... studies" but does not specify the number or qualifications of the physicians/experts performing this interpretation for the ground truth or comparison.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Missing. No information on adjudication methods is provided.
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
- Likely Not in the traditional sense. The study compares "visual interpretation of 30 patient studies using the previous analysis to visual interpretation of the Syntermed Live generated images." This is a comparison of display methods, not necessarily an AI-assisted interpretation versus unassisted human reading to assess improvement. It evaluates the equivalence of the display platform. No effect size for human reader improvement with AI assistance is mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable for this device as described. Syntermed Live™ is described as a "display program to aid in the visual interpretation" and a "tool to display the patient's medical images." It is described as a software for transfer, storage, and display, not an AI algorithm that makes interpretations independently. The "final responsibility for interpretation of the study lies with the physician."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Implied Expert Interpretation. The ground truth for the comparison seems to be derived from the "visual interpretation of... studies." This suggests an expert consensus or interpretation, but the specifics are not detailed.
8. The sample size for the training set
- Not applicable / Not explicitly mentioned. Since the device is a display and data transfer system, not an AI model that learns from data in a training set, the concept of a "training set" for an algorithm doesn't directly apply in the usual sense. The document discusses "software development" and "in-house testing," but not a data-driven training process for an AI model.
9. How the ground truth for the training set was established
- Not applicable. As above, there is no mention of a training set for an AI algorithm.
Summary of the "Study" (as much as can be discerned):
The study described is a comparison of the visual interpretation of 30 patient studies. It aimed to show that interpretations made using images generated/displayed by Syntermed Live™ were equivalent to those made using a "previous analysis" method. This implies a non-inferiority or equivalence study for the display and transfer capabilities, rather than an efficacy study for a diagnostic algorithm. The primary finding mentioned is that the program is "substantially equivalent" to the predicate device (INTEGRADWeb MPR/MIP™) for its intended purpose of image display and transfer.
§ 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).