(93 days)
The NDOHD system is intended for viewing, acquiring, archiving and retrieving video and still images of endoscopic and fluoroscopic procedures. The professionals or practitioners using this system would be medical doctors or clinicians such as speech pathologists. The device is a prescription device. The NDOHD system is not intended to be used in an environment that requires sterilization.
The NDOHD High Definition Imaging System (NDOHD) was initially commercialized in 2011 as a photographic accessory for endoscopes (FEM), Class I Exempt device. Altaravision has expanded the capabilities of the NDOHD system to include a computer and a camera, included a lossy image compression mechanism using standard irreversible compression technique, H.264, added a time code on the display of the image, created camera controls and added profiles for multiple camera settings and user preferences. Therefore, Altaravision has created a picture archiving and communication system that provides capabilities related to the acceptance, transfer, display, storage and digital processing of images and videos.
Here's an analysis of the provided 510(k) summary regarding the Altaravision NDOHD High Definition Imaging System, structured according to your requested points:
This device is a Picture Archiving and Communications System (PACS) and underwent a 510(k) submission, classifying it as a Class II medical device. The 510(k) submission primarily focuses on demonstrating substantial equivalence to a predicate device rather than conducting a separate clinical study to prove novel performance against specific acceptance criteria.
Therefore, there is no explicit table of acceptance criteria and reported device performance in the same manner one would expect for a diagnostic AI device or a device requiring new efficacy claims. The "acceptance criteria" for a 510(k) of this nature are implicitly met by demonstrating substantial equivalence through technical and functional comparisons, and adherence to relevant standards.
1. Table of Acceptance Criteria and Reported Device Performance
As noted, this 510(k) is for a PACS device demonstrating substantial equivalence, not a new AI diagnostic device with specific performance metrics like sensitivity or specificity. Thus, a traditional table of "acceptance criteria" and "reported device performance" in terms of clinical accuracy is not provided in the document.
Instead, the "acceptance criteria" are implied by conformance to international and FDA standards, and the "reported performance" is essentially the device's functional capabilities compared to a predicate device.
| Category | Acceptance Criteria (Implied by 510(k) Process) | Reported Device Performance (as demonstrated by substantial equivalence to K991738 and adherence to standards) |
|---|---|---|
| Intended Use | Must be the same or very similar to the predicate device. | The NDOHD system's intended use (viewing, acquiring, archiving and retrieving video and still images of endoscopic and fluoroscopic procedures) is determined to be the Same as predicate. |
| Indications for Use | Must be the same or very similar to the predicate device. | The NDOHD system's indications for use are determined to be the Same as predicate. |
| Target Population | Must be the same or very similar to the predicate device. | Target population (Medical doctors or clinicians such as speech pathologists) is determined to be the Same as predicate. |
| Display | Must be functionally comparable or superior, suitable for the intended use. | Uses a built-in computer display, which is considered Similar to predicate (NEC MultiSync E900+). |
| Storage Medium | Must be suitable for archiving and retrieving images. | Uses a non-removable hard drive, considered Similar to predicate (removable 2Gb hard drive). Functionally comparable. |
| Video Output Format | Must be suitable for image processing and archiving. | Uses .mov H.264 Video and .tiff still images. Considered Similar to predicate (MJPEG and AVI), with the NDOHD using an OS agnostic format compared to the predicate's Windows-specific formats. |
| Camera CCD | If integrated, must provide adequate image quality for the intended use. | 1032x762 CCD, 1/3" sensor, 31 FPS, 800Mb/s. The predicate device listed "Optional" for Camera. The NDOHD's integrated camera is compared to an optional component of the predicate. |
| Lossy Image Compression | Must utilize a known and accepted compression technique. | Uses H.264 compression. Considered Similar to predicate ("Yes," exact type unknown for predicate). |
| Energy | Must comply with safety standards for medical electrical equipment. | Computer built-in battery operated. Considered Similar to predicate (UPS battery operated). Both use battery during operation, and NDOHD includes safety controls to prevent use while plugged into AC power. |
| Software Functionality | Must adequately control recording, playback, storage, and retrieval of medical images. | NDOHD Software controls recording, playback, storage, retrieval, and live view of HD video, audio, and images. Considered Similar to predicate (DVRS Software controlling recording, playback, storage, retrieval of digital video and audio). NDOHD offers live view and is Macintosh-compatible, while the predicate is Microsoft-compatible. |
| Software Validation | Must comply with FDA guidance for medical device software. | Validation completed according to "General Principles of Software Validation; Final Guidance for Industry and FDA Staff, January 11, 2002" and "Guidance for the Submission of Premarket Notifications for Medical Image Management Devices, July 27, 2000". |
| Electrical Safety | Must comply with relevant IEC standards for medical electrical equipment. | Testing completed according to IEC 60601-1, IEC 60601-1-1, and IEC 60601-2-18. |
2. Sample Size Used for the Test Set and the Data Provenance
This document does not describe a clinical study with a "test set" of patient data in the typical sense (e.g., a set of medical images for diagnostic performance evaluation). The testing described relates to software validation and electrical safety, which are engineering and quality assurance activities, not clinical performance studies using patient data.
- Sample Size for Test Set: Not applicable/not specified for clinical performance. The testing involved functional and safety assessments of the device itself.
- Data Provenance: Not applicable, as no external patient data test set was used for performance claims.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts
Not applicable. No ground truth establishment by experts for a test set of patient data is mentioned because this is a PACS device whose 510(k) focused on substantial equivalence through functional and safety testing, not diagnostic performance.
4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set
Not applicable. No patient data test set requiring expert adjudication was described.
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
Not applicable. This device is a PACS for viewing, acquiring, archiving, and retrieving images. It is not an AI-assisted diagnostic tool, and therefore, an MRMC study comparing human reader performance with and without AI assistance was not conducted or mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. The NDOHD system is a human-in-the-loop system (a PACS) for medical professionals. It does not contain a standalone AI algorithm for diagnostic interpretation in the way one might evaluate AI performance for, say, lesion detection.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable. For the software validation and electrical safety tests, the "ground truth" would be the specifications, requirements, and industry standards themselves, rather than clinical ground truth from patient data.
8. The Sample Size for the Training Set
Not applicable. This document is for a medical device (PACS) that does not describe an AI algorithm explicitly trained on a dataset for clinical performance.
9. How the Ground Truth for the Training Set was Established
Not applicable, as no AI training set is described.
§ 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).