Search Results

UltraLinq is a software imagement system intended to receive, process, review, display, and archive medical images and data from imaging modalities (e.g. Ultrasound (US), and Magnetic Resonance (MR)). Images and data can be stored, communicated and displayed across computer systems and mobile devices. UltraLinq is a single system that can run on a web-enabled computer, iPad and iPhone and may be interfaced with other PACS systems. Diagnosis is not performed by the software but by qualified Physicians. Typical users of this system are trained and qualified professionals, e.g. physicians, radiologists, nurses, medical technicians, and assistants. UltraLinq is used to:

• · share reports and studies with other UltraLinq users,
• · review reports and studies,
• · download and save reports and studies,
• · send reports and studies to EMR and EHR systems, and
• · route reports and studies to other UltraLinq users.

UltraLinq provides access to medical images on mobile devices for non-diagnostic viewing and referral purposes. The mobile device access functionality is used for patient management by the medical community in order to access and display patient data, medical reports, and medical images. Mobile devices are not intended to replace full diagnostic workstations and should be used only when there is no access to a workstation.

UltraLinq is also intended for non-invasive processing of already acquired echocardiographic images in order to detect, measure, and calculate the left ventricular wall for left ventricular function evaluation. This measurement, available on workstations only, can be used to assist the clinician in cardiac evaluation.

This device is not to be used for mammography.

UltraLinq is a web-based software application that provides image processing and viewing tools and access to studies and reports from a web-enabled computer, iPad or iPhone.

UltraLing is intended for use by a physician or other trained medical professionals to receive, process, review, display and archive medical images and data from imaging modalities. Diagnosis is not performed by the software but by qualified Physicians.

UltraLinq is also intended for non-invasive processing of already acquired echocardiographic images in order to detect, measure, and calculate the left ventricular wall for left ventricular function evaluation. This measurement, available on workstations only, can be used to assist the clinician in a cardiac evaluation.

UltraLing conforms to the ACR/NEMA DICOM 3.0 standard for interoperability with other DICOM compliant systems.

This document is a 510(k) Pre-market Notification for the UltraLinq device, which is a Picture Archiving Communications System (PACS) with an added feature for echocardiographic image analysis. The document focuses on demonstrating substantial equivalence to predicate devices rather than presenting a standalone study with specific acceptance criteria and detailed performance data in the format requested.

Therefore, much of the requested information regarding specific acceptance criteria, detailed study design, sample sizes, and expert qualifications for a standalone performance study is not explicitly available within the provided text. The document refers to "Software validation" and "Performance testing" but does not detail the specific criteria or results in a measurable, quantifiable way for all functionalities.

However, it does describe the analytical validation for the echocardiographic measurement feature by referencing the predicate device.

Here's an attempt to answer your questions based on the provided text, highlighting what is available and what is not:

1. A table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria and reported device performance for all functionalities of UltraLinq. Instead, it states that "Software validation has been satisfactorily completed and the software met its performance requirements and specifications."

For the specific functionality of automated calculation of Left Ventricular Wall Boundary and Ejection Fraction, UltraLinq integrates the LVivo EF algorithm without changes. The performance of this specific function relies on a prior clinical study submitted by DiACardio for the LVivo EF Software Application (K130779). The document does not provide the acceptance criteria or reported performance results of that study.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not available in the provided text for UltraLinq's overall performance.

For the echocardiographic measurement functionality, it refers to "A Clinical Study was performed and submitted by DiACardio on the LVivo EF Software Application 510(k) K130779." Details of the sample size and data provenance for that study are not included here.

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)

This information is not available in the provided text for UltraLinq's overall performance.

For the echocardiographic measurement functionality, it would have been established by the clinical study for the predicate device (LVivo EF Software Application), but those details are not provided here.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not available in the provided text.

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

A multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned for UltraLinq. The document describes UltraLinq as a "software imagement system" that assists clinicians, explicitly stating "Diagnosis is not performed by the software but by qualified Physicians." This implies it's not a diagnostic AI in the sense that would typically require an MRMC study comparing human performance with and without AI assistance for improved diagnostic accuracy. Its role for most features is image management and display.

The only "AI-like" feature is the automated calculation of left ventricular wall boundary and ejection fraction. Even for this, the device states it "can be used to assist the clinician," not to replace their judgment. The document does not describe an MRMC study for this specific feature either, but rather relies on the predicate device's validation.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

For the core PACS functionalities (receiving, processing, reviewing, displaying, archiving, sharing, routing, etc.), these are inherent functions of the software itself and would be assessed in a standalone manner against technical and functional specifications. The document states, "Performance testing of UltraLinq was conducted to validate that the device conforms to the defined user needs and intended uses." However, specific metrics of "standalone performance" beyond functional correctness are not provided.

For the automated echocardiographic measurements, the document states: "UltraLinq integrates with DiACardio's LVivo EF to provide automated Ejection Fraction (EF) calculation. UltraLinq integrates the LVivo EF algorithm without changes. A Clinical Study was performed and submitted by DiACardio on the LVivo EF Software Application 510(k) K130779." This implies that the standalone performance of the EF algorithm was likely established by the DiACardio study, but the details are not replicated here.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

This information is not available in the provided text for UltraLinq's general performance.

For the echocardiographic measurement functionality, the ground truth would have been established in the predicate device's clinical study (K130779), but the type of ground truth is not specified in the provided text. Typically for such measurements, it would involve measurements by expert sonographers/cardiologists.

8. The sample size for the training set

This information is not available in the provided text. The document refers to software validation and performance testing but does not detail the machine learning model development process or training set specifics. Since the device is a PACS system with an integrated measurement algorithm, explicit "training sets" might not be applicable in the same way as for a deep learning diagnostic algorithm, except potentially for the LVivo EF component.

9. How the ground truth for the training set was established

This information is not available in the provided text.

Ask a specific question about this device