(28 days)
LVivo platform is intended for non-invasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of patients with suspected disease.
The LVivo platform is a software system for automated analysis of ultrasound examinations. Automated analysis of echocardiographic examinations is done using DICOM movies. The LVivo platform supports global and segmental evaluation of the left ventricle (LV) of the heart. The global LV function is evaluated from two of the apical views: four-chamber (4CH) and two-chamber (2CH) by ejection fraction (EF). The segmental LV function is done from three apical views 4CH, 2CH and three chamber (3CH) and supports wall motion evaluation and strain. The LVivo platform supports also global and segmental evaluation of the LV from the parasternal short axis (SAX) view. In addition to the LV analysis, the cardiology toolbox includes a module for automated evaluation of the Right Ventricular function. The LVivo platform includes one additional non-cardiac module for the measurement of the bladder volume.
Here's a breakdown of the acceptance criteria and the study details for the LVivo Software Application, based on the provided FDA 510(k) summary:
Acceptance Criteria and Device Performance
| Parameter | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| LVivo EF (Ejection Fraction) | Biplane EF correlation >= 80% | Implicitly met, as stated "similar or better EF biplane results in terms of correlation, specificity, sensitivity, and kappa with respect to subject device." Actual percentage not explicitly given but implied acceptable. |
| Similar or better EF biplane results in terms of correlation, specificity, sensitivity, and kappa with respect to subject device (predicate device) | Implicitly met, as described above. | |
| LVivo GLS (Global Longitudinal Strain) | Cutoff value = 75% compared to reference Wall Motion Score Index (WSMI) | Implicitly met, as stated "similar or better results compared to subject device." Actual percentage not explicitly given but implied acceptable. |
| Similar or better results compared to subject device (predicate device) | Implicitly met, as described above. | |
| LVivo SWM (Segmental Wall Motion) | Sensitivity >= 75% | Implicitly met, as stated "similar or better results compared to subject device." Actual percentage not explicitly given but implied acceptable. |
| Similar or better results compared to subject device (predicate device) | Implicitly met, as described above. |
Study Details
-
Sample Size used for the test set and the data provenance:
- EF Analysis: 96 examinations from a dataset of 100 ambulatory and hospitalized patients.
- SWM and GLS Analysis: 98 examinations from the same dataset of 100 ambulatory and hospitalized patients.
- Data Provenance: Retrospective, collected according to GCP standards from ambulatory and hospitalized patients referred for routine transthoracic echocardiography. The country of origin is not explicitly stated.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided in the given text. The text mentions "reference WSMI" and comparisons to a "subject device" (likely the predicate device's performance benchmarks), but it does not detail how the initial ground truth for the reference measurements was established.
-
Adjudication method for the test set:
- This information is not explicitly provided. The text refers to "reference" values but does not describe the adjudication process (e.g., expert consensus) if multiple readers were involved in establishing these reference values.
-
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 MRMC comparative effectiveness study involving human readers with and without AI assistance was not described in this summary. The study focuses on evaluating the standalone performance of the AI algorithm against established reference values or the predicate device's performance.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance evaluation of the algorithm was performed. The acceptance criteria and "reported device performance" (implicitly met) directly relate to the algorithm's performance on the test set.
-
The type of ground truth used:
- The ground truth appears to be based on clinically established methods and possibly expert consensus/measurements, as implied by "reference" values and comparison to "reference WSMI." The summary states the data was collected for "routine transthoracic echocardiography," suggesting standard clinical measurements were used as a basis. However, the specific method of establishing this ground truth (e.g., expert manual measurements, pathology) is not explicitly detailed.
-
The sample size for the training set:
- The sample size for the training set is not provided in the given text. The document describes the test set but offers no details on the data used to train the "neural network" cited as a modification.
-
How the ground truth for the training set was established:
- This information is not provided in the given text.
§ 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).