(155 days)
InVision Precision Cardiac Amyloid is an automated machine learning-based decision support system, indicated as a screening tool for adult patients aged 65 years and over undergoing cardiovascular assessment using echocardiography.
When utilized by an interpreting physician, this device provides information alerting the physician for referral to confirmatory investigations.
InVision Precision Cardiac Amyloid is indicated in adult populations over 65 years of age. Patient management decisions should not be made solely on the results of the InVision Precision Cardiac Amyloid.
The InVision Precision Cardiac Amyloid (InVision PCA) is a Software as a Medical Device (SaMD) machine-learning screening algorithm to identify high suspicion of cardiac amyloidosis from routinely obtained echocardiogram videos. The device assists clinicians in the diagnosis of cardiac amyloidosis.
The InVision PCA algorithm uses a machine learning process to identify the presence of cardiac amyloidosis. The device inputs images and videos from echocardiogram studies, and it outputs a report suggestive or not suggestive of cardiac amyloidosis.
The device has no physical form and is installed as a third-party application to an institution's PACS system.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) clearance letter:
InVision Precision Cardiac Amyloid: Acceptance Criteria and Performance Study
InVision Precision Cardiac Amyloid (InVision PCA) is a Software as a Medical Device (SaMD) machine-learning screening algorithm developed to identify a high suspicion of cardiac amyloidosis from routinely obtained echocardiogram videos. It acts as a decision support system, alerting interpreting physicians for referral to confirmatory investigations for adult patients aged 65 years and over undergoing cardiovascular assessment using echocardiography.
The device's performance was validated through a comprehensive study, demonstrating its substantial equivalence to the predicate device.
1. Acceptance Criteria and Reported Device Performance
The primary acceptance criteria for the InVision PCA device were established based on its ability to reliably screen for cardiac amyloidosis. The reported performance metrics from the validation study are as follows:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Sensitivity | 0.607 (60.7%) |
| Specificity | 0.990 (99.0%) |
Note: While specific numerical acceptance thresholds are not explicitly stated as "passing" values (e.g., "must achieve >X% sensitivity"), these reported values are presented as the results that successfully met the predefined endpoints of the validation study, implying they satisfied the implicit acceptance criteria deemed necessary for clearance.
2. Sample Size and Data Provenance for Test Set
- Sample Size: 1221 unique echocardiogram studies.
- Data Provenance: The data were selected from three geographically different U.S. sites. The study was conducted on "previously acquired" images, indicating it was a retrospective study.
3. Number of Experts and Qualifications for Ground Truth
The provided document does not explicitly state the number of experts used to establish the ground truth nor their specific qualifications. It mentions "confirmatory reference data," which could imply a consensus of expert opinion but does not detail the process.
4. Adjudication Method for Test Set
The document does not explicitly state the adjudication method used (e.g., 2+1, 3+1). It refers to the ground truth being established by "confirmatory reference data, such as diagnostic imaging or pathology," suggesting a definitive diagnostic pathway rather than a multi-reader visual interpretation adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was explicitly described in the provided text, meaning there is no information on how much human readers improve with AI vs. without AI assistance. The study focused on the standalone performance of the AI model.
6. Standalone (Algorithm Only) Performance
Yes, a standalone (algorithm only) performance study was conducted. The reported sensitivity of 0.607 and specificity of 0.990 are directly attributable to the InVision PCA algorithm's performance in analyzing echocardiogram studies against confirmed ground truth.
7. Type of Ground Truth Used
The ground truth for the test set was established using confirmatory reference data, such as diagnostic imaging or pathology. This indicates a high-fidelity ground truth derived from definitive diagnostic procedures rather than solely expert consensus on images.
8. Sample Size for Training Set
The document does not specify the sample size used for the training set. It only details the sample size for the validation/test set.
9. How Ground Truth for Training Set Was Established
The document does not explicitly state how the ground truth for the training set was established. It is assumed that similar rigorous methods involving confirmatory diagnostic imaging or pathology would have been used for the training data, consistent with the approach for the test set, but this is not directly mentioned.
§ 870.2200 Adjunctive cardiovascular status indicator.
(a)
Identification. The adjunctive cardiovascular status indicator is a prescription device based on sensor technology for the measurement of a physical parameter(s). This device is intended for adjunctive use with other physical vital sign parameters and patient information and is not intended to independently direct therapy.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Software description, verification, and validation based on comprehensive hazard analysis must be provided, including:
(i) Full characterization of technical parameters of the software, including any proprietary algorithm(s);
(ii) Description of the expected impact of all applicable sensor acquisition hardware characteristics on performance and any associated hardware specifications;
(iii) Specification of acceptable incoming sensor data quality control measures; and
(iv) Mitigation of impact of user error or failure of any subsystem components (signal detection and analysis, data display, and storage) on accuracy of patient reports.
(2) Scientific justification for the validity of the status indicator algorithm(s) must be provided. Verification of algorithm calculations and validation testing of the algorithm using a data set separate from the training data must demonstrate the validity of modeling.
(3) Usability assessment must be provided to demonstrate that risk of misinterpretation of the status indicator is appropriately mitigated.
(4) Clinical data must be provided in support of the intended use and include the following:
(i) Output measure(s) must be compared to an acceptable reference method to demonstrate that the output measure(s) represent(s) the predictive measure(s) that the device provides in an accurate and reproducible manner;
(ii) The data set must be representative of the intended use population for the device. Any selection criteria or limitations of the samples must be fully described and justified;
(iii) Agreement of the measure(s) with the reference measure(s) must be assessed across the full measurement range; and
(iv) Data must be provided within the clinical validation study or using equivalent datasets to demonstrate the consistency of the output and be representative of the range of data sources and data quality likely to be encountered in the intended use population and relevant use conditions in the intended use environment.
(5) Labeling must include the following:
(i) The type of sensor data used, including specification of compatible sensors for data acquisition;
(ii) A description of what the device measures and outputs to the user;
(iii) Warnings identifying sensor reading acquisition factors that may impact measurement results;
(iv) Guidance for interpretation of the measurements, including warning(s) specifying adjunctive use of the measurements;
(v) Key assumptions made in the calculation and determination of measurements;
(vi) The measurement performance of the device for all presented parameters, with appropriate confidence intervals, and the supporting evidence for this performance; and
(vii) A detailed description of the patients studied in the clinical validation (
e.g., age, gender, race/ethnicity, clinical stability) as well as procedural details of the clinical study.