Search Results

CariCloud is a software device used by operators to evaluate attenuation in the coronary arteries and surrounding tissue in CCTA images.
CariCloud is to be used by trained operators. CariCloud analysis results are to be used by Healthcare Professionals and may assist in diagnosis.
CariCloud analysis results are indicated for use for all patients referred for CCTA imaging.

CariCloud is an image processing prescription software device intended to be used to display, manipulate and quantify previously acquired CT images.
Datasets are downloaded from remote systems for clinical interpretation. Trained users will initiate and oversee image analysis and intervene when necessary to correct processing errors. The outcome of analysis will be used to create a summary report that includes qualitative and quantitative analysis.

Here's a breakdown of the acceptance criteria and study information for CariCloud v1.0, based on the provided text:

Acceptance Criteria and Device Performance

The submission primarily focuses on demonstrating substantial equivalence to a predicate device (TeraRecon iNtuition) through performance testing related to inter-operator and intra-operator variability in measurements. The acceptance criteria aren't explicitly stated as numerical thresholds for specific metrics, but rather derived from the performance of the predicate device and the conclusion that the new device's performance is "excellent" and shows "no significant difference."

Note: The specific meaning of PFA, TVOI-A, TVOI-V, and TROI-A are not explicitly defined in the provided document, but they represent different measures of attenuation in coronary arteries and surrounding tissue in CCTA images, as indicated by the device's intended use.

Study Details: Performance Testing - Inter-operator and Intra-operator Variability

1. Sample size used for the test set and the data provenance:

   • The document does not specify the sample size (number of cases/patients) used for the test set.
   • The document does not specify the data provenance (e.g., country of origin, retrospective or prospective) for the test set.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The document mentions "Reader 1," "Reader 2," and "Reader 3" in the ICC table, indicating that three operators were involved in the testing.
   • The qualifications of these operators are not provided. The Indications for Use state "CariCloud is to be used by trained operators," implying these readers were trained on the device.

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

   • The document states that ICC values were calculated "between individual results of each read by each operator on each device for each measure based on an average-rating, absolute-agreement, 2-way mixed-effects model." This implies that the individual reads of each operator were compared against each other, rather than against a single adjudicated ground truth derived from multiple experts. Therefore, a formal adjudication method like 2+1 or 3+1 for ground truth establishment is not mentioned and appears not applicable in the context of this inter/intra-operator variability study.

4. 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:

   • This document describes a study comparing the performance consistency (inter-operator and intra-operator variability) of the device itself (CariCloud v1.0) and a predicate device, as measured by human readers using them. It is not an MRMC comparative effectiveness study evaluating the improvement of human readers with AI assistance versus without AI assistance. Therefore, no such effect size is reported.

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

   • The testing described focuses on human operators using the device to make measurements. It is a "software device used by operators to evaluate attenuation." While the device itself performs analysis, the performance metrics reported here (ICC values) are derived from "individual results of each read by each operator." Therefore, a standalone (algorithm-only) performance study, independent of human interaction or measurement, is not explicitly described or reported in this section. The device's description does mention "trained users will initiate and oversee image analysis and intervene when necessary to correct processing errors," suggesting active human involvement.

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

   • For the inter-operator and intra-operator variability study, the "ground truth" for the ICC calculation is effectively the agreement between the operators' measurements themselves, or the agreement of an individual operator's repeated measurements. It does not refer to an independent, definitive medical ground truth like pathology or outcomes data. The study assesses the consistency of measurements obtained using the devices.

7. The sample size for the training set:

   • The document does not provide information regarding the sample size of any training set used for the CariCloud v1.0 software.

8. How the ground truth for the training set was established:

   • Since no training set information is provided, there is also no information on how the ground truth for any training set might have been established.

Ask a specific question about this device