Search Results

The Caption Interpretation Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using an ultrasound device, personal computer, or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection fraction. This measurement can be used to assist the clinician in a cardiac evaluation.

The Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

The Caption Interpretation Automated Ejection Fraction Software ("AutoEF") applies machine learning algorithms to process two-dimensional transthoracic echocardiography images for calculating left ventricular ejection fraction.

The current implementation of the device adds a predetermined change control plan (PCCP) to the device cleared under K210747, which allows future modifications to the device.

The version of Caption Interpretation AutoEF cleared under K210747 performs left ventricular ejection fraction estimation using apical four chamber (A4C), apical two chamber (A2C) and the parasternal long-axis (PLAX) cardiac ultrasound images.

The software uses an algorithm that was derived through use of deep learning and locked prior to validation. The product operates as an add-in to a DICOM PACS system, ultrasound device, or personal computer. Caption Interpretation receives imaging data either directly from an ultrasound system or from a module in a PACS system.

The device includes the following main components:

1. Clip Annotation and Selection: The AutoEF software includes a function that processes video clips in a study to automatically classify clips that are PLAX. AP4, and AP2 views. This view selection is based on a convolutional network. It also includes a function, Image Quality Score (IQS), that allows selection of best available PLAX, AP4, and AP2 clips within the study or provide an indication to the user if there are no clips with sufficient quality to estimate ejection fraction, based on prespecified IQS thresholds.
2. Eiection Fraction Estimator and Confidence Metric: The automated eiection fraction estimation is performed using a machine learning model trained on apical and parasternal long-axis views. The model is trained with a dataset from a large number of patients. representative of the intended patient population and variety of contemporary cardiac ultrasound scanners. The EF calculation can be performed on a 3-view combination (PLAX, AP4 and AP2), 2-view combinations (AP4 and AP2, AP2 and PLAX, AP4 and PLAX), or single views (AP4, AP2). The confidence metric provides expected error in left-ventricle ejection fraction estimation and is based on IQS.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

• AP4 and AP2: 7.27 [6.55, 7.92] (Meets Criteria)
• AP4 and PLAX: 7.50 [6.85, 8.09] (Meets Criteria)
• AP4, AP2, and PLAX: 7.24 [6.64, 7.80] (Meets Criteria)
• AP2 and PLAX: 8.04 [7.32, 8.7] (Meets Criteria) |
  | New views superior to 11.024% RMSD individually. | Individual Views:
• AP4 only: 7.76 [7.01, 8.45] (Meets Criteria)
• AP2 only: 8.27 [7.44, 9.03] (Meets Criteria) (Note: PLAX individual view is not explicitly reported here for comparison against this criterion, but the overall context implies good performance.) |
  | For each standard view, the Confidence Metric must meet the equivalence to expert EF criteria as defined in PCCP. | Testing of the confidence metric functionality verified successful performance of the Confidence Metric in estimating the error range of the EF estimates around the reference EF using equivalence criteria and the evidence that the difference between the estimated EF and the reference EF is normally distributed. (Meets Criteria) |

Study Details

2. Sample size used for the test set and the data provenance

• Sample Size for Test Set: 186 patient studies.
• Data Provenance: Retrospective, multicenter study. The studies were acquired from three sites across the US: Minneapolis Heart Institute, Duke University, and Northwestern University.

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

• Number of Experts: Not explicitly stated as a specific number of individual experts. The text refers to "a panel of expert readers" for the Clip Annotator study and "expert cardiologists" for establishing the EF reference standard.
• Qualifications of Experts: "Expert cardiologists." No further specific details like years of experience are provided, but the title implies appropriate medical qualifications for interpreting echocardiograms.

4. Adjudication method for the test set

• Adjudication Method (Clip Annotator Study): "Results of the Clip Annotator were compared to evaluation by a panel of expert readers." This implies a consensus-based or direct comparison method, but the specific adjudication (e.g., 2+1, 3+1) is not detailed.
• Adjudication Method (EF Calculation): The reference standard for ejection fraction was established by "expert cardiologists." This suggests expert consensus or established expert interpretation, but a formal adjudication process (e.g., how disagreements between experts were resolved if multiple experts reviewed the same case) is not explicitly 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

• MRMC Comparative Effectiveness Study: No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance was not reported in this document. The clinical validation focused on comparing the AutoEF device's performance directly against an expert-established reference standard, not on the improvement of human readers using the device.

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

• Standalone Performance: Yes, the clinical validation study assessed the standalone performance of the Caption Health AutoEF. The "test compared the Caption Health AutoEF to the expert produced and reported biplane Modified Simpson's ejection fraction." This means the algorithm's output was directly compared to the ground truth without human intervention in the device's estimation process. The clinician's ability to edit the estimation is mentioned as a feature, but the presented performance results are for the automated estimation.

7. The type of ground truth used

• Ground Truth Type (Clip Annotator): Evaluation by a "panel of expert readers."
• Ground Truth Type (Ejection Fraction): Reference standard for ejection fraction was established by 2D echo using the biplane Modified Simpson's method of disks, performed by "expert cardiologists."

8. The sample size for the training set

• Training Set Sample Size: The text states, "The model is trained with a dataset from a large number of patients." However, a specific numerical sample size for the training set is not provided. It also mentions training occurred on "a dataset from a large number of patients, representative of the intended patient population and variety of contemporary cardiac ultrasound scanners."

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

• Training Set Ground Truth Establishment: The document does not explicitly detail how the ground truth for the training set was established. It only mentions that the machine learning model was "trained on apical and parasternal long-axis views" and derived through "deep learning," and "locked prior to validation." Given the nature of EF calculation, it is highly probable that expert cardiologists also established the ground truth for the training data, likely using methods similar to the test set (e.g., biplane Modified Simpson's method).

Ask a specific question about this device

The Caption Interpretation Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using an ultrasound device, personal computer, or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection fraction. This measurement can be used to assist the clinician in a cardiac evaluation.

The Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

The Caption Interpretation Automated Ejection Fraction Software ("AutoEF") applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction. The cleared Caption Interpretation AutoEF performs left ventricular ejection fraction measurements using apical four chamber or apical two chamber cardiac ultrasound views, or the parasternal long-axis cardiac ultrasound view in combination with an apical four chamber view. The software selects the image clips to be used, performs the AutoEF calculation, and forwards the results to the desired destination for clinician viewing. The output of the Ejection Fraction estimate stated as a percentage, along with an indication of confidence regarding that estimate.

Here's a breakdown of the acceptance criteria and study details for the Caption Interpretation Automated Ejection Fraction Software, based on the provided FDA 510(k) summary:

1. Acceptance Criteria and Reported Device Performance

Notes on Acceptance Criteria:

• The specific "set threshold" for RMSD is not explicitly stated in the provided text. However, the summary indicates that the "primary endpoint for the subject device was met."
• The summary highlights that the subject device demonstrated "slightly improved performance" in RMSD compared to the predicate, and "comparable performance" in outlier rates.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: Over 186 acquired studies.
• Data Provenance:
  • Country of Origin: Not explicitly stated.
  • Retrospective or Prospective: Retrospective, non-interventional validation study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• This information is not explicitly stated in the provided text. The text only mentions that the device's measurements were "compared to the biplane method ejection fraction" as the reference. It doesn't detail who performed these biplane measurements or how many experts were involved.

4. Adjudication Method for the Test Set

• The text describes the ground truth as the "biplane method ejection fraction." It does not describe an adjudication method for the test set, implying that the biplane measurements served as the direct reference without further expert consensus or adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

• No, an MRMC comparative effectiveness study was not done. The study described is a standalone performance validation of the algorithm against a declared ground truth (biplane method ejection fraction). There is no mention of human readers assisting or being compared to the AI.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, a standalone performance study was done. The described study directly compares the Caption Interpretation Automated Ejection Fraction Software's output to the "biplane method ejection fraction" without human intervention in the loop for the device's calculation. The device provides an "automated estimation of left ventricular ejection fraction."

7. The Type of Ground Truth Used

• Expert Consensus / Clinical Standard: The ground truth used was the biplane method ejection fraction. This is a widely accepted clinical method for calculating EF, typically performed by trained professionals (e.g., echocardiographers, cardiologists). While the text doesn't specify if it was a "consensus" of multiple experts, it refers to a established clinical method.

8. The Sample Size for the Training Set

• The training set included an "additional 30% of training data from three ultrasound devices and two clinical sites" for retraining of algorithms, compared to the predicate device. The absolute sample size of the training set is not explicitly stated.

9. How the Ground Truth for the Training Set Was Established

• The text states that "Images and cases used for verification and validation testing were carefully separated from training datasets." While it doesn't explicitly detail how the ground truth for the training set was established, it's generally understood that for machine learning algorithms in medical imaging, the training data would also require some form of expert labeling or ground truth establishment (e.g., manual segmentation and measurement by cardiologists, confirmed by clinical standards like the biplane method). The summary does not provide specific details on this process for the training data.

Ask a specific question about this device

The Caption Interpretation Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using an ultrasound device, personal computer, or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection. This measurement can be used to assist the clinician in a cardiac evaluation.

The Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

The Caption Interpretation Automated Ejection Fraction Software applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction. Caption Interpretation AutoEF performs left ventricular ejection fraction measurements using the apical four chamber, apical two chamber or parasternal long-axis cardiac ultrasound views or a combination of those views. The software selects the image clips to be used, performs the AutoEF calculation, and forwards the results to the desired destination for clinician viewing. The output of the program is the Ejection Fraction estimate stated as a percentage, along with an indications of confidence regarding that estimate.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

Detailed Study Information:

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

   • The document does not explicitly state the sample sizes (number of patients or echocardiograms) used for the test sets in either the Clip Annotator study or the pivotal clinical investigation.
   • Data Provenance: The document does not specify the country of origin of the data. It implies the data was "previously acquired transthoracic cardiac ultrasound images," but does not explicitly state if it was retrospective or prospective data.

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

   • Clip Annotator Study: "a panel of expert readers" was used. The exact number of experts and their specific qualifications are not provided beyond "expert readers."
   • Pivotal Clinical Study: The "reference method" is mentioned, implying a ground truth was established, but the number and qualifications of experts involved in creating this reference (e.g., conventional EF calculation methods by cardiologists) are not detailed. It mentions "sonographers' biplane tracing before a cardiologist overread" in the context of comparison, suggesting cardiologist input in the reference.

3. Adjudication method for the test set:

   • Clip Annotator Study: "Results of the Clip Annotator were compared to evaluation by a panel of expert readers." This suggests a direct comparison rather than a specific multi-reader adjudication method like 2+1 or 3+1. It's unclear if there was an adjudication for disagreements among the panel.
   • Pivotal Clinical Study: The document refers to a "reference method" for EF calculation. It doesn't specify an adjudication method for this reference, nor for any disagreements in the human interpretations used for comparison (e.g., sonographers' tracings).

4. If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:

   • The document implies a comparison between the AI's performance and human performance, stating the AP4 view was "superior to physicians in making a qualitative and quantitative visual assessment" and that AP2-only and PLAX-only RMSD was "lower than the RMSD of sonographers' biplane tracing before a cardiologist overread."
   • However, it does not explicitly describe a formal MRMC comparative effectiveness study where human readers' performance with AI assistance is directly compared to their performance without AI assistance. The comparisons made seem to be between the AI's standalone performance and human performance (or a component of human performance like tracing).
   • Therefore, an effect size of how much human readers improve with AI vs. without AI assistance cannot be extracted from this text.

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

   • Yes, the core objective of the studies described is to evaluate the standalone performance of the "Caption Interpretation Automated Ejection Fraction Software" in calculating EF and selecting clips. The reported "AutoEF accuracy" and RMSD values are indicative of standalone algorithm performance.

6. The type of ground truth used:

   • Clip Annotator Study: Expert consensus/evaluation by a panel of expert readers concerning the correct imaging mode and view.
   • Pivotal Clinical Study: "Conventional EF calculation methods" served as the "reference method." This likely implies expert-derived EF measurements, potentially involving cardiologist overread of sonographer tracings, and possibly other established clinical methods.

7. The sample size for the training set:

   • The document states, "The algorithms for estimating ejection fraction have been further optimized though additional training." and "Images and cases used for verification testing were carefully separated from training algorithms."
   • However, the specific sample size for the training set is not provided in this document.

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

   • The document states that the algorithms were "optimized though additional training" but does not detail how the ground truth for this training data was established. It only mentions that "Images and cases used for verification testing were carefully separated from training algorithms," which relates to data splitting, not ground truth establishment for training.

Ask a specific question about this device