Search Results

When used in combination with a Swan-Ganz catheter connected to a pressure transducer, the Edwards Lifesciences Smart Wedge algorithm measures and provides pulmonary artery occlusion pressure and assesses the quality of the pulmonary artery occlusion pressurement. The Smart Wedge algorithm is indicated for use in critical care patients over 18 years of age receiving advanced hemodynamic monitoring. The Smart Wedge algorithm is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Smart Wedge algorithm parameters.

The Smart Wedge algorithm is designed to provide the value at end-expiration of the pulmonary artery occlusion pressure (PAOP) signal, also called pulmonary wedge pressure, pulmonary capillary wedge pressure (PCWP), or pulmonary artery wedge pressure (PAWP), and to assess the quality of the pulmonary artery occlusion pressure measurement.

The Smart Wedge algorithm is intended to be used with a Swan-Ganz pulmonary artery catheter connected to a pressure cable and pressure transducer.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

1. Acceptance Criteria and Reported Device Performance

The device performance is reported for two main aspects: PAOP (Pulmonary Artery Occlusion Pressure) Identification and PAOP Measurement. The acceptance criteria can be inferred from the reported performance results and the comparison to the predicate device, especially the statement: "Results for the Smart Wedge algorithm met or exceeded predicate device performance." While explicit numerical acceptance criteria aren't listed as "targets," the provided performance values serve as the acceptable outcomes.

Note: The document explicitly states for PAOP Measurement: "PAOP within mean absolute error < 4 mmHg accuracy." This serves as a clear numerical acceptance criterion for MAE.

2. Sample Sizes and Data Provenance

• Test Set (PAOP Identification): 225 PAP waveforms from 129 patients.
• Test Set (PAOP Measurement): 110 PAOP measurements from 59 patients.
• Data Provenance: Retrospectively collected from ICU and OR patients. The country of origin is not specified, but given the Edwards Lifesciences headquarters in Irvine, California, it's likely primarily US-based or multi-site.

3. Number of Experts and Qualifications

• Number of Experts: Three experienced healthcare providers (HCPs) were used to establish the ground truth.
• Qualifications: Described as "experienced healthcare providers (HCPs)." Specific qualifications (e.g., "radiologist with 10 years of experience") are not detailed, but the term "experienced" suggests domain expertise relevant to pulmonary artery occlusion pressure waveforms.

4. Adjudication Method for the Test Set

• For PAOP Identification: "Mode of three HCP annotations." This means the most frequent annotation among the three experts was
  taken as the ground truth.
• For PAOP Measurement: "Average PAOP measurement of three HCPs." This implies the numerical average of the three experts' measurements was used as the ground truth.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• The document explicitly states: "No clinical trial was performed in support of the subject 510(k)."
• Therefore, an MRMC comparative effectiveness study, which typically involves human readers improving with AI vs. without AI assistance, was not conducted. The study focuses on the algorithm's performance against expert consensus.

6. Standalone (Algorithm Only) Performance

• Yes, the reported study describes the standalone performance of the Smart Wedge algorithm. The tables ("Performance Results of PAOP Identification" and "Performance Results of PAOP Measurements") present the algorithm's capabilities (Sensitivity, Specificity, MAE, Bias, Correlation) measured against the established expert consensus ground truth. There's no mention of a human-in-the-loop component in the reported performance metrics.

7. Type of Ground Truth Used

• The ground truth used was expert consensus.
  • For PAOP Identification: "Mode of three HCP annotations."
  • For PAOP Measurement: "Average PAOP measurement of three HCPs."

8. Sample Size for the Training Set

• The document does not explicitly state the sample size used for the training set. It mentions the verification was performed using "waveforms retrospectively collected from ICU and OR patients", but the specific number for training versus testing is not provided. The provided numbers (225 waveforms/129 patients for identification, 110 measurements/59 patients for measurement) are for the test set.

9. How Ground Truth for Training Set Was Established

• Similar to the training set sample size, the document does not explicitly detail how the ground truth for the training set was established. Typically, for machine learning models, the training data also requires labeled ground truth, often established similarly to the test set (e.g., expert annotation or other reliable sources). However, this specific 510(k) summary focuses on the verification and validation of the algorithm's performance and the ground truth establishment for the test data.

Ask a specific question about this device