(169 days)
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.
| Smart Wedge Algorithm Parameter | Implicit Acceptance Criteria (Target/Goal) | Reported Device Performance (Mean with 95% CI) |
|---|---|---|
| PAOP Identification | High Sensitivity (close to 100%) | Sensitivity: 100% [100, 100] |
| (based on 225 PAP waveforms) | High Specificity (close to 100%) | Specificity: 96% [92, 100] |
| High Positive Predictive Value (PPV) (close to 100%) | PPV: 95% [89, 99] | |
| High Negative Predictive Value (NPV) (close to 100%) | NPV: 100% [100, 100] | |
| PAOP Measurement | Low Mean Absolute Error (MAE) (e.g., < 4 mmHg) | MAE: 1.1 mmHg [0.8, 1.5] |
| (based on 110 PAOP measurements) | Low Bias (close to 0 mmHg) | Bias: 0.4 mmHg [0.1, 0.7] |
| Low Standard Deviation (Std) | Std: 1.7 mmHg [1.4, 2.0] | |
| High Correlation (r) (close to 1.0) | Correlation (r): 0.98 |
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.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
August 18, 2023
Edwards Lifesciences, LLC Jennifer Wilbur Director, Regulatory Affairs Program Management 1 Edwards Way Irvine. California 92614
Re: K230579
Trade/Device Name: Smart Wedge algorithm Regulation Number: 21 CFR 870.1425 Regulation Name: Programmable Diagnostic Computer Regulatory Class: Class II Product Code: DOK Dated: July 14, 2023 Received: July 14, 2023
Dear Jennifer Wilbur:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal
{1}------------------------------------------------
statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Robert T. Kazmierski -S
for
LCDR Stephen Browning Assistant Director Division of Cardiac Electrophysiology, Diagnostics, and Monitoring Devices Office of Cardiovascular Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
Indications for Use
510(k) Number (if known) K230579
Device Name Smart Wedge algorithm
Indications for Use (Describe)
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.
Type of Use (Select one or both, as applicable):
| ☑ Prescription Use (Part 21 CFR 801 Subpart D) |
|---|
| ☐ Over-The-Counter Use (21 CFR 801 Subpart C) |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
| I. Submitter | ||
|---|---|---|
| Sponsor | Edwards Lifesciences, LLCOne Edwards WayIrvine, CA, USA 92614 | |
| Establishment RegistrationNumber | 2015691 | |
| Contact Person | Primary Contact | Secondary Contact |
| Jennifer WilburDirector, Regulatory AffairsProgram ManagementOne Edwards WayIrvine, CA 92614Telephone: (949) 756-4436Email:jennifer_wilbur@edwards.com | Karen ClementSr. Director, Regulatory AffairsEdwards LifesciencesOne Edwards WayIrvine, CA 92614Telephone: (949) 250-4746Email:Karen Clement@edwards.com | |
| Date Prepared | July 14, 2023 | |
| II. Device Information | ||
| Trade Name | Smart Wedge algorithm | |
| Common Name | Pulmonary Artery Occlusion Pressure (PAOP) | |
| Regulation Number/Regulation Name | 21 CFR 870.1425 /Computer, Diagnostic, Programmable | |
| Product Code | DQK | |
| Regulation Class | Class II | |
| III. Predicate Device | ||
| Predicate Device | The GE CARESCAPE B650 Patient Monitor (K213181, cleared April13, 2022) manufactured by GE Healthcare Finland Oy, and itspulmonary artery occlusion pressure measurement are being utilizedfor substantial equivalence as a predicate to the Smart Wedgealgorithm in terms of similar technology (principles of operation,functionality and performance) and same/similar indications/intendeduse. | |
| IV. Device Description | ||
| Device Description | 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 wedgepressure (PCWP), or pulmonary artery wedge pressure (PAWP), andto assess the quality of the pulmonary artery occlusion pressuremeasurement.The Smart Wedge algorithm is intended to be used with a Swan-Ganzpulmonary artery catheter connected to a pressure cable and pressuretransducer. | |
| V. Indications for Use and Intended Use | ||
| Indications for Use | When used in combination with a Swan-Ganz catheter connected to apressure cable and pressure transducer, the Edwards LifesciencesSmart Wedge algorithm measures and provides pulmonary arteryocclusion pressure and assesses the quality of the pulmonary arteryocclusion pressure measurement. The Smart Wedge algorithm isindicated for use in critical care patients over 18 years of age receivingadvanced hemodynamic monitoring. The Smart Wedge algorithm isconsidered to be additional quantitative information regarding thepatient's physiological condition for reference only and no therapeuticdecisions should be made based solely on the Smart Wedge algorithmparameters. | |
| Intended Use | The Smart Wedge algorithm is intended to be used by qualifiedpersonnel or trained clinicians in a critical care environment in ahospital setting. The Smart Wedge algorithm is intended to measureand provide accurate pulmonary artery occlusion pressure and toassess the quality of the pulmonary artery occlusion pressuremeasurement. | |
| VI. Comparison of Technological Characteristics with Predicate Device | ||
| Comparison to PredicateDevice | The subject device and predicate devices are based on the followingsame technological elements:Hemodynamic Parameters & Technological Characteristics:The subject device and predicate device (GE CARESCAPEB650 Patient Monitor, K213181, cleared April 13, 2022) bothmeasure and provide pulmonary artery pressure, have softwareand provide flag/message outputs.The subject device and predicate device (GE CARESCAPEB650 Patient Monitor, K213181, cleared April 13, 2022) bothmeasure and provide pulmonary artery occlusion pressure. |
{4}------------------------------------------------
{5}------------------------------------------------
Accessories/Components:
- . The subject device and predicate device (GE CARESCAPE B650 Patient Monitor, K213181, cleared April 13, 2022) both obtain a pressure waveform measurement from a commercially available pulmonary artery catheter connected to a pressure cable and pressure transducer to obtain a pulmonary artery pressure waveform measurement.
Intended Use/Indications for Use:
- · The subject device and predicate device (GE CARESCAPE B650 Patient Monitor, K213181, cleared April 13, 2022) both have similar intended use/indications for use.
- o The subject device has the same indications/intended purpose as the predicate with respect to its use by trained clinicians in a healthcare environment and with respect to the hemodynamic monitoring of invasive pressure in adult patients.
The following technological differences exist between the subject and predicate device:
Algorithm Modifications:
- The subject Smart Wedge algorithm provides the following ● functional and safety enhancements over the predicate (GE CARESCAPE B650 Patient Monitor, K213181, cleared April 13. 2022):
-
PAOP Measurement: The subject Smart Wedge algorithm will not only display a PAOP measurement like the predicate device, but it will also display PAOP within mean absolute error < 4 mmHg accuracy.
- A Measurement of PAOP Quality: The subject Smart Wedge algorithm includes a new measurement as to the quality of the PAOP reading. This quality measurement is provided simultaneously with the PAOP value.
- Additional Flag Outputs/Messages: The subject Smart A Wedge algorithm includes additional safety flag outputs/messages for "no wedge detected" and "wedge too long" and an additional "artifact detected" flag output/message.
-
The subject device continues to have the same overall intended use/indications and fundamental scientific technology.
{6}------------------------------------------------
The following verification activities were performed in support of a substantial equivalence determination for the Smart Wedge algorithm and predicate devices and to ensure safety and effectiveness of the Smart Wedge algorithm:
Software Verification:
Software verification was performed in accordance with IEC 62304:2006/A1:2016. Medical device software – Software life cvcle processes, ISO 14971:2019, Medical devices, Applications of risk management to medical devices, FDA's Guidance for Industry and FDA Staff, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (issued May 11, 2005) and FDA's Guidance for Industry and FDA Staff, General Principles of Software Validation (issued January 11, 2002). The Smart Wedge algorithm was tested at the algorithm level to ensure the safety of the device. The verification of the Smart Wedge algorithm was performed using waveforms retrospectively collected from ICU and OR patients. The basis for determination of substantial equivalence included retrospective clinical validation testing as shown in Table 1 for PAOP identification and Table 2 for PAOP measurement, with the references (i.e., consensus) being independent annotations by three experienced health care providers (HCPs). Results for the Smart Wedge algorithm met or exceeded predicate device performance.
Table 1: Performance Results of PAOP Identification
Data presented as average value with 95% confidence interval (CI). PPV: positive predictive value, NPV: negative predictive value.
| Smart WedgeAlgorithmParameter | Method Used toObtain ReferenceValue(Consensus) | Sensitivity(%) | Specificity(%) | PPV(%) | NPV(%) |
|---|---|---|---|---|---|
| PAOP Identification(225 PAP waveformsfrom 129 patients) | Mode of threeHCP annotations | 100[100,100] | 96[92, 100] | 95[89, 99] | 100[100, 100] |
Table 2: Performance Results of PAOP Measurements
Data presented as average value with 95% confidence interval (CI). MAE: mean absolute error Std. standard deviation
| Smart WedgeAlgorithmParameter | Method Used toObtain ReferenceValue (Consensus) | MAE(mmHg) | Bias(mmHg) | Std(mmHg) | Correlationr |
|---|---|---|---|---|---|
| PAOP Measurement(110 PAOPmeasurements from59 Patients) | Average PAOPmeasurement ofthree HCPs | 1.1[0.8, 1.5] | 0.4[0.1, 0.7] | 1.7[1.4, 2.0] | 0.98 |
Clinical Performance:
No clinical trial was performed in support of the subject 510(k).
Device Testing /
Performance Data
{7}------------------------------------------------
| Conclusion | Overall Conclusion:The subject Smart Wedge algorithm successfully passed all functionaland performance testing, including software verification andvalidation and bench studies. Completion of all performanceverification and validation activities demonstrated that the subjectdevice meets its predetermined design and performance specifications.Verification activities performed confirmed that the differences in thefeatures and design did not adversely affect the safety andeffectiveness of the subject device. The testing performeddemonstrates that the subject Smart Wedge algorithm is substantiallyequivalent to its legally marketed predicate. |
|---|---|
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).