(58 days)
EPIQ: The intended use of EPIQ Ultrasound Diagnostic System is diagnostic ultrasound imaging and fluid flow analysis of the human body, with the following indications for use: Abdominal, Cardiac Adult, Cardiac other (Fetal), Cardiac Pediatric, Cerebral Vascular, Cephalic (Adult), Cephalic (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), intra-luminal, intra-cardiac echo, Musculoskeletal (Conventional), Musculoskeletal (Superficial), Ophthalmic, Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal, Lung. Modes of operation include: B Mode, M Mode, PW Doppler, CW Doppler, Color Doppler, Color M Mode . Power Doppler and Harmonic Imaging. The clinical environments where EPIQ Series Diagnostic Ultrasound Systems can be used include clinics, hospitals, and clinical point-of-care for diagnosis of patients. When integrated with Philips EchoNavigator, the systems can assist the interventionalist and surgeon with image guidance during treatment of cardiovascular disease in which the procedure uses both live X-ray and live echo quidance. The systems are intended to be installed, used, and operated only in accordance with the safety procedures and operating instructions given in the product user information. Systems are to be operated only by appropriately trained healthcare professionals for the purposes for which they were designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgement and best clinical procedure.
Affiniti: The intended use of Affiniti Series Diagnostic Ultrasound Systems is diagnostic ultrasound imaging and fluid flow analysis of the human body, with the following indications for use. Abdominal, Cardiac Adult, Cardiac Other (Fetal), Cardiac Pediatric, Cerebral Vascular, Cephalic (Adult), Cephalic (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), Musculoskeletal (Conventional), Musculoskeletal (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal, Lung. Modes of operation include: B Mode, M Mode, PW Doppler, CW Doppler, Color Doppler, Color M Mode , Power Doppler and Harmonic Imaging. The clinical environments where the Affiniti diagnostic ultrasound systems can be used include clinics, hospitals, and clinical point-of-care for diagnosis of patients. The systems are intended to be installed, used, and operated only in accordance with the safety procedures and operating instructions given in the product user information. Systems are to be operated only by appropriately trained healthcare professionals for the purposes for which they were designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgement and best clinical procedure.
The purpose of this Traditional 510(k) Pre-Market Notification is to introduce the change in AutoMeasure V3 software application onto the EPIQ Series Diagnostic Ultrasound Systems and Affiniti Series Diagnostic Ultrasound Systems. Philips AutoMeasure feature provides the end user semi-automated 2D, Doppler and M-mode measurements with an adult cardiology transthoracic transducer and acquisitions that includes an electrocardiogram (ECG). The Auto Measure feature is designed to provide semi-automated and editable measures during an echocardiography. When Auto Measure is enabled, the healthcare professional performs an echocardiography with a workflow that provides the user with a semiautomated measurement that can be edited, accepted, or rejected. AutoMeasure is available in the Adult Echo analysis applications with ECG. Availability is also controlled by transducer and preset via the EPM. The software applications are supported by all EPIQ and Affiniti models running software version 13.0 or higher.
Here's an analysis of the acceptance criteria and study proving the device meets those criteria, based on the provided FDA 510(k) summary for Philips AutoMeasure V3 software.
Overview of the Device and Study:
The Philips AutoMeasure V3 software is an optional feature for EPIQ and Affiniti Series Diagnostic Ultrasound Systems. It provides semi-automated 2D, Doppler, and M-mode measurements during adult transthoracic echocardiography (TTE) using an AI-algorithm trained via machine learning. The study aimed to evaluate the performance of AutoMeasure V3 compared to standard of care (SOC) measurements.
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly list a table of acceptance criteria in numerical ranges for specific performance metrics (e.g., "accuracy > X%"). Instead, it describes a general acceptance methodology:
Acceptance Criteria for AutoMeasure V3 Software:
"meeting the pre-defined acceptance criteria for the study. Taken together, the results of the study demonstrated clinically reasonable, relevant and meaningful performance of the AutoMeasure V3 software supporting automation of measurements during cardiac TTE exams. Specifically, success on the hypotheses testing for AutoMeasure V3 agreement with ground truth measurements indicate that the safety and effectiveness of the proposed software is acceptable and aligns with previously reported agreement for cardiac assessment. Since the acceptance criteria were based on inter-observer data for echocardiographic measurements, the AutoMeasure V3 performance supports the conclusion that the algorithm behaves like any average human observer. Therefore, the clinical acceptability of AutoMeasure V3 is met."
This implies that the acceptance criteria for each of the 32 tested hypotheses were based on achieving agreement within the confidence intervals typically observed between human observers for echocardiographic measurements. The specific numerical thresholds for these confidence intervals are not provided in the summary.
Reported Device Performance:
The study concluded: "The results of the 32 hypotheses tested, demonstrated high agreement of AutoMeasure V3 software with Standard of Care Measurements (ground truth) obtained during initial subject exam, by producing confidence intervals for the limits of agreement, for each parameter (hypothesis) tested, meeting the pre-defined acceptance criteria for the study."
This indicates that for all 32 tested parameters, the AutoMeasure V3's performance was within the pre-defined limits of agreement, deemed comparable to human inter-observer variability.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 7127 transthoracic echocardiography (TTE) cardiac clips from 3964 subjects.
- Data Provenance: Retrospective, multi-institutional.
- Country of Origin: USA, Asia, and Europe.
- Retrospective/Prospective: "Subjects were enrolled at institutions between 2015 and June 2024, and the timeframes varied for different hospitals." This indicates retrospective data collection from existing patient records/imaging archives.
- Nature of Data: "Patients referred for clinical TTE as well as healthy volunteers were invited to participate."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Not explicitly stated as a specific number of unique experts who reviewed the test set for adjudication. The document states "Standard of Care (SOC) measurements obtained during initial subject visit, performed by qualified healthcare professional(s)." This implies that the ground truth was established by the original healthcare professional(s) performing the TTE exam in clinical practice.
- Qualifications of Experts: "qualified healthcare professional(s)". Specific qualifications (e.g., radiologist, cardiologist, sonographer, years of experience) are not detailed beyond "qualified". Given the context of echocardiography, these would likely be sonographers or cardiologists.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly described. The ground truth was based on "Standard of Care (SOC) measurements obtained during initial subject visit." This suggests a single reader paradigm where the initial clinical measurement serves as the ground truth, rather than a multi-reader consensus process specifically for the study.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- MRMC Study: No, a traditional MRMC comparative effectiveness study where multiple human readers systematically re-read cases with and without AI assistance was not explicitly described. The study focused on the agreement between the AI's measurements and existing Standard of Care human measurements.
- Effect Size of Human Improvement with AI Assistance: Not applicable, as this type of MRMC study was not performed. The study aimed to show that the AI's measurements were comparable to typical human variability.
6. If a Standalone (Algorithm Only) Performance Study Was Done
- Standalone Performance: Yes, implicitly. The "Performance Validation Study" evaluated "the performance of the AutoMeasure V3 software... compared to ground truth." While the user can edit the semi-automated measurements, the study's focus on "agreement of AutoMeasure V3 software with Standard of Care Measurements" suggests an evaluation of the algorithm's initial output before human intervention, establishing its standalone capability. The document states, "AutoMeasure V3 is created semi-automatically using machine learning algorithm without user interaction."
7. The Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (implicitly, as SOC measurements by "qualified healthcare professional(s)"). More specifically, it is "Standard of Care (SOC) measurements obtained during initial subject visit". This suggests reliance on clinical practice measurements rather than a separate, dedicated "gold standard" panel review or pathological confirmation.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not explicitly stated in this 510(k) summary. The document mentions "training via machine-learning techniques" but does not give the size of the dataset used for this training.
9. How the Ground Truth for the Training Set Was Established
- Training Set Ground Truth Establishment: Not explicitly stated in this 510(k) summary. However, it's highly probable that the training data's ground truth was also established by human expert annotation or existing clinical measurements, similar to how the test set ground truth was derived.
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.