EPIQ Series Diagnostic Ultrasound System: 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 guidance.
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 Series Diagnostic Ultrasound Systems: 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 510(k) Pre-market Notification is to introduce the SVS v2 Contrast software application with the EPIQ and Affiniti Series Diagnostic Ultrasound Systems as part of the VM13.0 program.
SVS v2 Contrast is an automated software feature that assists in the selection of images for analysis with the new Philips license options 2D Auto EF Advanced (Adv) developed by DiA Imaging Analysis (K243235), now part of Philips Ultrasound LLC, and existing Philips license options AutoStrain LV; or 2D Auto LV (both K240850) license application in Adult Echo Transthoracic (TTE) examinations.
As described in 510(k) K240850, this feature automatically classifies each acquired image by view and selects an appropriate set of images for Left ventricle (LV) analysis. The classification is based on a Deep Learning AI inference engine; the selection is a non-AI algorithm that considers the view classification and image depth to select the optimal set of images. The difference in SVS v2 Contrast from the predicate SVS v1 (K240850) is that the algorithm is revised to include the selection of optimal images for analysis when contrast is used in routine TTE exams.
Users can launch existing 2D Auto EF; 2D Auto EF Adv; AutoStrain LV; or 2D Auto LV with the set of images that have been automatically selected without the need to review the acquired images and manually select the views. Users may select 2D Auto EF Adv, to process the selected views by SVS v2 Contrast. SVS v2 Contrast prioritizes the contrast image pair; however, if an appropriate pair of contrast images is not found, then Auto EF Adv may select non-contrast images. The manual approach to select views is still available and the user can override automatically selected images from SVS v2 Contrast.
No hardware changes to the EPIQ or Affiniti Series Diagnostic Ultrasound Systems are required when using SVS v2 Contrast, and existing, cleared Philips TTE transducers.
The SVS v2 Contrast feature is supported by all EPIQ models running software version 13.0 or higher including EPIQ CVx/CVxi, EPIQ Elite Advanced, EPIQ Elite, EPIQ 7, EPIQ 5. The SVS v2 Contrast feature is supported by the Affiniti models running software version VM13.0 or higher, including Affiniti CVx, Affiniti 70, Affiniti 50, and Affiniti 30. The SVS v2 Contrast feature is associated with the cardiac adult indication.

Acceptance Criteria and Study Details for SVS v2 Contrast Software

This document outlines the acceptance criteria and details of the study conducted to demonstrate that the Philips Ultrasound systems (EPIQ and Affiniti Series Diagnostic Ultrasound System) with the SVS v2 Contrast software application meet the established performance benchmarks.

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

Intended Use / Indications for Use

EPIQ:

The intended use of Philips EPIQ 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, Intra-cardiac Echo, Intra-luminal, Intraoperative (Vascular), Intraoperative (Cardiac), 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 Philips EPIQ 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 guidance.

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 the 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 judgment and best clinical procedure.

The purpose of this Special 510(k) Pre-Market Notification is to expand the Smart View Select (SVS) software application onto the Affiniti Series Diagnostic Ultrasound Systems and to modify the Smart View Select software application onto both the EPIQ Series Diagnostic Ultrasound Systems.

Smart View Select is an automated software feature that assists the user in selection of images for analysis with the existing Philips AutoStrain LV or 2D Auto LV application in Adult Echo Transthoracic (TTE) examination. This feature automatically classifies each acquired image by view and selects an appropriate set of images for left ventricle (LV) analysis. The classification is based on a Deep Learning AI interface engine; the selection is a non-AI algorithm that considers the view classification and image depth to select the optimal set of images.

No hardware changes to the EPIQ or Affiniti systems are required when using SVS, and existing, cleared Philips TTE transducers are used with these software applications.

The SVS v2 feature is supported by all EPIQ models running software version 13.0 or higher including EPIQ CVx/CVxi, EPIQ Elite Advanced, EPIQ Elite, EPIQ 7, EPIQ 5. The SVS v2 feature is supported by the Affiniti models running software version VM13.0 or higher, including Affiniti CVx, Affiniti 70, Affiniti 50, and Affiniti 30. The SVS and SWM software features are associated with the cardiac adult indication.

The provided document details the 510(k) clearance for Philips Ultrasound's EPIQ and Affiniti Series Diagnostic Ultrasound Systems with the Smart View Select (SVS) v2 software. The SVS feature is an automated software that assists users in selecting images for Left Ventricle (LV) analysis using existing Philips AutoStrain LV or 2D Auto LV applications in Adult Echo Transthoracic (TTE) examinations. It classifies acquired images by view using a Deep Learning AI interface and then uses a non-AI algorithm to select an optimal set of images.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The study aimed to demonstrate agreement between LV analysis outputs (Ejection Fraction - EF, and Global Longitudinal Strain - GLS) derived from manually selected clips (ground truth) and automatically selected clips by the SVS software.

2. Sample Size and Data Provenance

• Test Set Sample Size: The exact number of patients or cases in the test set is not explicitly stated as a single number. However, the demographic characteristics section indicates n=71 for various demographic variables like Sex, Age, Height, Weight, BMI, Race, LV systolic function, RWMA, Known CAD, Previous reported MI Location, and LV Hypertrophy, suggesting the test dataset comprised data from at least 71 unique patients.
• Data Provenance: The data was collected from a US-based medical center. The study was a retrospective data analysis.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three (3) reviewers (clinical experts) participated in establishing the ground truth.
• Qualifications of Experts: They are referred to as "clinical experts." No further specific qualifications (e.g., years of experience, specific board certifications like radiologist/cardiologist) are provided in the document.

4. Adjudication Method for the Test Set

The adjudication method used to establish ground truth was consensus/averaging. For each output (GLS and EF), the average across the three reviewers was used as the ground truth.

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

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was described. The study focused on comparing the AI-selected clips' performance (GLS and EF) against the ground truth established by human experts using manually selected clips. There is no information provided regarding how much human readers improve with AI vs. without AI assistance. The study evaluates the AI's ability to select optimal clips, a step that precedes human analysis with AutoStrain LV.

6. Standalone Performance Study (Algorithm Only)

Yes, a standalone performance study was done. The performance of the SVS software was evaluated solely based on its ability to automatically select appropriate clips, and then the subsequent, un-edited evaluation of GLS and EF through AutoStrain LV using these SVS-selected clips was compared against the human-selected clips. This represents the algorithm's performance in its specific task (clip selection) without direct human intervention in the selection process.

7. Type of Ground Truth Used

The ground truth used was expert consensus. Specifically, it was the average of GLS and EF measurements obtained from clips manually selected and subsequently semi-automatically processed by three clinical experts using the AutoStrain LV software.

8. Sample Size for the Training Set

The document does not provide the sample size used for the training set of the deep learning AI model for image classification. It only states that "the neural network of the subject device was revised as described in attachment 002," implying updates to an existing model rather than a completely new one, but no training data details are given.

9. How Ground Truth for Training Set was Established

The document does not explicitly state how the ground truth for the training set was established. It mentions that the "classification is based on a Deep Learning AI interface engine," but details regarding the training data annotation and ground truth establishment are not provided within the excerpt.

Ask a specific question about this device

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.
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.

The R-Trigger algorithm software feature on Philips EPIQ and Affiniti Ultrasound System is intended to support detection of R-wave peak (R-trigger) as an input to certain TTE clinical applications, initially including AutoStrain LV, AutoEF, 2D Auto LV (collectively referred to as "AutoStrain"), and AutoMeasure applications. The R-trigger algorithm is planned to be implemented as workflow enhancement for transthoracic clinical applications on EPIQ and Affiniti Ultrasound Systems in the VM13 software release. The Auto-Measure and AutoStrain features support users during B-mode (2D), CW-, PW- and TDI-Doppler measurements by automating some of the measurements needed to complete a routine transthoracic echo (TTE) exam for adult patients. The R-trigger feature (non-ECG-based) has been developed to enable clinical users to use AutoMeasure and AutoStrain application without the R-trigger (ECG based) input, which is currently required. There are no hardware changes to the EPIQ and Affiniti systems due to change to the introduction of the R-Trigger software application. The software application is supported by all EPIQ and Affiniti models running software version 13.0 or higher.

The provided FDA 510(k) clearance letter describes the R-Trigger software application on Philips EPIQ and Affiniti Ultrasound Systems, which aims to provide an alternative method for detecting R-wave peaks (R-triggers) for cardiac clinical applications like AutoStrain and AutoMeasure, especially when the ECG signal is unavailable or unusable.

Here's an analysis of the acceptance criteria and the study proving the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

The primary acceptance criteria for the R-Trigger algorithm are related to the agreement of its R-wave time stamp detection with the ground truth (ECG-based R-trigger) and the subsequent impact on the clinical outputs of AutoMeasure and AutoStrain. These are evaluated using Bland-Altman analysis (for agreement, specifically the Upper and Lower Limits of Agreement, LoA) and Pearson's correlation (for correlation, specifically the Lower Confidence Bound, LCB).

Ask a specific question about this device

Indications for Use
Focal seizure detection (with or without secondary generalization) in patients with epilepsy age 6 years and older.

160 MHz 802.11ax Wi-Fi and Bluetooth 5.0 (Dual Band)

The provided FDA 510(k) clearance letter and summary for the Philips Lumify Diagnostic Ultrasound System (K242519) primarily focus on demonstrating substantial equivalence to predicate and reference devices, rather than detailing a specific study to prove the device meets acceptance criteria in a comprehensive clinical performance sense for a new AI/software feature.

The submission is for the addition of a new transducer (C9-4ec) and a "Fertility Package" feature. The primary change is the addition of the Trans-vaginal clinical indication, enabled by the C9-4ec transducer.

Therefore, many of the requested points regarding acceptance criteria, specific studies, sample sizes, and ground truth establishment for a clinical performance study are not explicitly detailed in the provided documents, as the application relies more on non-clinical performance data and comparison to already cleared devices.

Here's a breakdown of the information that can be extracted and what is not available:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not contain a table of specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy targets) for clinical performance of the Fertility Package or the C9-4ec transducer, nor does it report specific clinical performance metrics. Instead, "acceptance criteria were met" is a general statement from non-clinical testing.

The document indicates that non-clinical verification testing was conducted to address system-level requirements and design specifications, and that the device complies with referenced standards.

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

The document explicitly states: "The proposed Lumify Diagnostic Ultrasound System with C9-4ec transducer did not require clinical data for determination of substantial equivalence."

Therefore, there is no mention of a clinical "test set" sample size or data provenance (country of origin, retrospective/prospective) for a clinical performance study. The evaluation focused on non-clinical performance and substantial equivalence.

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

Not applicable, as no clinical test set requiring expert-established ground truth for performance metrics is described.

4. Adjudication method for the test set

Not applicable, as no clinical test set requiring adjudication is 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

Not applicable. The document does not describe an AI-assisted diagnostic feature that would warrant an MRMC study comparing human readers with and without AI assistance. The "Fertility Package" provides measurement tools and a summary page, which are productivity/workflow enhancements rather than AI-driven diagnostic interpretations.

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

Not applicable. The "Fertility Package" appears to be a set of measurement and reporting tools, not a standalone diagnostic algorithm.

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

Not applicable for a clinical performance study since none was conducted or reported. For the non-clinical testing, the "ground truth" would be the engineering specifications and recognized industry standards against which the device's hardware and software performance were verified.

8. The sample size for the training set

Not applicable, as no clinical data-driven "training set" for a new algorithm is described or implied. The Fertility Package seems to be functionality built upon established ultrasound principles and measurement techniques found in reference devices.

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

Not applicable, as no training set for a new algorithm is described or implied.

Ask a specific question about this device

EPIQ: The intended use of Philips EPIQ 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), 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.

Affiniti: The intended use of the 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.

The purpose of this Special 510(k) Pre-Market Notification is to modify the Segmental Wall Motion and introduce Auto EF with contrast software application onto the Philips EPIQ Series Diagnostic Ultrasound System and Affiniti Series Diagnostic Ultrasound Systems. SWM algorithm was previously cleared (K243862) and Auto EF contrast algorithm(K243235) was also previously cleared. The current software release version VM 13, replaces the previous version of the segmental wall motion algorithm included in version 11 of the software release with the current cleared version (K243862) without any modifications, and integrates Auto EF contrast algorithm(K243235) without any modifications into one software release.

The SWM v2 software automatically evaluates the segmental (regional) function of the left ventricle (LV) from adult TTE echo examinations. For input, the SWM algorithm uses 3 apical views (A4C, A2C and A3C) and performs border detection and tracking to identify each of the LV segments based on the three views. The SWM v2 software is a semi-automated quantitative imaging algorithm, as users are generally expected to review and concur with the initial and generated results. The users can also manually edit algorithm-generated segmental wall motion scores for individual segments based on their clinical expertise.

Auto EF with contrast is an AI based automated software feature that assists clinicians with assessing Left Ventricular Ejection Fraction (LVEF) from images acquired with contrast agent as part of an adult transthoracic echo (TTE) examination. The feature is located within the Philips Auto EF Adv application. Auto EF with contrast uses 2 apical views (Apical four chamber view (A4C), Apical two chamber (A2C)) and provides EF for each view and a biplane Simpsons EF.

No hardware changes to the EPIQ or Affiniti systems were made due to the SWM v2 and Auto EF with contrast, and existing, cleared Philips TTE transducers are used with these software applications.

This FDA 510(k) clearance (K251110) modifies the Segmental Wall Motion (SWM) algorithm and integrates an existing Auto EF with contrast software into Philips EPIQ and Affiniti Series Diagnostic Ultrasound Systems. The study details for each software component are primarily based on retrospective data analyses.

Here's a breakdown of the acceptance criteria and study information for each feature:

SWM v2 (Segmental Wall Motion v2)

1. Comparison of the average WMSI from ground truthers to the SWM v2 software's WMSI.
2. Majority agreement: A minimum of 2 out of 3 ground truthers were required to agree on WMSI = 1 (normal) or WMSI > 1 (abnormal) for the exam, which was then compared to the software's WMSI. |
   | 5. Multi-Reader Multi-Case (MRMC) Study | No, an MRMC comparative effectiveness study was not explicitly described. The study compared the algorithm's performance to expert visual estimation as the ground truth. |
   | 6. Standalone Performance | Yes, this was a standalone (algorithm only) performance evaluation against an expert-established ground truth. Although it is a "semi-automated quantitative imaging algorithm" where "users are generally expected to review and concur," the performance assessment described here focuses on the algorithm's output prior to user editing. |
   | 7. Type of Ground Truth Used | Expert consensus/visual estimation by 3 expert cardiologists. |
   | 8. Training Set Sample Size | Not provided in this document. This clearance refers to a previous clearance (K243862) for the SWM v2 algorithm. |
   | 9. Training Set Ground Truth Establishment | Not provided in this document. This clearance refers to a previous clearance (K243862). |

Auto EF with Contrast

1. Manual selection of clips by an experienced sonographer.
2. Manual EF assessment using Simpson's method of disks by 3 qualified sonographers.
3. "Shoulder to shoulder" consensus meetings among the 3 sonographers to review manual measurements, jointly select best traced images ("Best Trace"), and adjust traces if needed.
4. A cardiologist specializing in echo subsequently reviewed the selected A4C and A2C clips with "Best Trace" and the resulting LV EF measurements, performing manual adjustments if needed. These final measurements were used as ground truth. |
   | 5. Multi-Reader Multi-Case (MRMC) Study | No, an MRMC comparative effectiveness study was not explicitly described. This was a direct comparison of the algorithm's standalone performance against a consensus-derived ground truth. |
   | 6. Standalone Performance | Yes, the study describes the "Contrast EF application to an EF output" in an automated fashion, and "The ground truth EF measurements were compared to the Contrast EF automated results for EF (biplane)." This indicates a standalone performance evaluation. |
   | 7. Type of Ground Truth Used | Expert consensus (between 3 sonographers and 1 cardiologist) using manual EF assessment via Simpson's method of disks. |
   | 8. Training Set Sample Size | Not provided. This clearance refers to a previous clearance (K243235) for the Contrast EF algorithm. |
   | 9. Training Set Ground Truth Establishment | Not provided. This clearance refers to a previous clearance (K243235). |

Overall Context:

It's important to note that this 510(k) is a Special 510(k). This type of submission is usually for modifications to a currently cleared device where the changed device does not raise new questions of safety and effectiveness. Both SWM v2 and Auto EF with contrast were previously cleared as standalone applications (K243862 and K243235, respectively). This clearance focuses on integrating these previously cleared algorithms into the Philips EPIQ and Affiniti ultrasound systems and replacing an older SWM algorithm. Therefore, the performance studies described here are primarily to demonstrate that the algorithms maintain their previously established performance when integrated into the new platform, or to provide updated performance data for the newer version of the SWM algorithm.

Ask a specific question about this device

The Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), Pulsed Wave Doppler (PWD), and M modes.

It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Fetal/Obstetric,Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ,Musculoskeletal, Peripheral Vessel, Carotid, Cardiac, Lung, Ophthalmic.

The Lumify system is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.

The Philips Lumify Diagnostic Ultrasound System (Lumify) is a mobile, durable, and reusable, software-controlled medical device, which is intended to acquire high-resolution ultrasound data and to display the data in B mode (2D), Pulsed Wave Doppler, Color Doppler, Combined (B+ Color), and M modes. The Lumify system is compatible with iOS and Android operating systems.

The Lumify Diagnostic Ultrasound System (iOS) utilizes:

1. A commercial off-the-shelf (COTS) iOS mobile item (smart phone or tablet)
2. The Philips Ultrasound Lumify software running as a medical device application on the COTS device
3. The Philips C5-2 Curved array USB transducer
4. The Philips L12-4 Linear array USB transducer
5. The Philips S4-1 Sector array USB transducer
6. Lumify Micro B Transducer Cable
7. Lumify Micro C Transducer Cable
8. Lumify USB-C to USB-C Transducer Cable
9. Lumify Power Module

The purpose of this Traditional 510k pre-market notification is to add Ocular preset to currently commercialized L12-4 transducer available with Lumify Diagnostic Ultrasound System. Addition of Ocular preset will be available under newly added Ophthalmic clinical indication, as part of this 510k submission.

The Ocular Preset is an imaging setting to image the eye. It supports 2D (B Mode) and Color Doppler Mode and is available under "Ophthalmic" clinical indication.

The ocular preset is available to download with the Lumify 5.1 software and is available with the previously commercialized L12-4 Lumify transducer.

Based on the provided FDA 510(k) clearance letter for the Philips Lumify Diagnostic Ultrasound System (K242670), here's an analysis regarding acceptance criteria and the study that proves the device meets them:

It's crucial to understand that this 510(k) application is for an addition of an "Ocular preset" to an already cleared device (Lumify Diagnostic Ultrasound System, K192226), utilizing an already cleared transducer (L12-4). The core technology and device itself are established. Therefore, the "study" described focuses on validating the new Ocular preset and Ophthalmic indication against existing standards and a reference device, rather than a full de novo clinical trial for a completely new device.

Key takeaway: The document explicitly states, "The proposed Lumify Diagnostic Ultrasound System with Ocular preset did not require clinical data for determination of substantial equivalence" and "For testing, all pre-determined acceptance criteria were met." This suggests the acceptance criteria were primarily met through non-clinical performance testing and substantial equivalence arguments based on technical similarity to a predicate and reference device that already had the Ophthalmic indication.

Acceptance Criteria and Device Performance

Since no specific quantitative acceptance criteria or clinical study results are detailed in the provided document (as it was deemed unnecessary for this 510(k)), we infer the acceptance criteria from the information presented:

Table of Acceptance Criteria and Reported Device Performance

Study Details (Based on the supplied document)

Given that the submission category is a "Traditional 510(k)" for an addition to an already cleared device, and not a de novo submission or one requiring extensive clinical data, the "study" primarily consists of non-clinical performance testing and a technological comparison to establish substantial equivalence.

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

   • Test Set Sample Size: Not explicitly stated as a number of cases or images. The testing conducted was "non-clinical verification testing" to address system-level requirements, design specifications, and risk control measures. This implies testing against engineering specifications and possibly phantom studies rather than a clinical dataset of patients.
   • Data Provenance: Not applicable in the context of a clinical test set from patients. The testing was internal to Philips Ultrasound, conducted according to their internal procedures.

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

   • This information is not provided as no clinical test set requiring expert ground truth establishment was deemed necessary for this 510(k) submission. The substantial equivalence argument relies on the prior clearance of the predicate and reference devices for similar indications.

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

   • None is explicitly described. As no clinical test set was required for human review with an established ground truth, adjudication methods are not applicable here.

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:

   • No MRMC study was done. This 510(k) is for a diagnostic ultrasound system and its imaging preset, not an AI/CADe/CADx device that assists human readers. Therefore, the concept of human readers improving with AI assistance is not applicable to this submission.

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

   • Not applicable. This is a diagnostic imaging system, not an algorithm. Its performance is inherent to its ability to acquire and display ultrasound data.

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

   • For the non-clinical performance testing, the "ground truth" would be the engineering and performance specifications the device was designed to meet. For the substantial equivalence argument, the effective "ground truth" is the demonstrated safe and effective performance of the predicate and reference devices for similar imaging capabilities. No clinical ground truth (e.g., pathology, outcomes) was required for this specific 510(k) submission.

7. The sample size for the training set:

   • Not applicable. This is a traditional diagnostic ultrasound system, not an AI/machine learning product that requires a "training set" in the conventional sense. The "training" of the system refers to its design and engineering to meet diagnostic imaging requirements.

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

   • Not applicable, as there is no "training set" in the machine learning context for this device. Ground truth for the underlying ultrasound technology would be established through physics principles, engineering design, and prior clinical validation of similar devices.

In summary, the provided document explicitly states that clinical data was not required for this 510(k) submission. The acceptance criteria were primarily met through non-clinical performance testing (design reviews, risk analysis, system requirements verification) and demonstrating substantial equivalence to existing, cleared devices (the predicate Lumify system and the Sparq system which already has an Ophthalmic indication for the L12-4 transducer), ensuring the new Ocular preset did not introduce new safety or effectiveness concerns.

Ask a specific question about this device

The Flash Ultrasound System 5100 Point of Care (5100 POC and 5100 POC Pro) is indicated for diagnostic ultrasound imaging and fluid flow analysis of the human body, with the following indications for use:

Abdominal, Adult Cephalic, Cardiac Adult, Cardiac Pediatric, Cerebral Vascular, Fetal/OB, Lung, Musculoskeletal (Conventional), Musculoskeletal (Superficial), Neonatal Cephalic, Ophthalmic, Other: Carotid, Other: GYN, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Trans-Esophageal (Cardiac), Trans-Vaginal.

Modes of operation include B Mode (or 2D), Color Doppler, Color Power Angio Doppler, Continuous Wave Doppler, Pulse Wave Doppler, Tissue Doppler, M-Mode (including anatomical M-Mode), Harmonics (Tissue), and Combined modes.

The clinical environments where the Flash Ultrasound System 5100 POC may be used are: hospitals, surgery centers, clinics, physicians' offices, diagnostic centers, critical care and emergency room environments, and point-of-care clinical settings 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 the user's responsibility for sound clinical judgment and best clinical procedure.

The Flash Ultrasound System 5100 Point of Care (POC) device is constructed with assets from the previously cleared 5000 Compact Series hardware platform (K222648) and a new Rhythm software platform that is new to the POC environment.

The Flash Ultrasound System 5100 POC supports a full touch screen interface on the main display as the primary means of directing the system, leveraging customer familiarity with smart devices and the ease of cleaning and maintenance of a pure glass surface.

Additionally, Flash Ultrasound System 5100 POC is designed to fit into tight spaces in a crowded Emergency Room (ER) with its small footprint, sleek design, and a large vertical tablet with ergonomic controls. The new Rhythm software offers point-of-contact workflow enhanced with assisted needle visualization, streamline point-of-care workflows such as flexible patient data management and AutoStrain EF. In addition to these POC workflows, the Rhythm software provides enhanced responsiveness with an easy-to-learn user interface as all controls are located in the same plane as the user's eye and hand for working more efficiently with the patient. The Flash Ultrasound System 5100 POC has two models, the 5100 POC and the 5100 POC Pro. The 5100 POC version does not support two transducers, C5-1 and X8-2t; however, the 5100 POC Pro supports all the transducers listed for the system.

The provided FDA 510(k) clearance letter and summary for the Flash Ultrasound System 5100 Point of Care do not include detailed information about specific acceptance criteria related to its performance as a diagnostic imaging device (e.g., sensitivity, specificity, resolution), nor does it describe a study specifically designed to prove these performance metrics.

Instead, the document focuses on demonstrating substantial equivalence to predicate devices through a combination of design features, intended use, fundamental scientific technology, and a comprehensive suite of non-clinical performance and safety testing.

Here's an analysis based on the provided text, addressing the requested information to the extent possible:

Acceptance Criteria and Study Proving Device Meets Criteria

The submission primarily emphasizes compliance with recognized standards and verification testing against system and design specifications, rather than clinical performance metrics in a sense that would typically involve sensitivity, specificity, or human reader improvement with AI assistance.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the provided text, the "acceptance criteria" are broad compliance with international standards and internal design specifications, and the "reported device performance" is that these criteria were met.

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

• Not explicitly stated for clinical performance. The document states: "The proposed Flash Ultrasound System 5100 POC did not require clinical data for determination of substantial equivalence." This implies that no clinical test set (patient data) was used in a comparative effectiveness study for this submission. The testing was primarily non-clinical.
• Data Provenance: N/A for clinical performance. For non-clinical testing, the provenance would be internal Philips Ultrasound LLC laboratory testing.

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

• Not applicable. Since clinical data was not required for substantial equivalence, there was no independent expert panel establishing ground truth on patient cases for performance evaluation.

4. Adjudication Method for the Test Set

• Not applicable. No clinical test set requiring adjudication was used.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

• No. The document explicitly states: "The proposed Flash Ultrasound System 5100 POC did not require clinical data for determination of substantial equivalence." Therefore, no MRMC study was conducted to evaluate human reader improvement with AI assistance (as AI assistance is not mentioned as a feature of the device's diagnostic performance, but rather "assisted needle visualization" is a workflow enhancement).

• Effect size of human readers improve with AI vs without AI assistance: Not applicable, as no such study was performed or needed for this clearance. The "assisted needle visualization" is a feature mentioned, but its impact on reader performance is not quantified in this submission.

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

• Not applicable for diagnostic performance metrics. The device is an ultrasound system with various imaging modes and "assisted needle visualization." While there is a "new Rhythm software platform," the submission does not present it as a standalone diagnostic algorithm requiring performance metrics like sensitivity/specificity on its own. Its performance is integrated into the ultrasound system's overall functionality.

7. The Type of Ground Truth Used

• For non-clinical testing: The ground truth would be defined by the specifications and expected outputs of the system based on physical and engineering principles, verified through testing against known inputs or reference standards (e.g., phantom measurements, electrical signals, safety limits).
• For diagnostic clinical performance: No clinical ground truth (e.g., expert consensus, pathology, outcomes data) was used or required for this 510(k) submission.

8. The Sample Size for the Training Set

• Not applicable. The submission does not describe the development or training of a de-novo AI algorithm that would require a "training set" in the context of generating diagnostic performance metrics. The "Rhythm software" is mentioned, and "assisted needle visualization" is a feature, but the document focuses on its equivalence and compliance, not on a machine learning training paradigm.

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

• Not applicable. As no training set for a diagnostic AI algorithm in the context of performance evaluation was described, the method for establishing its ground truth is not provided.

Ask a specific question about this device

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. 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 guidance.

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.

The purpose of this Traditional 510(k) Pre-Market Notification is to introduce Remote Software Management (RSM) software feature onto the EPIQ and Affiniti Series Diagnostic Ultrasound Systems. The proposed EPIQ Series Diagnostic Ultrasound System and Affiniti Series Diagnostic Ultrasound Systems with new RSM software feature, which is a workflow-enhancement software feature, is equivalent to predicate device, K242020. The Philips RSM feature provides the capabilities to remotely upgrade EPIQ/Affiniti Systems, with the existing RSM capabilities, only patch upgrade was possible, and full upgrade (including OS components) was not supported. The full RSM feature provides the capabilities to perform a remote upgrade to EPIQ/Affiniti Systems. The RSM feature is capable of deploying following packages onto the system: OS Packages, Device Drivers, Printer Drivers, BIOS/UEFI version, Application Packages, Service Application Packages, Automatic backup/restore of existing system settings. Along with the above functionalities, it also supports Automatic and Scheduled software downloads/Installation. No hardware changes to the EPIQ or Affiniti Systems are required when using RSM software feature, and existing, commercialized Philips transducers are used for the RSM software feature. The feature is supported by EPIQ and Affiniti models running software version 12.0.

The provided FDA 510(k) clearance letter (K250177) describes the Philips EPIQ and Affiniti Series Diagnostic Ultrasound Systems with a new feature: Remote Software Management (RSM). The submission focuses on demonstrating substantial equivalence to a predicate device (K242020), specifically highlighting the enhancements to the RSM feature.

Here's an analysis of the acceptance criteria and study information, based on the provided document:

Acceptance Criteria and Device Performance

The document describes the acceptance criteria in terms of the RSM feature's capabilities and its performance in comparison to the predicate device's existing RSM. The key acceptance criteria revolve around the ability to perform comprehensive remote software upgrades without compromising safety or effectiveness.

Table 1: Acceptance Criteria and Reported Device Performance for Remote Software Management (RSM)

Study Details for Demonstrating Equivalence and Meeting Criteria

The provided document does not describe a clinical study or a comparative diagnostic performance study in the traditional sense, as the submission focuses on a software workflow enhancement feature (Remote Software Management). Instead, the "study" for this feature is a series of non-clinical performance tests and a demonstration of substantial equivalence.

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

• Test Set Sample Size: Not explicitly stated as a numerical sample size of patient data or images. The "test set" in this context refers to the simulated testing environments or actual ultrasound systems used to validate the RSM feature.
• Data Provenance: Not applicable in the context of diagnostic image data. The validation would have involved testing the software functionality on the EPIQ and Affiniti platforms. The document mentions "Philips Internal Procedures" for testing.

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

• Not applicable as this submission is for a software management feature, not a diagnostic algorithm that requires ground truth established by medical experts. The validation would have been performed by software/system engineers and subject matter experts in software deployment and system functionality.

3. Adjudication method for the test set:

• Not applicable for this type of submission. The "adjudication" would be internal verification and validation against functional and performance requirements by the development and quality assurance teams.

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:

• No MRMC comparative effectiveness study was done. This submission is for a Remote Software Management feature, which is a workflow enhancement for system maintenance, not a diagnostic AI tool that assists human readers.

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

• The "standalone" performance here refers to the RSM feature functioning correctly on its own in deploying software updates. The document states:
  • "All software verification tests met the acceptance criteria."
  • "Results of these tests show that the proposed Remote Software Management software feature meets the intended use."
  • This implies that the algorithm/feature was tested to ensure it performs its intended function (remote upgrades, backups, scheduled downloads) accurately and reliably.

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

• Not applicable in the medical/diagnostic sense. The "ground truth" for the RSM feature would be the successful execution of its defined functional and performance requirements (e.g., a software package is correctly installed, system settings are retained, the system remains operational after an upgrade).

7. The sample size for the training set:

• Not applicable. This is not a machine learning or AI algorithm in the context of diagnostic interpretation that requires a "training set" of patient data.

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

• Not applicable as there is no training set for a diagnostic algorithm.

Summary of the Study and Equivalence Argument:

The "study" described in K250177 for the Remote Software Management (RSM) feature primarily consisted of non-clinical performance testing and software verification/validation.

• Approach: Philips evaluated the RSM feature against internal procedures, adhering to software lifecycle processes (IEC 62304) and risk management (ISO 14971).
• Comparison Basis: The proposed RSM feature was compared to the predicate device's existing, more limited RSM capabilities (which only supported bug fixes and patch upgrades). The new feature expands this to include major software releases, OS components, drivers, BIOS/UEFI versions, application packages, service application packages, and automatic backup/restore.
• Conclusion of Testing: "All software verification tests met the acceptance criteria." and "Results of these tests show that the proposed Remote Software Management software feature meets the intended use."
• Substantial Equivalence Argument: The document argues that this enhancement is substantially equivalent to the predicate device because it does not introduce new questions of safety or effectiveness. The core function of the ultrasound system (diagnostic imaging) remains unchanged, and the RSM feature is purely a workflow enhancement for system maintenance. No hardware changes are required, and existing transducers are used. The comparison table directly addresses the differences and highlights how the improved RSM capabilities are an extension of the predicate's feature, not a fundamentally new diagnostic function.

Ask a specific question about this device

Indications for use of the product are quantification and reporting of cardiovascular, fetal, and abdominal structures and function of patients with suspected disease to support the physician in the diagnosis.

The purpose of this Traditional 510(k) Pre-market Notification is to introduce the SWM, 3D Auto TV and 3D Auto CFQ software applications as well as compatibility of VeriSight ICE / Pro ICE Probe data with the subject device Ultrasound Workspace Version 6.0.

The semi-automated Segmental Wall Motion feature (SWM) evaluates the segmental (regional) function of the left ventricle (LV) from adult TTE echo examinations. It performs border detection and tracking to identify each of the LV seqments, provides segmental wall motion scores for each segments of the LV by using machine learning algorithms and calculates an overall wall motion score index (WMSI) as the average of the segmental scores.

3D Auto TV software enables semi-automated quantification of the tricuspid valve. At a high level, this is accomplished through automatically derived measurements from a segmented model of the tricuspid valve annulus formed by the software through model-based segmentation of the acquired ultrasound images.

3D Auto CFQ provides semi-automated quantification of Mitral Requrgitation (MR) volume and peak flow rate based on 3D color flow images. This application uses a known fluid dynamic model of flow that is adapted to the acquired color information. This allows quantitative assessment of mitral valve leakage during systole. The derived result supports the assessment of mitral regurgitation volume and peak flow rate.

Data Compatibility of the VeriSight ICE / Pro ICE Probe, transducers cleared for the EPIQ Series Diagnostic Ultrasound System (K202216), will be introduced for Ultrasound Workspace 6.0.

General software architecture of the previously cleared version TOMTEC-ARENA remains unchanged. Two new clinical application packages will be introduced with UWS6.0: 3D Auto TV and 3D Auto CFQ. An existing feature AutoStrain Left Ventricle (AutoStrain LV) gains additional functionality by integration of Segmental Wall Motion (SWM) feature. The module using AutoStrain LV together with SWM is named 2D Auto LV.

Here's a breakdown of the acceptance criteria and study information for the Philips Ultrasound Workspace (UWS 6.0) based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Segmental Wall Motion (SWM):

  • Test Set Sample Size: Not explicitly stated as a number, but the study involved "subjects referred for clinical TTE exam."
  • Data Provenance: Retrospective, from transthoracic (TTE) ultrasound clips. Country of origin not specified.

• 3D Auto TV:

  • Test Set Sample Size: Not explicitly stated as a number, but involved "subjects whose clips contributed to the study." These subjects "represented a broad range of demographics, body habitus, and their severity of tricuspid regurgitation."
  • Data Provenance: Not explicitly stated as retrospective or prospective, but used "transesophageal echocardiography (TEE) cardiac clips." Country of origin not specified.

• 3D Auto CFQ:

  • Test Set Sample Size: Not explicitly stated as a number, but involved "the same subjects" for comparisons between 3D Auto CFQ and 2D PISA.
  • Data Provenance: Not explicitly stated as retrospective or prospective. Used "acquired 3D color flow images" and compared to Cardiac Magnetic Resonance Imaging (CMR). Country of origin not specified.

3. Number of Experts and Qualifications for Test Set Ground Truth

• Segmental Wall Motion (SWM): Not applicable for SWM's primary validation as it was compared against another software application (LVivo SWM) as ground truth.
• 3D Auto TV: 3 clinical experts (reviewers). Qualifications for these experts are not explicitly stated beyond "clinical experts (reviewers)."
• 3D Auto CFQ: Not applicable for 3D Auto CFQ's primary validation as it was compared against CMR as ground truth, and for peak flow, against 2D PISA methodology.

4. Adjudication Method for the Test Set

• Segmental Wall Motion (SWM): Not applicable, as the comparison was algorithm-to-algorithm.
• 3D Auto TV: No explicit mention of an adjudication method among the three experts. The text states "results compared to manual measurements by the same reviewers performed within 4D Cardio-View application, used as a ground truth." This implies individual expert measurements were used for comparison, but not necessarily adjudicated for consensus beyond the individual performing the manual measurement.
• 3D Auto CFQ: Not applicable, as the comparison was against objective measures (CMR) and an accepted methodology (2D PISA).

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

• No MRMC comparative effectiveness study is mentioned that measures the effect size of how much human readers improve with AI vs without AI assistance. The studies performed were for standalone performance (SWM, 3D Auto TV, 3D Auto CFQ algorithms) compared to established ground truths or other methods. A summative evaluation for 2D Auto LV, including SWM, indicated that "16 target users completed the critical tasks... with a success rate of 97.7%," but this is a user experience/usability study, not a comparative effectiveness study measuring improved human performance with AI.

6. Standalone (Algorithm Only) Performance Study

• Yes, standalone performance studies were done for each new feature:
  • SWM: The SWM algorithm's performance was evaluated against the LVivo SWM application ("ground truth"). This is a standalone algorithm-to-algorithm comparison.
  • 3D Auto TV: The 3D Auto TV software's performance was evaluated by comparing its derived measurements to manual measurements performed by clinical experts using the 4D Cardio-View application ("ground truth"). Although experts performed the "ground truth" measurements, the focus was on the algorithm's accuracy relative to these manual measurements.
  • 3D Auto CFQ: The 3D Auto CFQ software's performance was evaluated by comparing its regurgitant volume output to Cardiac Magnetic Resonance Imaging (CMR) ("ground truth") and its peak regurgitant flow output to the 2D PISA methodology. These are standalone evaluations of the algorithm's outputs.

7. Type of Ground Truth Used

• Segmental Wall Motion (SWM): Ground truth was established by comparing the SWM algorithm's output to the LVivo SWM (DiA Imaging Analysis) application. This is an algorithm-to-algorithm comparison where the comparator software is considered the ground truth.
• 3D Auto TV: Ground truth was established by manual measurements performed by clinical experts within the 4D Cardio-View application. This represents expert-derived measurements from a reference software application. In-silico phantoms with known dimensions were also used for accuracy and precision of underlying measurement primitives.
• 3D Auto CFQ:
  • For regurgitant volume: Cardiac Magnetic Resonance Imaging (CMR) regurgitant volume (RVol) was used. This is considered an outcomes data/reference standard.
  • For peak regurgitant flow: 2D PISA methodology was used. This is an expert-derived methodology/reference method.

8. Sample Size for the Training Set

• The document does not explicitly state the sample sizes used for training the machine learning algorithms for SWM, 3D Auto TV, or 3D Auto CFQ. It only refers to the retrospective nature of some of the test data.

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

• The document does not explicitly describe how the ground truth for the training set was established for any of the machine learning algorithms. It mentions the "use of machine learning algorithms" but focuses on the validation (test set) ground truth.

Ask a specific question about this device

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.

Ask a specific question about this device