Search Results

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

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 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,

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 (2D), Pulsed Wave Doppler, Color Doppler, Combined (B+ Color), and M modes.

The Lumify Diagnostic Ultrasound System (Android) utilizes:

• A commercial off-the-shelf (COTS) Android mobile device (smart phone or tablet)
• The Philips Ultrasound Lumify software running as an application on the COTS device
• The Philips C5-2 Curved array USB transducer
• The Philips L12-4 Linear array USB transducer
• The Philips S4-1 Sector array USB transducer
• Lumify Micro B Transducer Cable
• Lumify Micro C Transducer Cable

The Lumify system is compatible with iOS or Android operating systems. The Lumify system software provides various imaging features, including an Android-specific feature with artificial intelligence (AI) based, Auto EF Quantification (ejection fraction) technology during cardiac imaging.

Here's a breakdown of the acceptance criteria and the study details for the Philips Lumify Diagnostic Ultrasound System with Auto EF Quantification, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: 80 patients' Apical 4 Chamber (A4CH) view clips.
• Data Provenance: The data were acquired with the Lumify Diagnostic Ultrasound System, specifically for this clinical performance study. Patients were selected based on eligibility, and data were acquired consecutively for patients with normal and impaired LV function. This suggests a prospective acquisition for the purpose of the study. The document does not specify the country of origin for the data.

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

The ground truth was established by "manual tracing performed by sonographers."

• Number of Experts: The document refers to "sonographers" in the plural, but does not specify the exact number of sonographers involved in the manual tracing.
• Qualifications of Experts: The document implies that these were qualified "sonographers" experienced in echocardiographic LV function evaluation, but does not provide specific qualifications (e.g., years of experience, board certification). It can be inferred that they are healthcare professionals who routinely perform this task.

4. Adjudication Method for the Test Set

The ground truth for EF, EDV, and ESV was established by the "average results by manual tracing." This implies that IF multiple sonographers performed the manual tracings, their results were averaged. However, it does not explicitly state an adjudication method like 2+1 or 3+1 (where discrepancies are resolved by a third expert or consensus). It refers to "the average results by manual tracing," suggesting a quantitative aggregation rather than a specific adjudicative consensus process if multiple readers were used. If only one sonographer performed the tracing for each case, no adjudication would be necessary.

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

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done to evaluate how much human readers improve with AI vs. without AI assistance. The study focuses on the agreement between the AI's automated measurements and a "manual tracing" ground truth, not on reader performance with and without AI assistance.

6. Standalone (Algorithm Only) Performance

Yes, a standalone study was done. The clinical performance study directly compared the "automated EF evaluation by LVivo EF" (the algorithm's performance) against "Ejection Fraction (EF) evaluation by manual tracing performed by sonographers" (the ground truth). The results (correlation coefficients) reflect the algorithm's performance without a human-in-the-loop scenario. The LVivo EF automatically processed 95% of the clips, indicating its standalone capability.

7. Type of Ground Truth Used

The ground truth used was expert consensus/manual tracing. Specifically, it was defined as "Ejection Fraction (EF) evaluation by manual tracing performed by sonographers" and "the average results by manual tracing" for EF, EDV, and ESV. This is considered an expert-derived ground truth based on conventional, established methods for echocardiographic LV function evaluation.

8. Sample Size for the Training Set

The document explicitly states: "The data used for clinical performance study were completely distinct from that used during training of the algorithm, and there was no overlap between the two data sets." However, it does not provide the sample size for the training set used to develop the LVivo EF algorithm.

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

The document states that the clinical performance study data were "completely distinct from that used during training of the algorithm," but it does not describe how the ground truth for the training set was established. It implies that such a training process occurred ("training of the algorithm"), but details on its ground truth are not provided in this summary.

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.

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, software-controlled medical device, which is intended to acquire high-resolution ultrasound data and to display the data in B (2D), Pulsed Wave Doppler, Color Doppler, Combined (B+ Color), and M modes. It is intended to be used by trained professionals at various settings of patient point of care such as clinical admission, periodic evaluations, and prior to hospitalization discharge,

The Lumify system is compatible with iOS or Android operating systems. The B-lines feature is compatible only with Android operating systems and utilizes:

• A commercial off-the-shelf (COTS) Android mobile device (smart phone or tablet)
• The Philips Ultrasound Lumify software running as an application on the COTS device
• The Philips C5-2 Curved array USB transducer
• The Philips L12-4 Linear array USB transducer
• The Philips S4-1 Sector array USB transducer
• Lumify Micro B Transducer Cable
• Lumify Micro C Transducer Cable

The Lumify system software provides various imaging features, including an Android-specific feature with a guided scan protocol for comprehensive exams and real-time automated B-line assessment during lung exams.

Acceptance Criteria and Device Performance Study for Philips Lumify Diagnostic Ultrasound System (K223771)

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Philips Lumify Diagnostic Ultrasound System with the Expanded B-lines Software Feature were pre-defined success criteria for the AI algorithm's agreement with clinician readings (ground truth).

Note: The lower confidence limit of 0.746 for both sensitivity and specificity was explicitly determined through a pilot study to assess clinician agreement, forming the basis for the acceptance criteria for merged B-line detection. While an explicit numerical acceptance criterion for ICC in B-line counting isn't provided, the conclusion states the device met clinical user needs as intended, implying satisfactory performance against an internal threshold.

2. Sample Size and Data Provenance for Test Set

• Sample Size: 416 lung ultrasound (LUS) video loops.
• Data Provenance:
  • Collected from 157 subjects presenting with shortness of breath in a hospital setting.
  • Each subject may have contributed up to 4 video loops.
  • The study data were collected to ensure full coverage of the lung (posterior and anterior, left and right).
  • Representative of videos collected from three different transducers (C5-2, L12-4, S4-1).
  • The study used previously collected clinical ultrasound images.
  • Retrospective: The phrasing "previously collected clinical ultrasound images" suggests the data was retrospective, gathered before the specific performance study was conducted.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly state the number of experts used to establish the ground truth for the test set. However, it indicates that the ground truth was established by "clinicians" and refers to "clinician readings."

The qualifications of these clinicians are not specifically detailed (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set

The adjudication method is described as "majority agreement" among clinicians. The document states: "ground truth: majority agreement target was determined through pilot study conducted to assess clinician's agreement". This suggests a method where ground truth was established by the consensus of multiple clinicians, likely a 2+1 or similar majority-based approach, though the exact number of clinicians involved in each decision is not specified.

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

The document does not describe a multi-reader, multi-case (MRMC) comparative effectiveness study designed to measure the effect size of human readers improving with AI vs. without AI assistance. The study focuses solely on the standalone performance of the AI algorithm against clinician-established ground truth.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance study was conducted. The "Artificial Intelligence Summary" explicitly states: "A study using previously collected clinical ultrasound images with prospective reads by clinicians was conducted to evaluate the performance (including merged B-lines and B-line counting)." The reported sensitivity, specificity, and ICC values represent the algorithm's performance independent of real-time human intervention or assistance.

7. Type of Ground Truth Used

The type of ground truth used was expert consensus, specifically "clinician readings" based on "majority agreement."

8. Sample Size for the Training Set

The document explicitly states: "The data used for clinical performance study were completely distinct from that used during training of the algorithm, and there was no overlap between the two data sets." However, it does not provide the sample size for the training set.

9. How Ground Truth for the Training Set Was Established

The document does not provide details on how the ground truth for the training set was established. It only mentions that the training data was distinct from the test data. Given that the algorithm uses machine learning, it is highly probable that the training data also had a ground truth established by experts, but the specifics are not included in this document.

Ask a specific question about this device

Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), 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. Lumify is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.

Lumify Diagnostic Ultrasound System is a mobile, general, software-control medical device, which is intended to acquire high-resolution ultrasound data and to display the data in various modes of operation. It is intended to be used by trained professionals at various clinical settings including point-of-care. The Lumify Diagnostic Ultrasound System provides various imaging features including guided scan protocol for comprehensive lung exam. The introduction of the subject B-lines Feature enables the automated detection and counting of B-lines during a lung exam; the subject feature also provides the users the capabilities of reviewing the detected B-lines and editing the number of B-lines for each scanned lung zone. Clinically, B-line is a lung ultrasound artifact that can aid users in the assessment of patients with a variety of pulmonary conditions and diseases such as pneumonia, pulmonary edema, lung contusion, and acute respiratory distress syndrome (ARDS). The Lumify Diagnostic Ultrasound System includes: - A commercial off-the-shelf (COTS) mobile device l - I Philips Ultrasound software running as an app on the COTS device - I The C5-2 Curved array USB transducer - I The L12-4 Linear array USB transducer - I The S4-1 Sector array USB transducer - I The Lumify Power Module (LPM) to convert the USB interface used on the family of Lumify transducers to Apple's iAP2 Lightning interface standard used on iPhones and iPads, and to provide battery power to the transducers when using an iOS mobile device.

The provided text describes the Philips Lumify Diagnostic Ultrasound System and its new B-lines Feature. However, it does not contain specific acceptance criteria, detailed study results, or information about sample sizes, ground truth establishment, or expert qualifications for the B-lines Feature.

Instead, the document primarily focuses on regulatory approval (510(k) submission) and states generally that "all pre-determined acceptance criteria were met" and "performance test data is provided to support the introduction of the subject software algorithm."

Therefore, I cannot fulfill your request for a detailed table of acceptance criteria, reported performance, sample sizes, ground truth details, expert qualifications, or MRMC study information based solely on the provided text.

Here's what can be extracted and what is missing:

1. A table of acceptance criteria and the reported device performance:

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

• Sample Size (Test Set): Not specified.
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

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

• Not specified.

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:

• An MRMC study is not explicitly mentioned. The document states the B-lines Feature provides "automated detection and counting of B-lines," while the predicate had "manual counting," implying a standalone algorithm. However, no comparative effectiveness study with human readers and AI assistance is described, nor an effect size.

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

• The description of the B-lines Feature ("Automated detection and counting of B-lines from lung ultrasound images") suggests a standalone algorithm component. However, specific standalone performance metrics are not provided. The phrasing "the subject feature also provides the users the capabilities of reviewing the detected B-lines and editing the number of B-lines for each scanned lung zone" indicates a human-in-the-loop interaction, where the user can review and edit the device's output.

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

• Not specified.

8. The sample size for the training set:

• Not specified.

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

• Not specified.

Summary of what is present in the document:

• The device is called the "Lumify Diagnostic Ultrasound System" with a new "B-lines Feature."
• The B-lines Feature provides "automatic detection and counting of B-lines during a lung exam."
• Users can review and edit the detected B-lines.
• Clinically, B-lines are lung ultrasound artifacts that aid in assessing pulmonary conditions.
• The study conducted was "non-clinical testing" addressing the change and performance, following Philips' internal processes (Requirements Review, Risk Analysis and Management, Product Specifications, Design Reviews, Product Performance testing).
• The conclusion states that "all pre-determined acceptance criteria were met" and the device "does not raise new questions of safety or effectiveness and is substantially equivalent to the predicate device."
• The predicate device involved "manual counting of B-lines from lung ultrasound images."

Ask a specific question about this device

Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), 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.

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

The Lumify Diagnostic Ultrasound System is a mobile, general purpose, softwarecontrolled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data in various modes of operation. Lumify is a portable system facilitating point of care ultrasound applications.

The Lumify Diagnostic Ultrasound System includes:

• A commercial off-the-shelf (COTS) Android or iOS mobile device ●
• Philips Ultrasound software running as an app (Android or iOS) on the COTS device ●
• The C5-2 Curved array USB transducer
• The L12-4 Linear array USB transducer
• The S4-1 Sector array USB transducer
• The Lumify Power Module (LPM) to convert the USB interface used on the family of Lumify transducers to Apple's iAP2 Lightning interface standard used on iPhones and iPads, and to provide battery power to the transducers when using an iOS mobile device

This Philips Healthcare K192226 submission is for a Diagnostic Ultrasound System. The information provided does not detail specific acceptance criteria and performance data for an AI/ML component or a standalone algorithm. Instead, it focuses on the substantial equivalence of the Lumify Diagnostic Ultrasound System to a predicate device, primarily addressing hardware and software expansion to support iOS mobile devices.

Therefore, many of the requested data points (such as sample sizes for test and training sets, number of experts for ground truth, adjudication methods, MRMC studies, and standalone algorithm performance) are not applicable or not provided in the given document. The document explicitly states: "The Lumify Diagnostic Ultrasound System did not require clinical studies because substantial equivalence to the currently marketed predicate Lumify Ultrasound System (K162549) has been established."

However, I can extract the information related to the overall system's safety and nonclinical performance testing.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Not applicable, as no clinical studies or specific test set for AI performance are described. The evaluation was based on nonclinical performance testing against established standards and substantial equivalence to a predicate device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Not applicable, as no clinical studies or specific test set requiring expert-established ground truth are described.

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

Not applicable.

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. This device is not described as having an AI-assisted interpretation component for human readers.

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

Not applicable. This submission concerns a diagnostic ultrasound system, not a standalone AI algorithm for interpretation.

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

Not applicable. For the nonclinical performance testing, the "ground truth" would be the specifications and requirements set forth by the cited international and FDA-recognized consensus standards.

8. The sample size for the training set

Not applicable, as no AI/ML algorithm requiring a training set is described in the context of this submission.

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

Not applicable.

Ask a specific question about this device