Search Results

The DGTX CAL is an in vitro diagnostic product for the calibration of digitoxin on the Dimension Vista® System.

The DGTX CAL is a liquid bovine serum based product containing digitoxin.

The provided 510(k) summary for the Dimension Vista® DGTX CAL is for a calibrator device for an in vitro diagnostic system, not a device that involves image analysis or human interpretation. Therefore, many of the typical acceptance criteria and study components related to machine learning performance (e.g., sample size for test sets, data provenance, ground truth experts, MRMC studies, standalone performance, training set details) are not applicable to this type of medical device submission.

This submission focuses on demonstrating substantial equivalence to a predicate calibrator device (Dimension® Drug Calibrator II) by comparing their features, intended use, and formulation. The "study" here is essentially a comparison of product characteristics rather than a clinical performance study.

Here's a breakdown of the requested information, adapted for this specific device type:

1. Table of Acceptance Criteria and Reported Device Performance

For calibrators, the primary "acceptance criterion" is typically substantial equivalence to a legally marketed predicate device. Performance is demonstrated by showing that the new device has comparable characteristics and performs its intended function (calibration) in a similar manner.

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

• Sample Size: Not applicable in the context of a clinical test set. The "test" here involves comparing the characteristics of the new calibrator to the predicate device. This is a descriptive comparison, not a statistical sampling of patient data.
• Data Provenance: Not applicable. The "data" are the specifications and formulation details of the new device and the predicate device.

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

• Number of Experts: Not applicable. Ground truth in the sense of clinical interpretations or diagnoses is not involved. The "truth" here is the chemical composition and physical properties of the calibrator.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. There is no ambiguous clinical data requiring expert adjudication.

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

• MRMC Study: No. This type of study is relevant for diagnostic devices where human readers interpret output, often with AI assistance. A calibrator does not involve human interpretation in this manner.
• Effect Size of Human Readers Improvement with AI vs. without AI assistance: Not applicable.

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

• Standalone Study: No. This concept is for AI algorithms. A calibrator is a chemical reagent, not an algorithm.

7. The Type of Ground Truth Used

• Type of Ground Truth: The "ground truth" for this submission is the physical and chemical specifications, intended use, and formulation details of both the new calibrator and the legally marketed predicate device. The claim is that they are identical or highly similar in relevant aspects.

8. The Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. Calibrators are not "trained" like AI algorithms.

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

• How Ground Truth for Training Set Was Established: Not applicable.

Ask a specific question about this device

The Siemens Koordinat Angiographic X-ray Table family is intended to support and position patients for Angiographic examinations, Angiographic interventional techniques where an X-ray translucent tabletop is required, and for use during surgery where an X-ray translucent tabletop is required.

The Koordinat Table family is a modification to an existing floor mounted X-ray table for angiographic examinations and interventions, and surgery. The modified Koordinat table is based on knowledge and experience gained with the predecessor model, the Koordinat M Table. The Koordinat M was described in the 510(k) Submitted on 4/30/95 with the number K951176.

The provided text is a 510(k) summary for the Siemens Koordinat Angiographic and Operating Room Model X-Ray Table Family. It details the device's intended use and substantial equivalence to predicate devices. However, it does not contain information about acceptance criteria or specific studies demonstrating device performance against such criteria.

Here's why and what information is missing based on your request:

• Type of Device: The device is an X-ray table, which is a physical piece of equipment for patient positioning, not a medical device that produces diagnostic results (like an AI algorithm for image analysis). Therefore, the provided text focuses on hardware specifications and substantial equivalence, not performance metrics like sensitivity, specificity, or accuracy that would be relevant for an AI or diagnostic device.
• Focus of 510(k) Summary: A 510(k) summary primarily demonstrates that a new device is "substantially equivalent" to a legally marketed predicate device. This often involves comparing technological characteristics, intended use, and safety/effectiveness profiles, rather than presenting detailed clinical trial data with acceptance criteria for quantitative performance metrics.

Therefore, for your specific numbered points, the information is largely absent from the provided text:

1. A table of acceptance criteria and the reported device performance: Not present. The text describes the device's function and technical characteristics, but no quantitative performance metrics or acceptance criteria are listed.
2. Sample sized used for the test set and the data provenance: Not applicable/not present. This is a hardware device; there isn't a "test set" of data in the sense you're referring to for AI or diagnostic devices.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable/not present.
4. Adjudication method for the test set: Not applicable/not present.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done: Not applicable/not present. This device is not an AI for image interpretation.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable/not present.
7. The type of ground truth used: Not applicable/not present.
8. The sample size for the training set: Not applicable/not present.
9. How the ground truth for the training set was established: Not applicable/not present.

Summary of available information related to performance/equivalence:

• Device Description: The Koordinat Table family is a modification of an existing floor-mounted X-ray table.
• Technological Characteristics Comparison: The new Koordinat Table has "the same technological characteristics" as the predicate Koordinat M table. The primary difference highlighted is a change from analog to CAN bus interface for reporting and controlling table movements in the higher-end models.
• Predicate Devices: The new models are deemed substantially equivalent to the Koordinat M Table (K951176), OP/PTCA-System 1520 (K883613), Synchra Tilt (K940696), and 90/50 Mobile Imaging Table (K884531). This substantial equivalence implies that the new device meets the same safety and effectiveness standards as these previously cleared devices.
• Intended Use: "intended to support and position patients for Angiographic examinations, Angiographic interventional techniques where an X-ray translucent tabletop is required, and for use during surgery where an X-ray translucent tabletop is required."

In essence, the "study" demonstrating the device meets "acceptance criteria" in this context is the 510(k) submission itself, which argues and validates substantial equivalence to existing, legally marketed predicate devices. The "acceptance criteria" are implicitly met if the device fundamentally performs its intended function (patient support and positioning) in a manner that is as safe and effective as the predicate devices, despite minor technological updates.

Ask a specific question about this device

The AX Workstation DR-Viewer Software Option offers the ability to visualize composite images of selected anatomy (i.e. spine, legs, colon). The images produced by the package, as well as the measurement tools of DR-Viewer, are intended to assist the physician in diagnosis and treatment of musculoskeletal disorders and conditions of the gastrointestinal tract.

The AX Workstation DR-Viewer Software Option uses a series of images of the anatomy (i.e. spine, legs, colon) generated with a radiographic, fluoroscopic, or angiographic x-ray system, and reconstructs the images into a single composite image format. After reconstruction of the image, the software provides the user with various measurement tools and post-processing functions.

This submission (K992925) for the Siemens AX Workstation DR-Viewer Software Option does not include a study proving the device meets acceptance criteria.

The provided documents are a 510(k) Premarket Notification submission from Siemens Medical Systems, Inc. to the FDA. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, not for proving a device meets specific performance acceptance criteria through a clinical or performance study.

Here's why the requested information cannot be provided from this document:

• Nature of the Submission: 510(k)s are primarily about demonstrating that a new device is as safe and effective as (substantially equivalent to) an already legally marketed device. They rarely include detailed performance studies with pre-defined acceptance criteria, sample sizes, and expert ground truth establishment for a new, unproven technology. Instead, they often rely on bench testing, comparison to predicate device specifications, and sometimes limited clinical data for specific functions.
• Device Type: The DR-Viewer Software Option is described as a software feature that reconstructs and visualizes composite images from angiographic data and provides measurement tools. Its primary function is image processing and display, which typically relies on demonstrating accuracy of reconstruction, accurate measurement tools, and user interface validity, rather than clinical diagnostic accuracy studies with human readers.
• Content of the Document: The document focuses on identifying the device, its classification, predicate devices, and indications for use. There is no mention of a formal performance study with acceptance criteria, sample sizes, expert involvement, or adjudication methods.

Therefore, I cannot populate the table or answer the specific questions regarding acceptance criteria and study details because the provided K992925 submission does not contain such information.

The document serves to notify the FDA of intent to market and to establish substantial equivalence with predicate devices, which are:

• Philips EasyVision Family Workstation Legs Option (K990455)
• Philips Spine Option for Easy Vision Workstation (K963980)

The "Indications For Use" (Attachment 9) states: "The AX Workstation DR-Viewer Software Option offers the user the ability to visualize composite images of selected anatomy (i.e. spine, legs, colon). The images produced by the package, as well as the measurement tools of DR-Viewer, are intended to assist the physician in diagnosis and treatment of musculoskeletal disorders and conditions of the gastrointestinal tract." This describes the intended application, but not performance metrics or acceptance criteria.

Ask a specific question about this device

The MAGNETOM SYMPHONY with the High End Gradients is a whole body scanner with higher gradient amplitudes. The MAGNETOM SYMPHONY with the High End Gradients is indicated for use as diagnostic imaging device to produce transversal, sagittal, coronal and oblique images of the internal structures of the head or body. The images produced by the MAGNETOM SYMPHONY with the High End Gradients reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin lattice relaxation time (T1), spin-spin relaxation time (T") and flow. When interpreted by a trained by a trained physician, these images provide information that can be useful in determining a diagnosis.

The MAGNETOM SYMPHONY with the High End Gradients is a whole body scanner with higher gradient amplitudes.

The provided text describes a 510(k) submission for "High End Gradients" for the MAGNETOM SYMPHONY system, which is a Magnetic Resonance Diagnostic Device. This submission primarily focuses on demonstrating substantial equivalence to a predicate device and ensuring safety and effectiveness, rather than reporting on a study designed to meet specific diagnostic accuracy acceptance criteria.

The acceptance criteria mentioned are related to safety and performance parameters of the MR system itself, not the diagnostic accuracy of a specific AI algorithm. The study described is a laboratory testing to support the claim of substantial equivalence and ensure the technological differences do not raise new safety or effectiveness concerns.

Therefore, many of the requested elements (like sample size for test set, number of experts for ground truth, adjudication method, MRMC study, standalone performance, training set details) are not applicable or
available from this document because it's not an AI/algorithm performance study.

Here's an attempt to answer the questions based on the provided text, indicating where information is not available or not applicable:

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

The document lists "safety parameters with action levels" and "performance levels" as evaluation criteria for the device (High End Gradients for MAGNETOM SYMPHONY). It explicitly states that "the new levels are not significantly changed and, in the case of safety, parameters remain below the level of concern as outlined by the FDA Guidance." However, the exact numerical acceptance criteria and reported performance values for each are not detailed in the provided text.

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

The document states "Laboratory testing were performed." It does not specify the sample size of any test sets (e.g., number of phantom scans, number of human subject scans) or the data provenance (e.g., country of origin, retrospective/prospective). This is a device modification submission, not a clinical study on diagnostic accuracy.

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. The ground truth for this type of submission would relate to engineering measurements and adherence to technical specifications, not diagnostic interpretations by human experts in a clinical context.

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

Not applicable. This is not a study requiring adjudication of diagnostic findings. Adjudication would likely be part of the internal engineering and testing processes by qualified personnel.

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

No. This document does not detail an MRMC study. It describes a change to the hardware of an MRI system (High End Gradients) and assesses its impact on the system's safety and performance, demonstrating substantial equivalence to a predicate device. It does not involve AI assistance or human reader performance.

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

Not applicable. This submission is for MRI hardware (gradients), not a standalone algorithm.

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

The "ground truth" for this submission would be defined by established engineering and physics principles, such as standardized phantom measurements, calibrated sensors for field strength, RF power, acoustic levels, and image quality metrics. It is not related to clinical diagnostic ground truths like pathology or expert consensus.

8. The sample size for the training set

Not applicable. This is not a submission for an AI/ML algorithm that requires a training set.

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

Not applicable. There is no training set for an AI/ML algorithm in this submission.

Ask a specific question about this device

The SOMATOM Plus 4 with Sliding Gantry Option is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from either the same axial plane taken at different angels or spiral planes* taken at different angles. (*spiral planes: the axial planes resulted from the continuous rotation of detectors and x-ray tube, and the simultaneous movement of the sliding gantry.)

The SOMATOM Plus 4 with Sliding Gantry Option is a whole body X-ray computed tomography scanner that features a continuously rotating tube-detector system and functions according to the fan beam principle. The Sliding Gantry Option integrates the function of precise scan control driven horizontal movement, which is usually a function of the dedicated CT-table, into the CT gantry itself. This is achieved by mounting the gantry on a dedicated rail system and by having a scan control system that moves the gantry relative to the table instead of moving the table relative to the gantry.

The provided text is a 510(k) summary for the SOMATOM Plus 4 with Sliding Gantry Option, a Computed Tomography (CT) system. It focuses on demonstrating substantial equivalence to previously cleared devices. It does not contain information about acceptance criteria or a study proving the device meets specific performance criteria through a rigorous evaluation of its imaging capabilities.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and reported device performance.
• Sample size for the test set or data provenance.
• Number and qualifications of experts for ground truth.
• Adjudication method for the test set.
• MRMC comparative effectiveness study or its effect size.
• Standalone algorithm performance.
• Type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

This document is primarily concerned with regulatory approval based on technological equivalence to existing, legally marketed CT systems, rather than a clinical performance study with specific quantitative acceptance criteria for image quality or diagnostic accuracy. It states that:

• The device is substantially equivalent to the Angio-CT MIYABI (K990491) and SOMATOM Project 059 (K941546).
• It operates with SOMARIS/4 software.
• It adheres to recognized and established industry practices to minimize electrical, mechanical, and radiation hazards.
• It is designed to meet ELECTRICAL AND MECHANICAL SAFETY STANDARD IEC 601-1 and UL 187 X-RAY EQUIPMENT STANDARD FOR SAFETY.
• It is certified to meet the Federal Diagnostic Equipment Performance Standard and applicable regulations of 21 CFR § 1020.30 and § 1020.33.

These are regulatory and safety compliance standards, not specific performance criteria related to diagnostic accuracy or image quality that would typically be evaluated in a study with a test set, ground truth, and expert readers.

Ask a specific question about this device

The BOLD MRI Package for MAGNETOM VISION and SYMPHONY MR systems, provides dedicated acquisition and reconstruction techniques which offer the possibility of visualization of small susceptibility changes, due to increased levels of oxygen, by parametric images. The parametric images provide parameter information, instead of anatomical information. These parametric images can be overlaid on the anatomical images to optimize the presentation of information to support the diagnostic process. These BOLD images when interpreted by a trained physician, yield information that may assist in diagnosis.

The BOLD MRI Package is an postprocessing option for the MAGNETOM VISION and MAGNETOM SYMPHONY Systems

The provided text, a 510(k) summary for the BOLD MRI Package, does not contain any information about acceptance criteria or a study proving that the device meets such criteria.

The document primarily focuses on:

• General Information: Establishment details, contact person, date of summary, device name, classification.
• Device Description: The BOLD MRI Package is a postprocessing option for MAGNETOM VISION and SYMPHONY Systems.
• Intended Use: Visualization of small susceptibility changes due to increased oxygen levels via parametric images, which can be overlaid on anatomical images to assist diagnostic processes when interpreted by a trained physician.
• Technological Characteristics: Substantially equivalent magnet, RF, and gradient systems to standard MAGNETOM VISION and SYMPHONY systems.
• Safety and Effectiveness Concerns: States that operation is "substantially equivalent" and MR safety and performance parameters are "unaffected by the modification." It lists several safety and performance aspects (Maximum Static Field, RF Power Deposition, Signal to Noise, Image Uniformity, etc.) that are supposedly unchanged.
• Substantial Equivalence Claim: Mentions that "Laboratory and clinical testing were performed to support this claim of substantial equivalence and to show that the technological differences do not raise any new questions pertaining to safety and effectiveness," but no details of these tests are provided.
• FDA Communication: A letter from the FDA confirming receipt of the 510(k) and determining substantial equivalence.
• Indications for Use: Reiterates the intended use.

Therefore, I cannot populate the requested table and sections as the input text does not include the necessary information. The document explicitly states that laboratory and clinical testing were performed to support the claim of substantial equivalence, but it does not describe the methods, results, or acceptance criteria of these studies.

Ask a specific question about this device

The Perfusion Package for MAGNETOM Vision and Symphony MR Systems is a software package which allows the display of temporal variations in dynamic MR Datasets, showing changes in contrast over time. Its purpose is to provide either time intensity curves or the creation of parametric images for parameters like time to peak that support the diagnostic process. These images when interpreted by a trained physician, yield information that may assist in diagnosis. One clinical application where this could be useful is the diagnosis of lesions by temporal analysis of tumor enhancement.

The Perfusion Package is a post processing option for the MAGNETOM VISION and SYMPHONY MR system.

The provided 510(k) summary for the Siemens Perfusion Package for Magnetom Vision and Symphony MR systems does not contain the detailed information requested regarding specific acceptance criteria, a quantitative study proving it meets those criteria, or a comparative effectiveness study.

Instead, the submission focuses on demonstrating substantial equivalence to existing devices and assuring that the new software package does not raise new questions of safety and effectiveness compared to the standard operation of the base MR system.

Here's an breakdown of what can be extracted or inferred, and what is explicitly missing based on the provided document:

Extracted/Inferred Information:

The core "acceptance criteria" here are implied by the FDA's substantial equivalence pathway, meaning the device must be as safe and effective as a legally marketed predicate device. The document explicitly states that the technological differences (the Perfusion Package) do not raise any new safety or effectiveness concerns.

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

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

• Not specified. The document mentions "Laboratory and clinical testing were performed," but provides no details on sample size, data origin (country), or whether it was retrospective or prospective.

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

• Not specified. "Trained physician" is mentioned in the intended use, but there's no information on expert involvement in testing or ground truth establishment.

4. Adjudication method for the test set:

• Not specified.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• Not specified. There is no mention of an MRMC study or any comparison of human readers with vs. without AI assistance. The focus is on the software being equivalent to the standard operation of the MR system, not on improving human reader performance.

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

• Partially addressed. The device is a "post processing option" and its "purpose is to provide either time intensity curves or the creation of parametric images...These images when interpreted by a trained physician, yield information that may assist in diagnosis." This implies it's an algorithm-only output that a human then interprets, rather than an AI assisting in real-time reading. However, the performance metrics are related to the MR system's underlying capabilities, not specific diagnostic accuracy of the generated curves/images.

7. The type of ground truth used:

• Not specified. The document implies the "ground truth" is primarily based on the functional equivalence of the MR system with and without the software package, as well as the qualitative ability to generate time-intensity curves and parametric images for interpretation by a physician. There's no mention of specific clinical ground truth (e.g., pathology, outcomes data) beyond supporting the diagnostic process.

8. The sample size for the training set:

• Not applicable / Not specified. This appears to be more of a post-processing software package applied to existing MR data rather than a machine learning model that requires a dedicated "training set" in the modern sense. If there was an ML component, its training data details are not provided.

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

• Not applicable / Not specified. (See point 8)

Conclusion:

This 510(k) summary, typical for its era (1999), focuses on demonstrating substantial equivalence by asserting that the Perfusion Package does not alter the fundamental safety and established performance of the Siemens MAGNETOM Vision and Symphony MR systems. It does not provide the kind of detailed quantitative performance study, sample sizes, expert qualifications, or ground truth methodologies that are common in submissions for AI/ML-based medical devices today. The "acceptance criteria" are predominantly those associated with maintaining the safety and performance standards of the base MR imaging system rather than a new diagnostic claim in itself.

Ask a specific question about this device

Perfusion CT is an application software package that permits cerebral perfusion imaging based on dynamic CT images continuously acquired after the injection of contrast. The package allows visualization of apparent blood flow in brain tissue and pictorially illustrates perfusion related parameters (i.e. relative cerebral blood flow, relative cerebral blood volume, time to peak). By generating images of cerebral blood flow (CBF), cerebral blood volume (CBV), and local bolus timing (i.e. time to peak) from one set of dynamic CT images, Perfusion CT aids the physician in the assessment of the type and extent of cerebral perfusion disturbances. The software package also allows the calculation of mirrored regions of interest and the visual inspection of time density curves.

Perfusion CT is a post-processing software package which runs on an Intel-based PC platform designed to post-process images acquired with SOMATOM CT scanners which meet certain minimal requirements (i.e. Siemens SOMATOM Plus 4, SOMATOM AR.STAR, SOMATOM Classic). It is a package containing evaluation software that supports the evaluation of Dynamic CT data gathered after the injection of a compact bolus of contrast media, where the contrast media acts as a pure intravascular tracer.

Perfusion CT calculates the parameters related to brain perfusion and cerebral blood flow (CBF) using a simple linear relationship between the detected change of signal and the actual concentration of contrast media.

The Perfusion CT Software Package for SOMATOM CT Systems is a post-processing software package that aids physicians in assessing cerebral perfusion disturbances.

Here's an analysis of its acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance:

The provided document does not explicitly state quantitative acceptance criteria (e.g., specific sensitivity, specificity, or error rates) or reported device performance metrics (e.g., 90% accuracy). Instead, it focuses on qualitative utility and equivalence to predicate devices.

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

• Sample Size for Test Set: Not specified. The document states "Clinical studies were carried out in Europe to collect cerebral images from individuals with suspected local ischemia." It does not provide the number of patients or cases.
• Data Provenance: Europe. This was a clinical study. It does not specify whether the clinical studies were retrospective or prospective.

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

Not specified. The document states the software is "useful in aiding physicians in diagnosing ischemia," suggesting physician involvement in assessing the output, but it does not detail how ground truth was established or the number/qualifications of experts involved in the clinical studies.

4. Adjudication Method for the Test Set:

Not specified.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size:

Not specified. The document does not mention an MRMC study or any comparison of human readers with vs. without AI assistance, nor does it provide an effect size.

6. If a Standalone (Algorithm Only) Performance Study Was Done:

The description of the "Clinical Studies and Conclusion" focuses on the software's utility in aiding physicians. There is no explicit mention of a standalone algorithm-only performance study, nor are there quantitative metrics that would typically result from such a study (e.g., sensitivity, specificity, AUC). The device is described as a "post-processing software package" that "aids the physician," implying human-in-the-loop performance.

7. The Type of Ground Truth Used:

Not explicitly stated. Given that the software "aids the physician in the assessment of the type and extent of cerebral perfusion disturbances" and "diagnosing ischemia," it is implied that the ground truth for "diagnosing ischemia" would likely be through clinical diagnosis, potentially supported by other imaging modalities or follow-up clinical outcomes, rather than just expert consensus on the software's output alone. However, the exact reference standard is not detailed.

8. The Sample Size for the Training Set:

Not specified. The document focuses on performance evaluation rather than development.

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

Not specified. The document does not provide details about development or training data.

Ask a specific question about this device

Ask a specific question about this device