Search Results

The MAGNETOM system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross-sectional images, spectroscopic images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

The MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

The subject devices, MAGNETOM Aera (including MAGNETOM Aera Mobile), MAGNETOM Skyra, MAGNETOM Prisma, MAGNETOM Prisma™, MAGNETOM Vida, MAGNETOM Lumina with software syngo MR XA60A, consist of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Vida with syngo MR XA50A (K213693).

This FDA 510(k) summary describes several updates to existing Siemens Medical Solutions MRI systems (MAGNETOM Vida, Lumina, Aera, Skyra, Prisma, and Prisma fit), primarily focusing on software updates (syngo MR XA60A) and some modified/new hardware components. The document highlights the evaluation of new AI features, specifically "Deep Resolve Boost" and "Deep Resolve Sharp."

Here's an analysis of the acceptance criteria and the study details for the AI features:

1. Table of Acceptance Criteria and Reported Device Performance

The document provides a general overview of the evaluation metrics used but does not explicitly state acceptance criteria in a quantitative format (e.g., "Deep Resolve Boost must achieve a PSNR of X" or "Deep Resolve Sharp must achieve Y SSIM"). Instead, it describes the types of metrics used and qualitative assessments.

• Impact characterized by PSNR and SSIM. | The impact of the network has been characterized by several quality metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Most importantly, the performance was evaluated by visual comparisons to evaluate e.g., aliasing artifacts, image sharpness and denoising levels. |
  | Deep Resolve Sharp | - Preservation of image quality (image sharpness) compared to original.
• Impact characterized by PSNR, SSIM, and perceptual loss.
• Verification and validation by visual rating and evaluation of image sharpness by intensity profile comparisons. | The impact of the network has been characterized by several quality metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and perceptual loss. In addition, the feature has been verified and validated by inhouse tests. These tests include visual rating and an evaluation of image sharpness by intensity profile comparisons of reconstructions with and without Deep Resolve Sharp. |

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

• Deep Resolve Boost: The document doesn't explicitly state a separate "test set" size. It mentions the "Training and Validation data" which includes:
  • TSE: more than 25,000 slices
  • HASTE: pre-trained on the TSE dataset and refined with more than 10,000 HASTE slices
  • EPI Diffusion: more than 1,000,000 slices
  • Data Provenance: The data covered a broad range of body parts, contrasts, fat suppression techniques, orientations, and field strength. No specific country of origin is mentioned, but the manufacturer (Siemens Healthcare GmbH) is based in Germany, and Siemens Medical Solutions USA, Inc. is the submitter. The data was "retrospectively created from the ground truth by data manipulation and augmentation."
• Deep Resolve Sharp: The document doesn't explicitly state a separate "test set" size. It mentions "Training and Validation data" from "on more than 10,000 high resolution 2D images."
  • Data Provenance: Similar to Deep Resolve Boost, the data covered a broad range of body parts, contrasts, fat suppression techniques, orientations, and field strength. Data was "retrospectively created from the ground truth by data manipulation." No specific country of origin is mentioned.

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

Not specified. The document states that the acquired datasets "represent the ground truth." There is no mention of expert involvement in establishing ground truth for the test sets. The focus is on technical metrics (PSNR, SSIM) and "visual comparisons" or "visual rating" which implies expert review, but the number and qualifications are not provided.

4. Adjudication Method for the Test Set

Not explicitly stated. The document mentions "visual comparisons" for Deep Resolve Boost and "visual rating" for Deep Resolve Sharp. This suggests subjective human review, but no specific adjudication method (like 2+1 or 3+1 consensus) is detailed.

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 MRMC comparative effectiveness study is described for the AI features. The studies mentioned (sections 8 and 9) focus on evaluating the technical performance and image quality of the AI algorithms themselves, not on their impact on human reader performance.

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

Yes, standalone performance evaluation of the algorithms was conducted. The "Test Statistics and Test Results Summary" for both Deep Resolve Boost and Deep Resolve Sharp detail the evaluation of the network's impact using quantitative metrics (PSNR, SSIM, perceptual loss) and qualitative assessments ("visual comparisons," "visual rating," "intensity profile comparisons"). This represents the algorithm's performance independent of a human reader's diagnostic accuracy.

7. The Type of Ground Truth Used

The ground truth used for both Deep Resolve Boost and Deep Resolve Sharp was the acquired datasets themselves, representing the original high-quality or reference images/slices.

• For Deep Resolve Boost, input data was "retrospectively created from the ground truth by data manipulation and augmentation," including undersampling k-space lines, lowering SNR, and mirroring k-space data. The original acquired data serves as the target "ground truth" for the AI to reconstruct/denoise.
• For Deep Resolve Sharp, input data was "retrospectively created from the ground truth by data manipulation," specifically by cropping k-space data to create low-resolution input, with the original high-resolution data serving as the "output / ground truth" for training and validation.

8. The Sample Size for the Training Set

• Deep Resolve Boost:
  • TSE: more than 25,000 slices
  • HASTE: pre-trained on the TSE dataset and refined with more than 10,000 HASTE slices
  • EPI Diffusion: more than 1,000,000 slices
• Deep Resolve Sharp: more than 10,000 high resolution 2D images.

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

The ground truth for the training set was established as the acquired, unaltered (or minimally altered, e.g., removal of k-space lines to simulate lower quality input from high quality ground truth) raw imaging data.

• For Deep Resolve Boost: "The acquired datasets (as described above) represent the ground truth for the training and validation. Input data was retrospectively created from the ground truth by data manipulation and augmentation." This implies that the original, high-quality scans were considered the ground truth, and the AI was trained to restore manipulated, lower-quality versions to this original quality.
• For Deep Resolve Sharp: "The acquired datasets represent the ground truth for the training and validation. Input data was retrospectively created from the ground truth by data manipulation. k-space data has been cropped such that only the center part of the data was used as input. With this method corresponding low-resolution data as input and high-resolution data as output / ground truth were created for training and validation." Similar to Boost, the original, higher-resolution scans served as the ground truth.

Ask a specific question about this device

The Prismaflex ST set is a single use device that provides blood purification through a semipermeable membrane.

The Prismaflex ST set is for use only in conjunction with the PrismaFlex control unit or with the PrisMax control unit (in countries where PrisMax is cleared or registered).

All treatments administered via the PrismaFlex ST sets must be prescribed by a physician. The size, weight, state of uremia, cardiac status, and general physical condition of the patient must be carefully evaluated by the prescribing physician before each treatment.

If patients suffer from acute kidney injury and / or volume overload, the Prismatlex ST set is indicated for continuous renal replacement therapies (CRRT), in modalities such as:

• · Slow Continuous UltraFiltration (SCUF)
• · Continuous Veno-Venous Hemofiltration (CVVH)
• · Continuous Veno-Venous HemoDialysis (CVVHD)
• Continuous Veno-Venous HemoDiaFiltration (CVVHDF)

to perform fluid management and reduction of uremic toxins.

The Prismaflex ST100 and ST150 set is indicated for use in patients with a body weight equal or greater than 30 kg (661b) and Prismaflex ST60 set is indicated to patients with a body weight greater than 11kg (24lb).

The Prismaflex ST60/ST100/ST150 set is a disposable, extracorporeal circuit for use with the PrismaFlex system, or with the PrisMax system. The Prismaflex ST60/ST100/ST150 set consists of an AN69 ST hollow fiber haemofilter/dialyser and tubing system.

These Prismaflex disposable sets allow the following fluid management and renal replacement therapies to be performed :

• SCUF: Slow Continuous Ultrafiltration
• CVVH: Continuous Veno-Venous Hemofiltration
• CVVHD: Continuous Veno-Venous Hemodialysis
• CVVHDF: Continuous Veno-Venous Hemodiafiltration

The fluid pathways of the Prismaflex set are guaranteed sterile and pyrogen-free. The Prismaflex set is sterilized by ethylene oxide (EO).

The shelf life of the Prismaflex ST60/ST100/ST150 sets is 24 months from the date of sterilization. The device is intended for single use.

The provided text describes a 510(k) premarket notification for the "Prismaflex ST set" (ST60/ST100/ST150 sets), a high permeability hemodialysis system. The submission aims to demonstrate substantial equivalence to legally marketed predicate devices. The document focuses on non-clinical testing to support this claim.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding device performance values like a clinical trial report would for specific endpoints (e.g., sensitivity, specificity for diagnostic devices, or specific measurable outcomes for therapeutic devices).

Instead, it states that the device was evaluated against established international standards and internal performance requirements. The "reported device performance" is described qualitatively as meeting these standards and requirements.

Here's a synthesized representation based on the information provided, inferring "acceptance criteria" from the standards and tests mentioned:

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

The provided text describes non-clinical bench and pre-clinical testing. These are laboratory-based tests of the device's physical and chemical properties, as well as its interaction with biological models (e.g., blood, cell cultures).

• Sample Size for Test Set: The document does not specify the exact number of units/sets tested for each performance characteristic. In bench testing for medical devices, this often involves a pre-defined number of samples per batch or according to a statistical sampling plan to ensure reliability and representativeness for the specific test (e.g., n=3, n=5, n=10 per test condition). However, these specific numbers are not disclosed in this summary.
• Data Provenance: The data provenance is from non-clinical (bench and pre-clinical) laboratory testing. There is no mention of human subject data, retrospective, or prospective studies involving patients.

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

This question is not applicable to the type of study described. "Ground truth" established by experts (like radiologists for image analysis) is relevant for clinical studies, especially those involving human interpretation or diagnostic accuracy. The studies detailed here are non-clinical, focusing on the device's physical and chemical performance, where "ground truth" is typically defined by objective measurements against established engineering specifications and international standards, not expert consensus.

4. Adjudication Method for the Test Set

This question is not applicable. Adjudication methods (e.g., 2+1, 3+1) refer to procedures for resolving disagreements among multiple human readers/experts in clinical studies, particularly in diagnostic accuracy assessments. As this is a non-clinical device performance study, such a method would not be used.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states that the safety and performance were evaluated through non-clinical testing. There is no mention of human readers, AI assistance, or comparative effectiveness studies involving human-in-the-loop performance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

This question is not applicable. The device described, the "Prismaflex ST set," is a medical device for blood purification (hemodialysis/hemofiltration), not an AI algorithm or a diagnostic tool that would typically have a "standalone" algorithmic performance. The "performance" here refers to its physical and functional operation.

7. Type of Ground Truth Used

The "ground truth" for these non-clinical tests is established by:

• Objective Measurements: Directly measuring physical and chemical properties (e.g., ultrafiltration rate, clearances, pressure drop) using calibrated equipment.
• International Standards: Compliance with recognized international standards (ISO 8637-1, ISO 8638, ISO 10993 series) which define acceptable ranges and methodologies.
• Device Specifications: Meeting internal design specifications for the device.

There is no use of expert consensus, pathology, or outcomes data as "ground truth" in these non-clinical tests.

8. Sample Size for the Training Set

This question is not applicable. The Prismaflex ST set is a hardware medical device; its development and validation do not involve "training sets" in the context of machine learning or AI algorithms. The "training" that occurs is in the manufacturing and quality control processes to ensure consistency and adherence to specifications.

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

This question is not applicable, as there is no "training set" in the context of an AI/machine learning algorithm for this device.

Ask a specific question about this device

Promogran Prisma™, when used without ActiV.A.C.™ Negative Pressure Wound Therapy, is intended for the management of exuding wounds. Under the supervision of a health care professional, Promogran Prisma™ may be used for the management of:

• Diabetic ulcers
• Venous ulcers
• Pressure ulcers
• Ulcers caused by mixed vascular etiologies
• Full-thickness & partial thickness wounds
• Donor sites and other bleeding surface wounds
• Abrasions
• Traumatic wounds healing by secondary intention
• Dehisced surgical wounds.

Promogran Prisma™ when used with ActiV.A.C.TM Negative Pressure Wound Therapy is intended for the management of exuding wounds. Under the supervision of a health care professional, Promogran Prisma™ with ActiV.A.C.™ Negative Pressure Wound Therapy may be used only for the management of:

• Diabetic ulcers
• Venous ulcers
• Pressure ulcers
• Partial-thickness burns
• Traumatic wounds healing by secondary intention
• Dehisced surgical wounds.

Compression therapy may only be used with Promogran Prisma™ under professional healthcare supervision. Compression therapy may not be used when Promogran Prisma™ is used with ActiV.A.C.TM Negative Pressure Wound Therapy.

3MTM Promogran Prisma™ is comprised of a sterile, freeze-dried composite of 44% oxidized regenerated cellulose (ORC), 55% collagen and 1 % silver ORC. Silver ORC contains 25% w/w ionically bound silver.

It is a primary dressing that can be cut with scissors to fit the wound and used in combination with either a semiocclusive or non-occlusive secondary dressing. The dressing is hexagonal in shape, provided in two sizes (28 cm² and 123 cm²) that are packaged in a hexagonal thermoformed tray and sterilized by gamma irradiation.

As described in the product labeling, when used with the ActiV.A.C.TM Negative Pressure Wound Therapy System, seven slits are cut into the 3M™ Promogran Prisma™ by the health care provider before applying the dressing and the components of the ActiV.A.C.™ Negative Pressure Wound Therapy System.

After reviewing the provided document, it is not possible to describe the acceptance criteria and the study that proves the device meets the acceptance criteria as requested.

The document is an FDA 510(k) clearance letter and its associated summary for the PROMOGRAN PRISMA Matrix wound dressing. This document primarily focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than providing detailed acceptance criteria and performance data for an AI/ML-driven medical device.

Here's why the requested information cannot be extracted:

• Device Type: PROMOGRAN PRISMA Matrix is a wound dressing, a physical medical device, not an AI/ML-driven diagnostic or therapeutic system.
• Study Focus: The "Performance Data" section (page 11) explicitly states:
  • "Summary of non-clinical tests conducted for determination of substantial equivalence": This refers to biocompatibility and bench studies for the physical dressing and its compatibility with Negative Pressure Wound Therapy, not an algorithm's performance.
  • "Summary of clinical tests conducted for determination of substantial equivalence": This states "No clinical tests were necessary to demonstrate acceptable use of the Promogran Prisma™ with ActiV.A.C.™ Negative Pressure Wound Therapy." It mentions a "human factors engineering assessment" with 30 subject nurses and doctors to ensure changes to labeling for combined use are safe and effective. This is not a study proving an AI/ML device's diagnostic performance.
• Absence of AI/ML Specifics: There is no mention of algorithms, machine learning models, image analysis, diagnostic performance metrics (e.g., sensitivity, specificity, AUC), ground truth establishment by experts, test sets, training sets, or MRMC studies, all of which are pertinent to AI/ML device evaluations.

Therefore, the requested tables and details pertaining to AI/ML device acceptance criteria and performance studies are not present in this document. The document describes a traditional medical device's clearance process based on substantial equivalence.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal, and oblique cross sectional images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/ or spectra and the physical parameters derived from the images and/or spectra, when interpreted by a trained physician, vield information that may assist in diagnosis.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-safe biopsy needles.

MAGNETOM Aera, MAGNETOM Skyra and MAGNETOM Prisma/ Prisma/ with software syngo MR XA30A, include new and modified hardware and software compared to the predicate device, MAGNETOM Vida with software syngo MR XA20A. A high-level summary of the new and modified hardware and software is provided below:

Hardware

• New Computer

Software
New Features and Applications

• SVS EDIT is a special variant of the SVS SE pulse sequence type, which acquires two different spectra (one with editing pulses on resonance, one with editing pulses off resonance) within a single sequence.
• BEAT_FQ_nav is a pulse sequence that allows the user to make use of navigator echo based respiratory gating for flow imaging to acquire 4D flow data. Both navigator echo based respiratory gating and flow imaging are cleared features available on the predicate device. However, the combination of the two is new.
• Injector coupling is a software application that allows the connection of certain contrast agent injectors to the MR system for simplified, synchronized contrast iniection and examination start.
• The Prostate Dot Engine provides an assisted and guided workflow for prostate imaging. This automated workflow leads to higher reproducibility of slice angulation and coverage based on the segmentation algorithm described and cleared with syngo.via VB40; this may support exams not having to be repeated.

Modified Features and Applications

• An optimized high bandwidth inversion recovery pulse is combined with gradient echo readout to improve diagnostic image quality when imaging myocardial tissue.
• The AbsoluteShim mode is a shimming procedure based on a 3-echo gradient echo protocol.

Other Modifications and / or Minor Changes

• Elastography-AddIn synchronizes settings between the Elastography sequence and the active driver.
• HASTE MoCo is an image-based motion correction function in the averagedimension for the HASTE pulse sequence type.
• Coil independent pulse sequences remove the coil information from the pulse sequences and generate this information during run-time from automatic coil detection and localization.

The provided document is a 510(k) summary for the Siemens MAGNETOM Aera, MAGNETOM Skyra, and MAGNETOM Prisma/Prismafit MR systems with syngo MR XA30A software. It details the device's substantial equivalence to a predicate device but does not describe specific acceptance criteria for a new feature's performance or a study demonstrating the device meets such criteria.

The document primarily focuses on demonstrating substantial equivalence by outlining:

• Device Description: New and modified hardware/software features (e.g., SVS EDIT, BEAT_FQ_nav, Injector coupling, Prostate Dot Engine, optimized high bandwidth inversion recovery pulse, AbsoluteShim mode, Elastography-AddIn, HASTE MoCo, Coil independent pulse sequences).
• Nonclinical Tests: These include "Sample clinical images," "Image quality assessments using sample clinical images," "Performance bench test," and "Software verification and validation." The results "demonstrate that the devices perform as intended and are therefore, substantially equivalent to the predicate device to which it has been compared."
• Clinical Tests/Publications: No clinical tests were conducted to support substantial equivalence for the subject devices. However, "sample clinical images were provided," and "clinical publications were referenced to provide information on the use of the following features and functions" (listing publications for SVS_EDIT and Prostate Dot Engine).

Therefore, I cannot extract the specific information requested because it is not present in the provided text. The document does not contain:

• A table of acceptance criteria and reported device performance.
• Details on sample sizes, data provenance, number of experts for ground truth, or adjudication methods for any specific test set.
• Information regarding MRMC comparative effectiveness studies or standalone algorithm performance.
• Details on the type of ground truth used for specific features.
• Training set sample size or how ground truth was established for a training set.

The document's purpose is to show that the new/modified features are substantially equivalent to existing ones and perform as intended through verification and validation activities, rather than presenting a performance study against predefined acceptance criteria for novel functionalities.

Ask a specific question about this device

The PrisMax control unit is intended for:
· Continuous Renal Replacement Therapy (CRRT) for patients weighing 20 kilograms or more with acute renal failure and/or fluid overload.
• Therapeutic Plasma Exchange (TPE) therapy for patients weighing 20 kilograms or more with diseases where removal of plasma components is indicated.
All treatments administered via the PrisMax control unit must be prescribed by a physician.

The PrisMax System is intended for Continuous Renal Replacement Therapy (CRRT) for patients with acute renal failure and/or fluid overload. The goals of acute renal failure treatments are removal of waste products, restoration of acid-base balance; correction of electrolyte imbalances (e.g., hyperkalemia), patient fluid balance, nutritional support, and other conditions in which fluid removal is needed. PrisMax System offers four Continuous Renal Replacement Therapy (CRRT) options: Slow Continuous Ultrafiltration (SCUF), Continuous Veno-Venous Hemofiltration (CVVH), Continuous VenoVenous Hemodialysis (CVVHD), and Continuous Venovenous Hemodialfiltration (CVVHDF). The proposed device PrisMax System Version 3 uses the current marketed device PrisMax System Version 2 as the predicate.

This document is a 510(k) Pre-market Notification for a medical device, the PrisMax System Version 3. The document aims to demonstrate that the new device is substantially equivalent to a legally marketed predicate device (PrisMax System Version 2), and therefore does not require a new premarket approval application (PMA).

Here's an analysis of the provided information regarding acceptance criteria and the supporting study, organized by your requested points:

Acceptance Criteria and Device Performance

The acceptance criteria are implicitly defined by the technical specifications outlined in the "Substantial Equivalence Summary" tables (Table 3), comparing the PrisMax System Version 3 to the predicate PrisMax System Version 2. The reported device performance is stated as meeting these specifications, thereby achieving "substantial equivalence" to the predicate.

Table 1: Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

The PrisMax control unit is intended for:
· Continuous Renal Replacement Therapy (CRRT) for patients weighing 20 kilograms or more with acute renal failure and/or fluid overload.
• Therapeutic Plasma Exchange (TPE) therapy for patients weighing 20 kilograms or more with diseases where removal of plasma components is indicated.
All treatments administered via the PrisMax control unit must be prescribed by a physician.

The PrisMax System is intended for Continuous Renal Replacement Therapy (CRRT) for patients with acute renal failure and/or fluid overload. The goals of acute renal failure treatments are removal of waste products, restoration of acid-base balance; correction of electrolyte imbalances (e.g., hyperkalemia), patient fluid balance, nutritional support, and other conditions in which fluid removal is needed. PrisMax System offers four Continuous Renal Replacement Therapy (CRRT) options: Slow Continuous Ultrafiltration (SCUF), Continuous Veno-Venous Hemofiltration (CVVH), Continuous VenoVenous Hemodialysis (CVVHD), and Continuous Venovenous Hemodialfiltration (CVVHDF). The proposed device PrisMax, which is the subject of this Traditional premarket notification (510(k)), consists of the PrisMax Control Unit System, Blood Tubing Sets and Accessories. Specific to this submission, is the accessory for blood warming and a blood tubing set for Therapeutic Plasma Exchange (TPE2000).

Here's a breakdown of the acceptance criteria and the study information for the PrisMax System Version 2, based on the provided document.

It's important to note that this document is a 510(k) summary for a medical device and not a study report for an AI/algorithm-based device. Therefore, many of the requested categories (like sample sizes for test/training sets, number of experts, adjudication methods, MRMC studies, standalone AI performance, and ground truth establishment for AI) are not applicable to this submission, as it concerns a physical medical device (CRRT/TPE system) and its software/accessories, not an AI model.

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the safety and performance requirements for a high permeability hemodialysis system, as demonstrated by equivalence to predicate devices and compliance with recognized standards. The "performance" here refers to the functional performance of the device's physical and software components.

Study Information (Relevant to this device submission)

1. Sample size used for the test set and the data provenance: Not applicable. This is a submission for a physical medical device and its accessories/software, not an AI/algorithm. Performance was evaluated through non-clinical functional testing, verification, and validation of the device components and system.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for a physical device's functional performance is typically based on engineering specifications, physical measurements using calibrated equipment, and compliance with recognized standards.

3. Adjudication method: Not applicable for an AI context. Device performance was assessed against predefined engineering specifications and regulatory standards in non-clinical testing.

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: Not applicable. This is a medical device, not an AI diagnostic/classification system requiring human reader studies.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This device is not an AI algorithm. Its software runs on the device to control its functions.

6. The type of ground truth used:

   • Engineering Specifications: The device's operating ranges, accuracies (e.g., flow rates, pressure sensors, fluid removal), and control parameters were tested against predetermined engineering specifications.
   • Regulatory Standards: Compliance with recognized international standards (e.g., IEC60601-2-16 for Hemodialysis Equipment, IEC60601-1 for Electrical Safety, IEC60601-1-8 for Alarms, IEC60601-1-2 for EMC, ISO10993-1 for Biocompatibility).
   • Successful Functional Performance: Verification and validation testing confirmed that the device and its accessories (including software) performed as intended and met user needs.

7. The sample size for the training set: Not applicable. No AI model training set is mentioned or relevant for this device submission. The "software" referred to is control software, not a machine learning model.

8. How the ground truth for the training set was established: Not applicable. There is no AI training set. Software verification and validation (V&V) involved testing against functional requirements derived from design specifications, risk analysis, and regulatory requirements.

Ask a specific question about this device

The Prismaflex control unit is intended for:
· Continuous Renal Replacement Therapy (CRT) for patients weighing 20 kilograms or more with acute renal failure and/or fluid overload.
• Therapeutic Plasma Exchange (TPE) therapy for patients weighing 20 kilograms or more with diseases where removal of plasma components is indicated.
All treatments administered via the Prismaflex control unit must be prescribed by a physician.

The Prismaflex control unit is a software controlled device that performs the following functions:
Loads and primes the Prismaflex disposable set automatically.
• Pumps blood through the blood flow path of the Prismaflex disposable set.
· Delivers anticoagulant solution into the blood flow path.
• Pumps sterile infusion solutions into the blood flow path of the Prismaflex disposable set according to therapy in use.
· Pumps sterile dialysate into the fluid compartment of the filter in CRRT therapies.
· Controls the patient fluid removal or plasma loss according to the therapy in use.
• Monitors the system and alerts the operator to abnormal situations through alarms.
· Provides treatment data to an external Patient Data Management Systems (PDMS)

The provided document, a 510(k) premarket notification letter from the FDA to Baxter Healthcare Corporation for the Prismaflex System 8.10, is a regulatory submission for a medical device. It does not contain information about an AI/ML-based medical device software or a study that proves a device meets acceptance criteria in the context of an AI/ML system's performance metrics (like sensitivity, specificity, or AUC).

The document details the device's substantial equivalence to a predicate device (Prismaflex System 7.10) based on its functional parameters, physical characteristics, and adherence to performance standards for a hemodialysis system. The "acceptance criteria" here refer to the predefined performance ranges and characteristics of the device itself (e.g., dialysate flow rate accuracy, blood flow rate accuracy, pressure sensor accuracy), and the "study" is the non-clinical testing (software and system verification and validation) done to prove that the updated Prismaflex System 8.10 meets these established parameters and functions equivalently to its predecessor.

Therefore, I cannot extract the requested information, which pertains to AI/ML device performance and testing, from this document. The document primarily focuses on demonstrating substantial equivalence for a non-AI/ML medical device based on established performance specifications and regulatory compliance.

Ask a specific question about this device

The MAGNETOM systems are indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities.

Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These mages and the physical parameters derived from the images and/or spectra, when interpreted by a trained physician, yield information that may assist in diagnosis.

The MAGNETOM systems may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

MAGNETOM Aera, MAGNETOM Skyra and MAGNETOM Prisma/Prisma" with syngo MR E11C software were cleared with K153343 and MAGNETOM Avanto" and MAGNETOM Skyrafff systems with syngo MR E11C software were cleared with K162102.

To address the new feature GOKnee3D and the modifications summarized in Section 3 and furthermore described in this Premarket Notification Siemens intends to make the software application package syngo MR E11C - AP04 available to the systems mentioned above.

The additional options for the synqo MR E11C software is being made available for the following MAGNETOM MR Systems:

• . MAGNETOM Aera,
• MAGNETOM Skyra / Skyraf" ●
• MAGNETOM Prisma / Prisma™ ●
• MAGNETOM Avantofit .

Those options include a new feature with a modified sequence and modified features for the above mentioned MR systems. A high level summary of sequences, features and improvements made available for the above systems is included below.

The provided text does not contain information about specific acceptance criteria, a study proving a device meets these criteria, or detailed performance metrics. The document is a 510(k) premarket notification summary for Siemens MAGNETOM MRI systems, explaining their substantial equivalence to previously cleared devices.

It discusses:

• Device Name: MAGNETOM Aera, MAGNETOM Skyra/Skyrafit, MAGNETOM Prisma/Prismafit, MAGNETOM Avantofit with syngo MR E11C - AP04 software.
• Intended Use: Magnetic resonance diagnostic device (MRDD) for imaging internal structures and functions of the head, body, or extremities, assisting in diagnosis.
• New Feature: GOKnee3D (fast, push-button knee examination with AutoAlign knee localizer and two CAIPIRINHA SPACE sequences).
• Modified Features: SPACE with CAIPIRINHA acquisition technique, Dual Monitor support, Compressed Sensing Cardiac Cine (BEAT_CS Sequence).
• Technological Characteristics: Similar to predicate devices, conforming to IEC 62304:2006 and other standards.
• Nonclinical Tests: Performance testing for modified sequence (CAIPIRINHA SPACE), image quality assessments of new sequences/algorithms, software verification and validation.
• Clinical Tests: "No clinical tests were conducted to support the subject devices and the substantial equivalence argument; however, clinical images and LV evaluation were provided to support the argumentation and documentation which demonstrate the clinical utility and technical capabilities of the method."
• Safety and Effectiveness: Risk management via ISO 14971:2007, adherence to IEC 60601-1 series, and compliance with FDA recognized standards.
• Substantial Equivalence: Concluded based on identical intended use and similar technological characteristics to predicate devices. The hardware is unchanged.

Therefore, I cannot populate the requested table or answer the specific questions about acceptance criteria, study details, sample sizes, expert involvement, and ground truth establishment, as this information is not present in the provided text. The document explicitly states that no clinical tests were conducted, and the assessment relies on nonclinical tests and substantial equivalence to predicate devices.

Ask a specific question about this device

The PrisMax control unit is intended for:
• Continuous Renal Replacement Therapy (CRRT) for patients weighing 20 kilograms or more with acute renal failure and/or fluid overload.

All treatments administered via the PrisMax control unit must be prescribed by a physician.

The PrisMax System is intended for Continuous Renal Replacement Therapy (CRRT) for patients with acute renal failure and/or fluid overload. The PrisMax System offers four Continuous Renal Replacement Therapy (CRRT) options: Slow Continuous Ultrafiltration (SCUF), Continuous Veno-Venous Hemofiltration (CVVH), Continuous VenoVenous Hemodialysis (CVVHD), and Continuous Venovenous Hemodialfiltration (CVVHDF). The proposed device PrisMax consists of PrisMax Control Unit and accessories for removing effluent.

The provided text describes a 510(k) premarket notification for the PrisMax device, which is a high-permeability hemodialysis system. The core of this submission is to demonstrate the substantial equivalence of the PrisMax to a predicate device, the Prismaflex.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based solely on the provided text. It's important to note that a 510(k) summary often summarizes extensive testing, so not all details of the actual studies might be present in this brief document.

First and foremost, this document describes a device comparison for substantial equivalence to a predicate, not a study evaluating clinical performance against a specific disease outcome or a MRMC study. Therefore, some of the requested information (like effect size of human readers improving with AI, or number of experts for ground truth) is not applicable to this type of regulatory submission. The acceptance criteria here are about equivalence to the predicate device's established performance parameters and safety.

1. Table of Acceptance Criteria and the Reported Device Performance

The acceptance criteria are generally that the PrisMax device performs at least as well as or equivalently to the predicate Prismaflex device for various technical specifications. The reported device performance is the PrisMax's specification for that feature. The table below is extracted directly from the "Table 3. Substantial Equivalence Table Device Comparison" in the provided document. The "Acceptance Criteria" column reflects the predicate device's performance, as the goal is to demonstrate equivalence or improvement without raising new safety/effectiveness concerns.

Study Proving Device Meets Acceptance Criteria

The document states: "Performance testing was conducted on the PrisMax System to evaluate the functional performance of the system. The performance testing confirms PrisMax remains as safe and effective as Prismaflex and is substantially equivalent."

The nature of the "study" demonstrating this is predominantly nonclinical performance testing, verification, and validation against engineering and regulatory standards, and comparison to the predicate device's specifications.

Specifically, the document explicitly mentions:

• Design validation: The PrisMax design validation meets user needs and intended use and is substantially equivalent to the predicate.
• Compliance with IEC 60601-2-16 Hemodialysis Equipment: Testing confirmed by CSA, a recognized test laboratory, for essential performance.
• Electrical safety testing: According to IEC 60601-1 Edition 3.1. This includes reports for software, alarms, usability, safety, and performance.
• Electromagnetic compatibility (EMC) testing.
• Risk Assessment and risk control measures: Hazard analysis (therapy level, product level, process level) confirming the device does not perform in an unexpected or unsafe manner.
• Labeling, Software including cybersecurity, Human Factors: These have been successfully implemented.
• Verification and validation tests: These were performed subsequent to risk analysis and include Human Factors and Software Validation.

The key changes and their justification for not raising new safety/effectiveness concerns are footnoted in Table 3:

• Syringe Sizes (30ml removed): Due to infrequent use, device behavior unchanged.
• Dialysate Flow Rate / Replacement Solution Flow Rate Increment (50ml/hr to 10ml/hr): Allows for more precise settings, verified and validated to comply to updated specifications without new risks.
• Pre-Blood Pump Flow Rate (SCUF range clarification): Corrected the predicate's stated range to its actual operational range, showing PrisMax is equivalent. Verified and validated.
• Trans Membrane Pressure Alarms (Fixed default of +300 mmHg, removed user settable): Removes infrequent use case, reduces use-error risk, increases usability, lowers default to reduce risk. Verified and validated.
• Patient Fluid Removal Performance Increment (10ml/hr to 5ml/hr): Increases setting range, allows more precise setting. Verified and validated.
• The software update (version 1.0.6.0) was verified and validated subsequent to risk analysis and includes Human Factors and Software Validation.

Details based on the provided text:

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

  • Sample Size: Not explicitly stated in terms of patient count or device unit count for the validation tests. These are typically engineering performance tests, not clinical trials with "patients." The performance tests would use a relevant number of devices or test conditions to ensure specifications are met.
  • Data Provenance: The testing appears to be internal "performance testing" and "verification and validation" conducted by Baxter Healthcare Corporation and by a recognized test laboratory (CSA) for specific standards like IEC 60601-2-16. This is non-clinical, laboratory-based data, not patient data from a specific country.

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

  • Not applicable in the context of a 510(k) submission based on technical performance and equivalence to a predicate device, rather than a clinical diagnostic study requiring expert interpretation of results. The "ground truth" here is adherence to engineering specifications and safety standards.

• 4. Adjudication method for the test set:

  • Not applicable, as this is not a study requiring human adjudication for diagnostic categorization. The "adjudication" is through engineering verification and validation processes against predefined technical specifications and standards.

• 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 is a medical device for continuous renal replacement therapy, not an AI/diagnostic imaging device that would typically involve human readers. Therefore, an MRMC study is not relevant here.

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

  • Not applicable in the way this question typically refers to AI algorithms. The device itself is a "standalone" system in its function, but its performance is verified through engineering tests against objective criteria, not an "algorithm only" performance separate from the device's integrated function. Its operation relies on physician prescription (human-in-the-loop for clinical application, but not for the device's technical performance evaluation).

• 7. The type of ground truth used:

  • Engineering Specifications and Performance Standards: The "ground truth" for this submission is compliance with established engineering specifications for flow rates, accuracy, pressure ranges, alarm settings, and adherence to international safety standards (e.g., IEC60601 series). Additionally, the predicate device's cleared performance serves as a comparative ground truth for equivalence.

• 8. The sample size for the training set:

  • Not applicable. This is not a machine learning or AI device that requires a "training set" in the conventional sense. The "training" for the device's development would be iterative engineering design and testing.

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

  • Not applicable, as there is no "training set" in the AI/ML context. The functional requirements for the device are derived from clinical needs, regulatory standards, and the performance of previous generations of such devices.

Ask a specific question about this device

PrismaSATE solutions are indicated for use as a dialysate in Continuous Renal Replacement Therapy.

PrismaSATE dialysis solutions are ready to use sterile dialysate solutions for use in Continuous Renal Replacement Therapy (CRRT) for the treatment of acute renal failure and in other cases necessitating fluid or solute removal, such as in the case of drug poisoning with dialyzable or filterable substances. The solutions are intended to be used with commercially available CRRT systems as dialysate. A physician prescribes the chemical composition of the solution to be used. The solutions are sterile, and packaged in flexible bags. The composition of the fluid used in renal therapies mirrors normal plasma water, since normalization of the blood is the objective.

PrismaSATE solutions, like other currently available dialysate solutions, consist of various quantities of the following chemicals: sodium chloride, potassium chloride, magnesium chloride, calcium chloride, dextrose, and a buffer of lactose and/or bicarbonate. The solution is prescribed by a physician; the physician selects the appropriate formulation based on the patient's blood electrolyte level and desired traits. PrismaSATE dialysate solutions are offered in a range of electrolyte concentrations which mirror the range of electrolytes in plasma. The solution may be buffered using lactate, bicarbonate using lactic acid as a pH adjustor, or bicarbonate using hydrochloric acid as a pH-adjusting excipient.

This document is a 510(k) premarket notification for a medical device called "PrismaSATE dialysis solutions" by Baxter Healthcare Corporation.

Based on the provided text, the device is the PrismaSATE dialysis solutions buffered with bicarbonate using hydrochloric acid as a pH-adjusting excipient, packaged in polyolefin primary packaging materials. The purpose of this 510(k) is to expand the existing PrismaSATE solution formulations into a different packaging material.

Here's an analysis of the acceptance criteria and the "study" (design verification in this case) that aims to prove the device meets these criteria:

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

The document states: "Baxter Healthcare Corporation performed design verification for the modification. The result met its acceptance criteria, and supports that the proposed device is appropriately designed for its intended use." However, it does not explicitly list the acceptance criteria or specific numerical performance results of this "design verification".

Instead, it refers to the modification of packaging material. The acceptance criteria would likely relate to the integrity and compatibility of the solution with the new polyolefin packaging, and the maintenance of the solution's properties.

Based on the "Device Comparison Table" (Table 3) and the "Discussion of Nonclinical Tests," the implied performance criteria and the device's reported ability to meet them are:

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

The document explicitly states: "No performance data is included in this Special 510(k)." This implies that no new testing with a specific test set was conducted or provided in this submission to demonstrate performance with the new packaging. The submission relies on the substantial equivalence to predicate devices, where performance data would have been established for the individual components (solution formulation and packaging material).

Therefore, specific sample sizes, country of origin, or retrospective/prospective nature of the data for this specific submission are not provided. The "design verification" mentioned is described broadly without these details.

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. No new test set data is presented for which ground truth would need to be established by experts for performance evaluation. The "design verification" would likely involve internal company experts in engineering, quality, and manufacturing, but their specific roles or number are not specified for "ground truth" establishment in a performance study context.

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

Not applicable. There is no mention of a performance study involving interpretation or scoring of data that would require an adjudication method.

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 a dialysis solution and its packaging, not an AI or imaging diagnostic device that would require an MRMC study.

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

Not applicable. This device is not an algorithm.

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

Not applicable in the conventional sense of a clinical performance study for an AI or diagnostic device. The "ground truth" for this submission is effectively the established performance and safety profiles of the predicate devices. The "design verification" likely relied on manufacturing specifications, chemical analysis, stability testing, and packaging integrity tests, rather than a clinical "ground truth" established by external experts.

8. The sample size for the training set:

Not applicable. This is not a machine learning or AI device that would require a training set.

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

Not applicable.

Ask a specific question about this device