Search Results

The Prestige Coil System is indicated for arterial and venous embolizations in the peripheral vasculature.

The Prestige Coil System is intended for use in the peripheral vasculature to endovascularly obstruct or occlude blood flow in vascular abnormalities of the peripheral vessels.

The Prestige Coil System is a product family of embolic coils with associated delivery system components. These devices are angiographically delivered through the vasculature to embolize peripheral vascular abnormalities. The devices are to be permanently placed in the peripheral vessels to create blood stasis, reducing flow into the anomaly, and thrombosing the target site.

The provided FDA 510(k) Clearance Letter for the Prestige Coil System (Prestige Packing Coil Line Extension) does not describe a study involving an AI/Machine Learning device, human readers, or image interpretation. Instead, it describes a vascular embolization device and its mechanical and physical performance testing.

Therefore, many of the requested points in your prompt are not applicable to this document, as they relate to studies of AI performance or human reader studies in diagnostic imaging, which is not the subject of this 510(k) clearance.

However, I can extract the relevant information from the provided text regarding the device's acceptance criteria and the performance testing conducted.

Here's the breakdown based on the provided document:

Device: Prestige Coil System (Prestige Packing Coil Line Extension)

Type: Vascular Embolization Device (mechanical medical device)
Purpose: Arterial and venous embolizations in the peripheral vasculature.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document repeatedly mentions "test samples" but does not specify the exact number of samples used for each test (Visual Inspection, Dimensional Inspection, Resistance Check, and Simulated Use).
• Data Provenance: Not applicable in the context of clinical data. This refers to bench testing involving physical device samples. No specific country of origin or retrospective/prospective data collection is mentioned as this relates to device manufacturing and testing, not patient data.

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

• Not Applicable. "Ground truth" in this context refers to the defined engineering specifications and performance characteristics of the device. These are established through design controls, manufacturing standards, and engineering principles, not through expert consensus on medical image interpretation. The "experts" would be engineers and quality control personnel involved in the device's design and testing.

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

• Not Applicable. This is a concept related to consensus building among human readers (e.g., radiologists) for establishing ground truth in image-based studies. For physical device bench testing, the "adjudication" is based on objective measurements against pre-defined engineering specifications and Pass/Fail criteria. No multi-reader adjudication method applies here.

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 document describes a vascular embolization device, not an AI/Machine Learning diagnostic device. Therefore, no MRMC study or AI assistance was involved.

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

• Not Applicable. This is a mechanical device, not an algorithm. Standalone performance refers to the device's inherent functional capabilities as demonstrated in the bench tests, which are independent of a human operator's actions beyond following the instructions for use during the test.

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

• The "ground truth" for this device's performance testing is based on pre-established engineering specifications, design requirements, and manufacturing tolerances for the physical device. The device passes if its measured physical and functional characteristics meet these objective, pre-defined criteria. There is no biological "ground truth" (like pathology or outcomes data) in this specific submission, as it focuses on demonstrating the substantial equivalence of a modified mechanical device through bench testing.

8. The sample size for the training set

• Not Applicable. This applies to AI/Machine Learning models, not physical medical devices undergoing bench testing. The device itself is not "trained."

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

• Not Applicable. As above, this applies to AI/Machine Learning models.

Ask a specific question about this device

The Prestige Coil System is indicated for arterial and venous embolizations in the peripheral vasculature.

The Prestige Coil System is a series of specialized coils that are inserted into the vasculature under angiographic visualization to embolize peripheral vascular anomalies. The system consists of an embolization coil implant comprised of platinum/tungsten, affixed to a delivery pusher to facilitate insertion into the hub of a microcatheter. The system is available in various shapes, lengths, and sizes. The devices are to be placed into anomalies to create blood stasis, reducing flow in the target vasculature, and inducing thrombosis. Upon positioning coils into the vasculature, the coils are thermally detached from the delivery pusher in serial manner until the target vasculature is occluded.

The provided text is a 510(k) summary for the Prestige Coil System, a vascular embolization device, which explicitly states that it is not an AI/ML powered device. Therefore, it does not involve any of the AI/ML related concepts you asked about, such as training sets, test sets, ground truth establishment, MRMC comparative effectiveness studies, or AI performance metrics.

However, I can still extract the acceptance criteria and information about the studies performed for this non-AI medical device.

1. Table of Acceptance Criteria and Reported Device Performance

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

As this is a non-AI/ML device, the concept of a "test set" in the context of AI does not directly apply. The studies mentioned are bench tests and non-clinical device assessments. Specific sample sizes for each test are not provided in this summary. The data provenance is from non-clinical bench testing performed by the manufacturer (Balt USA, LLC) to demonstrate 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

Not applicable, as this is not an AI/ML device and does not involve establishing ground truth through expert review for a test set.

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

Not applicable, as this is not an AI/ML device and does not involve adjudication of expert assessments for a test set.

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, as this is not an AI/ML device and does not involve human readers or AI assistance.

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

Not applicable, as this is not an AI/ML device and does not have an algorithm to be evaluated in standalone mode.

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

Not applicable, as this is not an AI/ML device. The "ground truth" for the device's performance in these non-clinical tests is based on pre-defined acceptance criteria derived from device specifications and recognized standards (e.g., ISO 10993-1).

8. The sample size for the training set

Not applicable, as this is not an AI/ML device and therefore no training set was used.

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

Not applicable, as this is not an AI/ML device and therefore no training set was used or ground truth established for it.

Ask a specific question about this device

The Prestige Ameritech Pediatric/Child Face Mask is intended to be worn by the patient/Child Facemask is a single use, disposable device, provided non-sterile. The Pediatric/Child Facemask is intended to be worn by the patient (ages 4-12) to cover the nose and mouth to provide a barrier for the respiratory tract for microorganisms and particulate materials. The mask is specifically for use with patients whose age or illness may prevent them from taking necessary precautions where transfer of microorganisms, body fluids, and particulates can occur.

The Prestige Ameritech Pediatric/Childs Face Mask is manufactured using ultrasonic bonding, composed of three layers of materials and pleated to form the mask. The inner layer is composed of nonwoven, the middle layer is meltblown polypropylene filter material, and the outer layer is cellulose. Decorative patterns are printed with colored inks. Masks are held in place on wearer with knitted polyester/spandex elastic earloop and contain a malleable aluminum nosepiece strip. The Pediatric/Child's Face Mask is appropriately sized to the smaller faces of children across a diverse population. The Pediatric/Child's Face Mask is a single use, disposable device, provided non-sterile with no shelf-life. Storage conditions will not affect device safety of effectiveness. All of the materials used in this device are typical materials commonly used in the construction of Surgical Masks and are being used in current legally marketed devices. This product is not made with natural rubber latex.

The provided text describes the acceptance criteria and performance of the Prestige Ameritech Pediatric/Child's Face Mask, comparing it to a predicate device. Here's a breakdown of the requested information:

1. A table of acceptance criteria and the 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)

The document does not explicitly state the specific sample sizes for each test performed on the Prestige Ameritech Pediatric/Child's Face Mask. It mentions that the anthropometric study sample for determining fit was "representative of the current US population in both gender and racial distribution," implying a prospective study, but exact numbers are not given. The origin of the data is not specified beyond being generated for a U.S. FDA 510(k) submission.

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)

This document pertains to the performance testing of a physical medical device (a face mask) against established industry standards. There is no mention of "experts" in the context of establishing ground truth for a test set, as the evaluation relies on standardized laboratory testing methods rather than expert interpretation of data like in an AI/imaging study.

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

Not applicable. The evaluation is based on objective laboratory test results against predefined standards, not on human interpretation requiring adjudication.

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 is a review of a physical medical device (face mask) and does not involve AI or human "readers."

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

Not applicable. This is a review of a physical medical device (face mask) and does not involve an algorithm.

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

The "ground truth" for the device's performance is based on the results of standardized laboratory tests conducted according to recognized national and international standards (e.g., ASTM F2101, Mil M36954C, ISO 10993, CPSC, EN 71-3). These standards define the methodology and expected outcomes for measuring properties like filtration efficiency, breathability, flammability, and biocompatibility. For anthropometry, it's based on measurements against a "representative" population sample.

8. The sample size for the training set

Not applicable. There is no "training set" as this is a physical device evaluation, not an AI model.

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

Not applicable. There is no "training set" as this is a physical device evaluation, not an AI model.

Ask a specific question about this device

Prestige is a dental composite restorative material designed to be used in all classes of cavities

Prestige™ is a light-cured, Nanohybrid dental restorative material intended for use for the restoration in all classes of cavities

The provided document is a 510(k) premarket notification for a dental composite restorative material named "Prestige." It does not describe an AI/ML-driven device or study. Therefore, most of the requested information regarding acceptance criteria, study design, sample sizes, expert qualifications, and ground truth establishment for such a device is not applicable to this document.

The document discusses the "Prestige" dental composite restorative material and its substantial equivalence to a predicate device (Herculite XR & XRV). It focuses on non-clinical performance testing for material properties.

However, I can extract the relevant information from the document that pertains to the non-clinical performance testing conducted for the "Prestige" device to demonstrate substantial equivalence.

Here's the information that can be extracted, interpreted in the context of material performance rather than AI/ML algorithms:

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

The document states that the substantial equivalence is supported by "Physical and Mechanical Properties performance testing." While explicit acceptance criteria values are not given in this summary, the reported performance is that the Prestige™ device "has the same performance and technological characteristics" as the predicate device, and that bench testing indicates its suitability for the intended purpose. The overall acceptance criterion for the 510(k) submission is to demonstrate substantial equivalence to the predicate device.

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

• Sample Size: Not specified in the provided summary. The non-clinical testing refers to "in-house testing" and "side-by-side comparisons" but does not give specific numbers of samples or units tested for each property (e.g., number of specimens for flexural strength).
• Data Provenance: The testing was conducted as "in-house testing" by Danville Materials LLC, located in San Ramon, California, USA. The data would be prospective in relation to the submission, as it was generated specifically to support the 510(k) application.

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)

This is not applicable as the document describes a dental restorative material, not an AI/ML device that requires expert-established ground truth for image interpretation or diagnosis. The "ground truth" for this device would be the objective measurements of its material properties.

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

This is not applicable as the document describes a dental restorative material, not an AI/ML device requiring adjudication of human interpretations.

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

This is not applicable as the document describes a dental restorative material, not an AI/ML device.

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

This is not applicable as the document describes a dental restorative material, not an AI/ML device. The "standalone" performance here would refer to the intrinsic material properties measured in a lab, which are described as being tested.

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

The "ground truth" for this device's performance would be the objective, empirically measured physical and mechanical properties of the material itself (e.g., actual flexural strength values, depth of cure measurements, radiopacity readings, etc.) using established testing standards and methodologies for dental materials.

8. The sample size for the training set

This is not applicable as the document describes a dental restorative material, not an AI/ML device that requires a training set.

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

This is not applicable as the document describes a dental restorative material, not an AI/ML device that requires a training set and associated ground truth.

Ask a specific question about this device

The device is a motor driven, indoor and outdoor transportation vehicle with the intended use to provide mobility to a disabled or elderly person limited to a seated position.

The MOBIE scooter consists of a foldable platform which connects the two front wheels and two rear wheels, an adjustable tiller, a Li-ion battery with an off-board charger, a motor/electromagnetic brake assembly, a electric motor controller and a seat /backrest set. It can be folded for transport in a car trunk. The patient uses the tiller handle/handlebar for steering and a thumb operated potentiometer throttle control lever located at the top of the tiller to engage and disengage the scooter motion in both the forward and reverse directions. When the throttle control lever is released, the electromagnetic brake will be actuated and the scooter is slow to stop.

The provided text is a 510(k) summary for the MOBIE scooter. It describes the device, its intended use, and its substantial equivalence to a predicate device. However, this document does not contain the specific information required to answer your request regarding acceptance criteria for an AI/device performance study.

The MOBIE scooter is a Class II medical device, specifically an electrical scooter for mobility. The "Summary of non-clinical testing" section indicates compliance with various ISO and ANSI/RESNA standards related to wheelchairs and motorized vehicles. These standards generally cover aspects like safety, durability, stability, electromagnetic compatibility, and biocompatibility, but they are not "acceptance criteria" for an AI performance study, nor do they detail a study where device performance is measured against such criteria.

Here's why the requested information cannot be extracted from this document and what each numbered item from your prompt means in the context of an AI device submission:

1. A table of acceptance criteria and the reported device performance: This document lists various ISO and ANSI/RESNA standards that the MOBIE scooter complied with. It does not provide specific numerical acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds for an AI algorithm) nor does it report the device's performance against such metrics. The compliance statement simply says the device met the requirements of these standards, which are qualitative or quantitative tests for physical and electrical safety/performance, not AI algorithm performance.

2. Sample size used for the test set and the data provenance: There is no mention of a "test set" in the context of evaluating an AI algorithm. The testing described for the MOBIE scooter is hardware-focused, likely involving physical devices undergoing tests dictated by the listed standards.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This is entirely irrelevant for a physical mobility device like the MOBIE scooter. Ground truth established by experts is crucial for AI/ML medical devices where the AI is performing a diagnostic or prognostic task.

4. Adjudication method: Similar to point 3, this is for AI performance evaluation, not a physical product's safety and performance testing.

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 designed to evaluate the impact of an AI algorithm on human reader performance for tasks involving interpretation (e.g., radiology images). This is not applicable to a mobility scooter.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: "Standalone" performance refers to an AI algorithm operating independently to produce an output. The MOBIE scooter does not contain an AI algorithm that would have standalone performance in a medical decision-making context.

7. The type of ground truth used: As mentioned, the concept of "ground truth" as it applies to AI algorithm validation (e.g., pathology, expert consensus) is not pertinent to the evaluation of a physical medical device like this scooter. The "ground truth" for the scooter's performance would be whether it physically meets the engineering and safety specifications of the relevant standards.

8. The sample size for the training set: This refers to the data used to train an AI algorithm. The MOBIE scooter does not describe any AI component requiring a training set.

9. How the ground truth for the training set was established: Again, this relates to AI algorithm development, which is not discussed in this document regarding the MOBIE scooter.

In summary, the provided 510(k) pertains to a physical medical device (an electrical scooter) and describes its compliance with established safety and performance standards for such devices. It does not contain any information related to the development or validation of an AI/ML medical device, which would involve acceptance criteria, test sets, ground truth, or expert evaluations as outlined in your prompt.

Ask a specific question about this device

The Biolis 24i Clinical Chemistry Analyzer is a discrete photometric clinical chemistry analyzer. The device is intended to duplicate manual analytical procedures by automating various steps such as pipetting, heating, measuring color intensity, and reporting results. The device is intended to be used with certain materials to measure various analytes of diagnostic interest including glucose.

The Biolis 24i analyzer with glucose hexokinase assay is intended to measure glucose quantitatively in human serum. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic glycemia, and of the pancreatic islet cell carcinoma.

Using photometry, the Biolis 24i instrument measures the glucose concentration in serum by monitoring the change in absorbance at 340 nm. Additionally, the Biolis 24i with Ion-Selective Elective module additionally measures the concentration of the electrolytes, sodium, potassium and chloride in serum, using indirect potentiometry.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Tokyo Boeki Medisys Inc. Biolis 24i Clinical Chemistry Analyzer, specifically for glucose measurement:

Acceptance Criteria and Device Performance for Biolis 24i Clinical Chemistry Analyzer (Glucose)

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary does not explicitly state pre-defined acceptance criteria values for each performance characteristic. Instead, it presents the results of the performance studies and implicitly suggests that these results demonstrated substantial equivalence to the predicate device. For the purpose of this response, I infer the reported performance as the outcome that met the (unspecified) acceptance criteria for substantial equivalence.

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

• Method Comparison: The document does not explicitly state the total number of samples used for the method comparison (correlation analysis) with the Beckman CX-7.
• Precision (Repeatability): 60 replicates for each of 5 serum samples.
• Precision (Total Imprecision): 80 replicates for each of 4 samples (2 controls, 2 serum pools) on each of two different analyzers.
• Linearity: The sample size for the linearity study is not explicitly stated, but it covered a range of 25 - 500 mg/dL.
• Interferences: The sample sizes for the interference study are not explicitly stated, but tests were performed at two glucose concentrations (e.g., 75 mg/dL and 140 mg/dL for Ascorbic acid).
• Data Provenance: The document does not explicitly state the country of origin of the data or whether the studies were retrospective or prospective clinical studies. Given the manufacturer's location (Japan) and the context of typical lab instrument validation, these are likely prospective laboratory studies rather than large-scale clinical trials. The samples used (serum, controls, serum pools) suggest laboratory-generated or purchased materials.

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

This device is a clinical chemistry analyzer, which measures quantitative values of analytes. The "ground truth" for such devices is established by reference methods or validated calibrated materials, not typically by human expert consensus or adjudication on individual cases.

• For Method Comparison: The "ground truth" was essentially the measurements obtained from the predicate device, the Beckman CX-7.
• For Calibration: The calibrator (Pointe Scientific Chemistry Calibrator) was verified against NIST SRM 965b (Glucose in Frozen Serum), which serves as a highly reliable reference.
• No human experts were used to establish the ground truth for the analytical performance of the test set in this context.

4. Adjudication Method for the Test Set

Not applicable. As noted above, the ground truth for this type of device is established by reference methods/calibrators, not by human expert adjudication of individual cases.

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

No. An MRMC study is not relevant for a standalone clinical chemistry analyzer. MRMC studies are typically used for diagnostic imaging devices where human readers interpret images or data, and the effect of AI assistance on their performance is evaluated. This device provides a quantitative measurement directly.

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

Yes, this entire submission focuses on the standalone performance of the Biolis 24i analyzer as a device for measuring glucose quantitatively. There is no human-in-the-loop component in its measurement principle; it is an automated instrument.

7. The Type of Ground Truth Used

The ground truth used was based on:

• Reference measurements from a predicate device (Beckman CX-7) for method comparison studies.
• NIST Standard Reference Material (SRM 965b, Glucose in Frozen Serum) for verifying the calibrator used to establish the measurement accuracy.
• Known concentrations in control materials and serum pools for precision studies.

8. The Sample Size for the Training Set

The document does not explicitly mention a "training set" in the context of device development. Clinical chemistry analyzers are typically developed and validated using well-established analytical principles and internal testing, calibration, and verification processes rather than machine learning "training sets" in the way an AI algorithm might have one. The "training" would refer to the calibration of the instrument using known calibrators. The text states:

• The calibrator (Pointe Scientific Chemistry Calibrator) was assayed eight times over each of four analytical runs against NIST standard levels 3 and 4, each assayed in duplicate. This process helps "train" or verify the calibration curve for the device.

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

As mentioned above, the "training" in this context refers to the calibration and verification process. The ground truth for the calibrator was established by comparing it to NIST SRM 965b, Glucose in Frozen Serum, which has certified glucose values (118.5 mg/dL and 294.5 mg/dL). This comparison allowed for the verification of the 185 mg/dL glucose set point for the Pointe Calibrator.

Ask a specific question about this device

The following Prestige Ameritech Surgical Masks are single use disposable devices intended to be worn in the operating room as well as dental, isolation and other medical procedures to protect both the patient and healthcare personnel from transfer of microorganisms, body fluids, and particulate material.

Prestige Ameritech Earloop Surgical Mask-Blue, Pink, Green, White, Yellow, Peach Prestige Ameritech Earloop Surgical Mask with splash shield-Blue Green, White, Peach Prestige Ameritech Earloop Surgical Mask Tissue-Blue, Pink, White, Yellow Prestige Ameritech Tie on Surgical Mask-Blue, Pink, Green, White, Peach Prestige Ameritech Tie on Surgical Mask with splash shield-Blue, Green, White, Peach

The Prestige Ameritech Surgical Mask device is composed of three layers of material flat folded and pleated to form the Mask. The inner layer is composed of cellulose or spunbonded polypropylene, the middle layer is a meltblown polypropylene filter material and the outer layer is a medical grade tissue or spunbonded polypropylene. Masks with splash shields have anti-fog plastic shields attached to masks. Masks are held in place on wearer with tie strips or latex free elastic loops and contain a malleable aluminum nosepiece strip. All of the materials used in this device are typical materials commonly used in the construction of Surgical Face Masks and are being used in current legally marketed devices.

The provided 510(k) summary describes the Prestige Ameritech Face Mask, a surgical face mask. The acceptance criteria and device performance are based on bench testing of physical properties rather than clinical studies with human participants. Therefore, several of the requested sections (e.g., sample size for test set, number of experts, adjudication method, MRMC study, training set information) are not applicable or cannot be extracted from this document.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the results of the predicate devices, as the Prestige Ameritech device aims to demonstrate substantial equivalence by performing similarly or better.

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

• Sample Size: Not specified in the document. These are bench tests, so sample sizes would refer to the number of mask samples tested for each characteristic.
• Data Provenance: The data is generated from laboratory bench testing (non-clinical tests) of the device and predicate devices. No information about the country of origin or whether it's retrospective or prospective is provided, but it's understood to be prospective testing for the submission.

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

Not applicable. The ground truth for these performance characteristics is established through standardized laboratory test methods (e.g., ASTM F1862, ASTM F2299, ASTM F2101, MIL M36954C, 16CFR 1610). Experts are involved in designing and executing these tests, but "ground truth" isn't established through expert consensus in the typical sense for medical imaging or diagnostic devices.

4. Adjudication method for the test set

Not applicable. This is not a study involving human interpretation or subjective assessments that would require adjudication.

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 is a surgical mask, not an AI-powered diagnostic device, so MRMC studies and AI assistance are not relevant.

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

Not applicable. This is a surgical mask, not an algorithm.

7. The type of ground truth used

The "ground truth" for the device's performance is objective measurement against established industry standards and test methodologies. For example:

• Fluid Resistance: Visual observation of penetration after exposure to synthetic blood.
• Particulate Filtration Efficiency: Quantitative measurement of particle removal at a specific micron size.
• Bacterial Filtration Efficiency: Quantitative measurement of bacterial removal.
• Differential Pressure: Measurement of airflow resistance.
• Flammability: Classification based on burn rate.

8. The sample size for the training set

Not applicable. This is a physical device, and the submission does not describe a training set in the context of machine learning or AI.

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

Not applicable. No training set is described.

Ask a specific question about this device

The PRESTIGE CPAP system is indicated for the treatment of obstructive sleep apnea (OSA) in patients weighing more than 66 lb (>30 kg). It is intended for use at home.

The PRESTIGE CPAP System is similar to the predicate devices, (S8 Prime and S7 Elite CPAP System with H2i) with a new and improved micro-processor controlled blower system that generates Continuous Positive Airway Pressure (CPAP) from 4-20 cmHo as required to maintain an "air splint" for effective treatment of OSA. The system comprises the Flow Generator, patient tubing, mask (patient interface) and humidifier.

The provided text describes a 510(k) premarket notification for the RESMED PRESTIGE CPAP System. It states that "Design and Verification activities were performed on the PRESTIGE CPAP System as a result of the risk analysis and product requirements. All tests confirmed the product met the acceptance criteria." However, it does not provide any specific acceptance criteria or details about the studies performed to demonstrate that the device meets these criteria.

The document mainly focuses on establishing substantial equivalence to predicate devices (S8 Prime and S7 Elite) based on similar intended use, operating principles, technologies, and manufacturing processes. It confirms that the new device has "not altered the safety and effectiveness of CPAP treatment."

Therefore, I cannot populate the requested table and answer the study-specific questions based on the provided text. The submission is a regulatory filing focused on equivalence, not a detailed report of performance studies with specific statistical outcomes or methodologies.

Ask a specific question about this device

This device with an optional Ion Selective Electrode (ISE) module is a clinical chemistry analyzer intended to be used for the measurement of sodium, potassium and chloride in serum to monitor electrolyte balance.

The Prestige 24i with Ion Selective module additionally measures the concentration of the electrolytes, sodium, potassium and chloride in samples, using indirect potentiometry.

Here's an analysis of the provided text regarding acceptance criteria and the supporting study, structured as requested:

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary for the Prestige 24i (and equivalent models) details performance characteristics. The acceptance criteria themselves are not explicitly stated as pass/fail thresholds in the document. Instead, the study aims to demonstrate substantial equivalence to a predicate device (Roche Cobas Mira Plus) through correlation, linearity, and precision. The reported performance is presented to support this claim of equivalence.

Given this, the table below presents the reported performance values. The implied acceptance criteria are that these values should be comparable to or within acceptable ranges for similar clinical chemistry analyzers for the measurement of sodium, potassium, and chloride, especially when compared to the predicate device.

2. Sample Size and Data Provenance

• Sample Size for Test Set: The document does not explicitly state the total number of patient samples or data points used for the correlation or linearity studies.
  • For the precision test, the "N=20" indicates 20 measurements were taken for both "Within Run" and "Day by Day" precision calculations for each analyte (Sodium, Potassium, Chloride) and for two different samples (Sample 1 and Sample 2). This refers to the number of replicates, not necessarily unique patient samples.
• Data Provenance: Not specified. The document does not mention the country of origin of the data or whether it was retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth

• This device is a clinical chemistry analyzer, which measures analytes directly. Therefore, the "ground truth" for the test set is established by the measurement itself from a reference method (the predicate device, Roche Cobas Mira Plus) or controlled samples with known concentrations for linearity and precision.
• No human experts (e.g., radiologists) were involved in establishing the ground truth for this type of device performance study.

4. Adjudication Method for Test Set

• Not applicable. As a clinical chemistry analyzer, the "ground truth" is based on the analytical measurements from a reference method or known concentrations, not on expert interpretation requiring adjudication.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is relevant for image-interpretation devices where human readers' performance is assessed. For a clinical chemistry analyzer measuring analytes, the direct comparison is between the new device's readings and a reference method's readings.
• Therefore, there is no effect size reported for human readers' improvement with or without AI assistance.

6. Standalone (Algorithm Only) Performance

• This is a standalone device in the sense that its measurements are directly compared to a predicate device. The performance characteristics (correlation, linearity, precision) are measures of the algorithm/device's analytical performance on its own. It's not an "AI algorithm" in the typical sense of interpreting complex data like images, but rather an automated analytical instrument.

7. Type of Ground Truth Used

• The ground truth for the correlation study was established by comparison to a legally marketed predicate device (Roche Cobas Mira Plus).
• For the linearity test, the ground truth would be samples with known, incrementally varied concentrations of the analytes.
• For the precision test, the ground truth would be repeated measurements of control or patient samples to assess the variability.

8. Sample Size for Training Set

• The document does not specify a separate "training set" or its sample size. Clinical chemistry analyzers are typically developed and validated using a range of samples and controls, but the concept of a "training set" like in machine learning models is not explicitly mentioned or typically applicable in the same way for these types of analytical instruments. The performance data presented are from validation studies, which serve to demonstrate the device's accuracy and reliability.

9. How Ground Truth for Training Set Was Established

• Given that a "training set" is not explicitly defined or described in the context of this device in the provided text, the method for establishing its ground truth is not specified. The validation relies on comparisons to known materials and a predicate device as described in point 7.

Ask a specific question about this device

Ask a specific question about this device