Search Results

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

High gold casting alloy

The provided document is a 510(k) summary for a dental casting alloy, AURELUX 77. This document focuses on demonstrating substantial equivalence to a predicate device (Jelenko Jel 96) rather than proving device performance against specific acceptance criteria in a clinical or standalone study as one would expect for an AI/CADe device.

Therefore, the information required to answer the prompt (acceptance criteria, study details, sample sizes, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, or standalone algorithm performance) is not present in this document because it describes the submission of a material device, not a software or AI-driven device.

However, I can extract the comparison data between the new device and the predicate device, which serves as the "performance" demonstrated for this type of submission.

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

The acceptance criteria for this type of device are intrinsic to demonstrating "substantial equivalence" to a legally marketed predicate device. This means the new device's characteristics should be similar enough to the predicate device that it doesn't raise new questions of safety or effectiveness. The comparison table below effectively acts as the "performance" data against these implicit acceptance criteria of substantial equivalence.

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

This information is not applicable and not provided in the document. The "study" here is a comparison of material properties, not a clinical trial with a test set of patients or images. The "data" are the results of material tests (chemical composition analysis, melting point tests, hardness tests, etc.), which are inherent properties of the alloy. The provenance would be the laboratory where these tests were conducted, which is not specified but would typically be an internal or contracted materials testing lab.

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. "Ground truth" in the context of an AI/CADe device refers to highly accurate clinical diagnoses or annotations. For a material science submission, "ground truth" is established through standardized laboratory testing yielding objective physical and chemical measurements. There are no human experts establishing ground truth in the clinical sense for this type of submission.

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

This is not applicable. Adjudication methods are relevant for human interpretation tasks, especially in AI/CADe studies where there might be disagreement among experts. Here, the "test set" consists of laboratory measurements, not 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. An MRMC study is relevant for evaluating the impact of AI on human reader performance in diagnostic tasks. This document describes a dental casting alloy, not an AI or diagnostic software.

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

This is not applicable. Standalone performance refers to the performance of an AI algorithm independent of human intervention. This document describes a physical material.

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

For this material device, the "ground truth" (or the reference standard for comparison) is derived from standardized physical and chemical laboratory testing and measurements performed on both the predicate device (Jel 96) and the new device (Aurelux 77) according to recognized test methods (ANSI/ADA 5 and ISO 9693). There is no "pathology" or "outcomes data" in the clinical sense for this type of submission.

8. The sample size for the training set

This is not applicable. "Training set" refers to data used to train an AI algorithm. This document describes a physical material.

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

This is not applicable. There is no training set or AI algorithm in this submission.

Ask a specific question about this device

Dental Casting alloy used for fabrication of metallo-ceramic restorations in conjunction with dental ceramics of thermal expansion co-efficient not less than 16.3 x 10 -9K. (25 - 600°C)

High gold casting alloy

The provided text describes the 510(k) summary for AURENORM 68, a dental casting alloy, and its comparison to a legally marketed predicate device, Jelenko Allround 4. The focus is on demonstrating substantial equivalence based on technological characteristics rather than clinical performance from a study. Therefore, the request for "acceptance criteria and the study that proves the device meets the acceptance criteria" as it pertains to AI/medical imaging performance metrics cannot be fully answered in the typical sense.

However, I can extract and structure the information provided in a way that aligns with the spirit of your request, interpreting "acceptance criteria" as the comparison points for demonstrating substantial equivalence and "reported device performance" as the properties of AURENORM 68.

1. Table of Acceptance Criteria and Reported Device Performance

For medical devices applying for 510(k) clearance, the "acceptance criteria" for demonstrating substantial equivalence often involve showing that the new device has similar technological characteristics (composition, physical, and mechanical properties) and intended use as a predicate device. The "study" in this context is the comparison of these characteristics.

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

This information is not applicable to the provided document. The submission is a 510(k) summary for a material (dental alloy) and does not involve a clinical study with a test set of data like an AI/imaging device would. The "test methods applied" refer to industry standards for material testing (ANSI/ADA 5, ISO 1562, and 9693), not a clinical trial or performance evaluation using patient data.

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. Ground truth as typically understood in AI/imaging studies (e.g., expert consensus on medical images) is not relevant for this type of device submission. The "ground truth" here is the measured physical and chemical properties of the alloy.

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

Not applicable. No expert adjudication for a test set is described.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This is not a study involving human readers or AI assistance.

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

Not applicable. This is a material submission, not an algorithm.

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

The "ground truth" in this context would be the empirical measurements of the chemical composition and physical/mechanical properties of the alloy (Aurenorm 68 and Allround 4) adhering to the specified industry standards (ANSI/ADA 5, ISO 1562, and 9693).

8. The sample size for the training set

Not applicable. There is no training set in the context of this device submission.

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

Not applicable. There is no training set mentioned in the document.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

High gold casting alloy

The provided document is a 510(k) summary for a dental casting alloy, AURELUX Bio Y85PF. The primary study presented is a comparison between the new device and a legally marketed predicate device (Argen Argedent Bio Yellow PF) based on composition and physical/mechanical properties. The overall conclusion is that the new alloy is "substantially equivalent" to the predicate, implying it meets similar performance characteristics.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in the traditional sense of a numerical threshold that must be met. Instead, the acceptance is based on demonstrating substantial equivalence to a predicate device. The performance is reported as a direct comparison of physical and mechanical properties and composition. The implication is that if the new device's properties are comparable to the predicate, it meets the "acceptance criteria" for substantial equivalence.

Note on "Acceptance Criteria": For an equivalence study like this, the "acceptance criteria" are implicitly that the measured properties of the new device are sufficiently close to those of the predicate device to justify the claim of substantial equivalence. The document concludes: "On the basis of the very high noble metal content and essentially same constitution it may be expected that the new alloy perform very similarly to Argident B Y PF." This statement serves as the justification for meeting the implicit acceptance criteria.

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

• Sample Size: The document does not specify a "sample size" in terms of number of manufactured devices tested. Instead, it presents specific compositional percentages and physical/mechanical property values, which are likely derived from laboratory testing of material samples. The number of samples per test is not detailed.
• Data Provenance: The document does not explicitly state the country of origin of the data. Given the address of the applicant (Aurex Precious Metal Industries, Republic of South Africa), it's reasonable to infer the testing was conducted there or by a contracted lab. The data is retrospective, as it compares the new device's properties to a pre-existing, legally marketed predicate device.

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

Not applicable. This study does not involve expert evaluation of clinical images or diagnostic outcomes. The "ground truth" here is objective material science data (composition, physical/mechanical properties) as measured by standard test methods (ANSI/ADA 5 and ISO 9693).

4. Adjudication Method for the Test Set

Not applicable. There is no adjudication method described as this is not a study requiring expert consensus or multiple readings.

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

No, an MRMC comparative effectiveness study was not done. This is a material science comparison for a dental casting alloy, not a diagnostic device involving human readers or cases.

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

Not applicable. This is not an algorithm-based device.

7. The Type of Ground Truth Used

The ground truth used is objective material science data derived from standardized laboratory test methods (ANSI/ADA 5 and ISO 9693) for:

• Elemental composition (weight percentage of metals)
• Physical properties (melting point range, density, CTE)
• Mechanical properties (hardness, yield strength, elongation)

8. The Sample Size for the Training Set

Not applicable. This is not a machine learning or algorithm-based device, so there is no concept of a "training set."

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

Not applicable. As there is no training set, there is no ground truth established for one.

Ask a specific question about this device

Dental casting alloy for making restoration.

High gold casting alloy

I am sorry, but the provided text describes a 510(k) submission for a dental casting alloy named AURECAST 92. This document is a regulatory submission for a material, not a medical device that would involve a study with acceptance criteria, sample sizes, expert ground truth, or human-in-the-loop performance as you've requested.

The document focuses on comparing the AURECAST 92 alloy to a legally marketed predicate device (Argenco Bio10) based on composition, physical, and mechanical properties. The acceptance is based on the substantial equivalence of these material properties, rather than performance metrics of a device against specific clinical or diagnostic criteria.

Therefore, I cannot extract the information required for the table and bullet points you provided, as those concepts (like sample size for test sets, ground truth by experts, MRMC studies, standalone performance) are not applicable to the type of device and submission described in the text.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Medium gold casting alloy

This document is a 510(k) premarket notification for a dental casting alloy, AUREBOND 51. The information provided is primarily focused on demonstrating substantial equivalence to a predicate device, Jelenko Olympia, rather than presenting a study proving the device meets specific performance acceptance criteria for an AI/ML medical device.

Therefore, most of the requested information regarding acceptance criteria, study design for AI/ML performance, sample sizes, expert involvement, and ground truth establishment is not present in this document. This typically applies to AI/ML software as a medical device (SaMD) or as part of a medical device (SiMD).

Here's an attempt to answer the questions based only on the provided text, recognizing its limitations for the requested context:

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

Based on the document, the "acceptance criteria" are implied to be the ranges and values of the predicate device (Jelenko Olympia) for its composition and physical/mechanical properties. The "reported device performance" are the measured values for the new device (Aurebond 51).

Conclusion from the document: "Essentially similar composition, only slight difference in mechanical properties." This indicates that the observed differences were deemed acceptable for substantial equivalence.

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. Standard material testing would use multiple samples, but the exact number isn't in the provided text.
• Data Provenance: The device manufacturer (Aurex) is in the Republic of South Africa. The testing methods applied are "as in ANSI/ADA 5 and ISO 9693," which are international standards for dental materials. The raw data origin (country, retrospective/prospective) is not specified.

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 to a material testing submission. "Ground truth" in this context would be physical and chemical measurements performed according to established standards, not expert consensus or interpretation.

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

Not applicable. Material testing follows standardized methods, not expert 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 material science submission, not an AI/ML diagnostic device.

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

Not applicable. This is a material science submission, not an AI/ML diagnostic device.

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

The "ground truth" for this device's performance is established by standardized physical and chemical testing methods using laboratory equipment, as referenced by ANSI/ADA 5 and ISO 9693 standards. It's not based on expert consensus, pathology, or outcomes data in the way an AI/ML diagnostic would be.

8. The sample size for the training set

Not applicable. This is a material science submission, not an AI/ML device that requires a training set.

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

Not applicable. This is a material science submission, not an AI/ML device.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Low gold palladium based casting alloy

The provided text describes a 510(k) summary for a dental casting alloy named PALAUREX 78, seeking to establish its substantial equivalence to a legally marketed device, Jelenko Freedom Plus. It is not a study proving a device meets acceptance criteria in the typical sense of a clinical or performance study with defined performance metrics like sensitivity, specificity, or reader improvement. This document is a pre-market notification to the FDA, demonstrating that a new device is as safe and effective as a predicate device.

Therefore, the requested information elements such as "sample size for the test set," "number of experts," "adjudication method," "MRMC comparative effectiveness study," and "standalone performance" are not applicable to this type of submission. This submission focuses on comparing the new device's technological characteristics (composition and physical/mechanical properties) to a legally marketed predicate device.

Here's the information that can be extracted from your input, framed within the context of substantial equivalence rather than traditional acceptance criteria:

1. Acceptance Criteria and Reported Device Performance

The "acceptance criteria" for this 510(k) submission are not explicit numerical thresholds for clinical performance (like accuracy metrics). Instead, the acceptance criterion is demonstrating substantial equivalence to the predicate device, Jelenko Freedom Plus, by showing similar technological characteristics and an expectation of similar biological effect and intended use. The "reported device performance" is a comparison of these characteristics.

Discussion from the document:

• "The noble content metal is high (80%) in both alloy, with almost identical breakdown to the respective elements."
• "Palaurex 78 has two base metal elements, Cu and Ga; Freedom Plus has In as well."
• Conclusion: "On the basis of the identical major elements and high noble metal content similar biological effect may be expected from both alloys."

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

• Sample Set: Not applicable in the context of a clinical test set. The "test set" here refers to the actual alloy samples of PALAUREX 78 that were subjected to the specified physical and mechanical tests. The exact number of samples tested for each property is not disclosed, but it would have been sufficient to perform the tests as per the cited standards (ANSI/ADA 5 and ISO 9693).
• Data Provenance: The device manufacturer, Aurex Precious Metal Industries (PTY)-LTD., is based in the Republic of South Africa. The testing would have been conducted to international standards (ANSI/ADA 5 and ISO 9693), implying a laboratory setting for material characterization. This is a retrospective analysis of the material's properties based on standardized lab tests.

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 the sense of expert consensus on clinical findings, is not relevant for this material characterization submission. The "ground truth" for the material properties (e.g., melting point, hardness) is established by the standardized test methods themselves (ANSI/ADA 5 and ISO 9693) which are internationally recognized protocols for material characterization. Compliance with these standards is considered the "truth."

4. Adjudication method for the test set

• Not Applicable. Adjudication methods like '2+1' or '3+1' are used for resolving discrepancies in expert interpretations of clinical data. This submission relies on objective, quantifiable material properties measured according to established standards, not subjective 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

• Not Applicable. This is a submission for a dental casting alloy, not an AI-powered diagnostic device or a system involving human readers.

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

• Not Applicable. This is a dental material, not an algorithm.

7. The type of ground truth used

• The "ground truth" for the performance claims (compounds, mechanical and physical properties) is derived from standardized laboratory testing methods (ANSI/ADA 5 and ISO 9693). These standards define how to measure these properties precisely and objectively.

8. The sample size for the training set

• Not Applicable. There is no "training set" in the context of this material property comparison. Machine learning or AI models, which typically require training sets, are not involved.

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

• Not Applicable. As there is no training set, this question is not relevant.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Palladium based casting alloy

This document is a 510(k) summary for the Palceram 82SF dental casting alloy, asserting its substantial equivalence to the legally marketed device Argipal. The information provided heavily emphasizes a direct comparison of the new device to the predicate device, rather than defining independent acceptance criteria with separate performance goals.

Therefore, the "acceptance criteria" and "device performance" are presented as a comparison to the predicate device, Argipal, arguing that because Palceram 82SF has "practically identical technological characteristics" it meets the necessary standards. There is no explicit and distinct set of predetermined acceptance criteria independent of the predicate device for this submission.

Here's the information requested, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The acceptance criteria for Palceram 82SF are implicitly defined by its substantial equivalence to the Argipal alloy. The "reported device performance" for Palceram 82SF is presented as being nearly identical to Argipal.

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

The document states that "Test methods applied: as in ANSI/ADA 5 and ISO 9693." However, it does not specify the sample size for any of the tests performed or the data provenance (e.g., country of origin, retrospective or prospective). The data presented appears to be summary statistics rather than raw data from a specific test set.

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

Not applicable. This submission concerns a dental casting alloy, and performance is determined by physical and chemical property testing, not expert interpretation of outputs.

4. Adjudication method for the test set

Not applicable. This submission concerns a dental casting alloy, and performance is determined by physical and chemical property testing, not subjective 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 not an AI-assisted device.

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

Not applicable. This is not an algorithm-based device. The testing described is for material properties.

7. The type of ground truth used

The "ground truth" for the performance claims is based on standard laboratory measurements of chemical composition as well as physical and mechanical properties, conducted according to ANSI/ADA 5 and ISO 9693 standards.

8. The sample size for the training set

Not applicable. This is not a machine learning or AI-based device, so there is no concept of a training set. The data presented is for the characterization of the material.

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

Not applicable. As there is no training set for this type of device, this question is not relevant.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Gold reduced palladium based casting alloy

The provided document is a 510(k) summary for a dental casting alloy, Hipallaur 19. It focuses on demonstrating substantial equivalence to a predicate device (Aurolite 2A) through a comparison of composition and physical/mechanical properties. This type of submission is not a clinical study report and therefore does not contain the information requested in your prompt regarding acceptance criteria, study design, expert ground truth, or human-AI performance.

The document discusses the technical characteristics of the device and its predicate, including:

• Comparison of composition (weight %):

  • Legal (Aurolite 2A): Au (13.5), Ag (27.8), Pd (49.5), Sn (4.6), In (4.4), Fe (0), Mn (0), Ru (x < 1%)
  • New (Hipallaur 19): Au (19), Ag (10.4), Pd (57.1), Sn (10.3), In (2.3), Fe (0.3), Mn (0.5), Ru (0.1)

• Comparison of physical and mechanical properties:

• Test Methods Applied: ANSI/ADA 5 and ISO 9693 standards were used for testing the characteristics.

The report concludes that the new alloy (Hipallaur 19) is very similar to Aurolite 2A based on its constitution, with potentially slightly better corrosion resistance due to higher noble metal content.

In summary, the document does not contain the information you requested about acceptance criteria and a study proving device performance in a clinical or AI context because it is a regulatory submission for a dental casting alloy, not a clinical trial or AI performance study.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Medium gold palladium based casting alloy

The provided text is a 510(k) summary for a dental casting alloy named HIPALLAUR 51. This document describes the device and compares it to a legally marketed predicate device (Jelenko Cameo) based on composition and physical/mechanical properties to demonstrate substantial equivalence. It does not describe an AI/ML device or a study with acceptance criteria and device performance in the way requested in the prompt.

Therefore, many of the requested categories are not applicable to the provided text. I will address the relevant information that can be extracted.

Not Applicable:

• A table of acceptance criteria and the reported device performance: This document is a 510(k) submission, which focuses on demonstrating substantial equivalence to a predicate device, not on meeting specific, predefined acceptance criteria for a new AI/ML device performance. The "performance" here is comparison to a predicate.
• Sample size used for the test set and the data provenance: There isn't a "test set" in the context of an AI/ML device. The comparison is based on material properties.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable.
• Adjudication method for the test set: Not applicable.
• If a multi reader multi case (MRMC) comparative effectiveness study was done: Not applicable for a dental alloy.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable for a dental alloy.
• The type of ground truth used: Not applicable in the AI/ML sense. The "ground truth" for this submission is established chemical composition and physical properties measured by standard methods.
• The sample size for the training set: Not applicable for a dental alloy.
• How the ground truth for the training set was established: Not applicable for a dental alloy.

Applicable Information (based on interpretation of the prompt for a non-AI/ML device):

The "acceptance criteria" for a 510(k) submission like this are implicitly demonstrating substantial equivalence to a legally marketed predicate device. The "device performance" is presented through direct comparison of material properties.

1. Table of Acceptance Criteria and the Reported Device Performance

For this 510(k) submission, the implicit "acceptance criteria" are that the new device (HIPALLAUR 51) has a composition and physical/mechanical properties that are sufficiently similar to the legally marketed predicate device (Jelenko Cameo) to ensure equivalent safety and effectiveness.

Here's a table synthesizing the comparison presented:

Summary of the study/comparison:
The study demonstrates that "All the elements above 1 % are the same in both alloys. The difference in concentration for every component is less than 5 %. The elements under 1 % content are either noble ones, or the ones that oxidize and be eliminated during melting. Consequently, they have little effect upon the characteristics of the alloys." The conclusion states, "Up to 99 % both alloy consist of the same elements. This suggests that chemical and biological behaviour should be similar."

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

The document does not specify a "sample size" in the context of a statistical study for device performance. The data provenance is from the manufacturer, Aurex Precious Metal Industries (PTY) LTD., based in the Republic of South Africa. The data appears to be based on laboratory testing of material properties, rather than clinical trials with human subjects. The data is retrospective in the sense that the predicate device's data is existing, and the new device's data is measured for comparison.

6. If a standalone was done:
Yes, the comparison of the HIPALLAUR 51 alloy's composition and physical/mechanical properties, as measured according to ANSVADA 5 and ISO 9693 standards, is a standalone assessment of the device's characteristics against those of the predicate device. There is no human-in-the-loop component for evaluating the performance of a dental alloy.

7. The type of ground truth used:
For the purpose of this 510(k) submission, the "ground truth" is established by:

• Chemical Analysis: Determining the exact elemental composition (weight%) of both the predicate and new alloys.
• Standardized Physical/Mechanical Property Testing: Measurements of properties like melting point, hardness, yield strength, elongation, CTE, and density, conducted according to recognized industry standards (ANSVADA 5 and ISO 9693). These standards define the accepted methods for obtaining these measurements, ensuring consistency and reliability of the "ground truth" data.

Ask a specific question about this device

Dental casting alloy used in combination with dental ceramics for fabrication of metallo-ceramic restoration.

Low gold palladium based casting alloy

1. Acceptance Criteria and Reported Device Performance:

The "acceptance criteria" here are defined by the properties of the legally marketed predicate device, Jelenko Legacy XT. The study demonstrates that the Palaurex 76 KF, while having some differences, is considered substantially equivalent based on the listed physical and mechanical properties and composition. The discussion indicates that the differences, such as Sn compensating for lower Ag, were deemed acceptable.

2. Sample Size for Test Set and Data Provenance:

   • Sample Size: Not explicitly stated for each test beyond the comparative tables showing single values for each property. The tests were run according to ANSI/ADA 5 and ISO 9693 standards, which would define the number of samples required for each specific test (e.g., hardness, tensile).
   • Data Provenance: Not explicitly stated, but the submission is from "Aurex Precious Metal Industries (PTY) LTD." in the "Republic of South Africa." The data likely originated from their internal testing or accredited labs in support of their submission. The data is retrospective in the context of the 510(k) submission, as it was generated prior to the submission for pre-market notification.

3. Number of Experts and Qualifications:

   • Not applicable. This is a submission for a dental casting alloy, and the evaluation relies on objective physical and chemical property comparisons, not expert interpretation of images or clinical outcomes.

4. Adjudication Method:

   • Not applicable. This is not a study involving human interpretation or clinical adjudication. Properties are measured against standard test methods.

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

   • Not applicable. This is a material science comparison, not a study evaluating human readers' performance with or without AI assistance.

6. Standalone (Algorithm Only) Performance:

   • Not applicable. This is not a software device or an algorithm. The "performance" refers to the intrinsic physical and chemical properties of the alloy.

7. Type of Ground Truth Used:

   • The "ground truth" for the new device's performance is based on measurements taken according to established international standards (ANSI/ADA 5 and ISO 9693).
   • The "ground truth" for the comparison/acceptance criteria is the reported properties of the legally marketed predicate device, Jelenko Legacy XT.

8. Sample Size for Training Set:

   • Not applicable. This is a materials comparison, not a machine learning model.

9. How Ground Truth for Training Set was Established:

   • Not applicable. This pertains to machine learning models, which is not relevant here.

Ask a specific question about this device