Search Results

Hardware:
The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.

The Materialise Shoulder Guide and Models are single use only.

The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

• · DePuy Synthes'
• GLOBAL® APG+ Shoulder System (K052472)
• DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077, K203694)
• GLOBAL® STEPTECH® APG Shoulder System (K092122)
• INHANCE™ Anatomic Shoulder System (K202716)1
• INHANCE™ Reverse Shoulder System (K212737)
• INHANCE™ Hybrid Anatomic Glenoid Implant (K212933)
• INHANCE™ Reverse Glenoid Peripheral Posts (K221467)
• INHANCE Convertible Glenoid (K230831)
• · Enovis'2 (DJO)
• Reverse® Shoulder Prosthesis (K051075, K111629, K092873)
• Turon® Shoulder System (K080402)
• AltiVate™ Anatomic Shoulder System (K162024)
• AltiVate™ Anatomic Augmented Glenoid (K213387, K222592)
• AltiVate™ Reverse Glenoid (K233481)
• · Smith+Nephew's3
• Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)
• Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• AETOS Total Shoulder System (K220847, K230572)
• AETOS Reverse Shoulder System (K220847, K230572)
• · Lima's
• SMR™ Shoulder System (K100858)
• SMR™ Reverse Shoulder System (K110598)
• SMR™ Modular Glenoid (K113254) (K143256)
• SMR™ 3-Pegs Glenoid (K130642)
• SMR™ TT Metal Back Glenoid (K133349)
• SMR TM 40mm Glenosphere (K142139)
• SMR™ TT Augmented 360 Baseplate (K220792)
• SMR™ TT Hybrid Glenoid (K220792)
• PRIMA TT Glenoid (K222427)

Software:
SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

• a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used . to generate a pre-surgical plan for a specific patient.
• Materialise Shoulder Guide and Models, which are a patient-specific quide and models that are based ● on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patientspecific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

The provided FDA 510(k) summary (K242813) for the Materialise Shoulder System™ describes a submission seeking substantial equivalence to a previously cleared device (K241143). This submission is primarily for adding compatibility with new implant components rather than introducing a completely new AI capability or significant software change that would necessitate extensive new performance data. Therefore, the document does not contain the detailed information typically found in a study proving a device meets acceptance criteria for an AI/ML product.

Specifically, the document states:

• "The non-clinical performance data has demonstrated that the subject software technological differences between the subject and predicate devices do not raise any different questions of safety and effectiveness." (Page 9)
• "Software verification and validation were performed, and documentation was provided following the 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.' This includes verification against defined requirements, and validation against user needs." (Page 10)
• "Previous testing for biocompatibility, sterility, cleaning, debris, dimensional stability and packaging are applicable to the subject device. Testing verified that the accuracy and performance of the system is adequate to perform as intended. The stability of the device placement, surgical technique, intended use and functional elements of the subject device are the same as that of the predicate device of Materialise Shoulder System™ K241143 and previously cleared devices... therefore previous simulated surgeries using rapid prototyped bone models and previous cadaver testing on previously cleared devices K153602 and K131559 are considered applicable to the subject device." (Page 10)

Given this, I cannot provide detailed answers to many of your questions as the submission relies on the substantial equivalence principle and prior testing rather than new, extensive performance studies for AI/ML.

However, I can extract what is available:

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

The document does not provide a specific table of quantitative acceptance criteria and reported device performance for the current submission (K242813), as it relies on the previous clearance and the assessment that the changes (adding implant compatibility) do not raise new safety or effectiveness concerns.

The general acceptance criterion mentioned is that the "accuracy and performance of the system is adequate to perform as intended." This was verified through previous testing, including "simulated surgeries using rapid prototyped bone models and previous cadaver testing."

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 mentions "previous simulated surgeries using rapid prototyped bone models and previous cadaver testing on previously cleared devices K153602 and K131559." It does not specify the sample size for these tests, nor the country of origin of the data or whether it was retrospective or prospective.

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

This information is not provided in the document.

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

This information is not provided in the document.

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 such MRMC study is mentioned. The device is a "pre-surgical planner" and "surgical instrument" designed to assist the surgeon, but the provided text does not detail comparative effectiveness studies of human readers (surgeons) with and without the AI (planning software) assistance.

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

The software (SurgiCase Shoulder Planner) generates a pre-surgical plan which the "qualified surgeon" can "visualize, measure, reconstruct, annotate, edit and approve" (Page 9). This indicates a human-in-the-loop process. Standalone performance of the algorithm without human interaction is not discussed as it's not the intended use.

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

The document generally refers to "verification against defined requirements, and validation against user needs" and "accuracy and performance of the system is adequate to perform as intended" based on "simulated surgeries using rapid prototyped bone models and previous cadaver testing." This suggests a ground truth established through expert-defined surgical planning parameters and comparison to physical outcomes in the simulated/cadaveric environment, but specifics on how this ground truth was formalized (e.g., expert consensus on optimal planning, precise measurement validation) are not detailed.

8. The sample size for the training set

This device is a surgical planning tool and guides, not a deep learning AI model that requires a "training set" in the conventional sense for image classification or similar tasks. It is based on algorithms that process CT-imaging scans and anatomical landmarks to generate personalized plans and guides. Therefore, the concept of a "training set" for AI/ML is not applicable here in the way it would be for a pattern recognition AI. The software's robustness and accuracy are likely validated through extensive testing against various patient anatomies and surgical scenarios.

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

As explained above, the concept of a training set as typically understood for AI/ML models is not directly applicable to this device based on the provided information.

Ask a specific question about this device

Hardware:
The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.
The Materialise Shoulder Guide and Models are single use only.
The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

• DePuy Synthes'
• GLOBAL® APG+ Shoulder System (K052472)
• DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077, K203694)
• GLOBAL® STEPTECH® APG Shoulder System (K092122)
• INHANCE™ Anatomic Shoulder System (K202716)1
• INHANCE™ Reverse Shoulder System (K212737)
• INHANCE Hybrid Anatomic Glenoid Implant (K212933)
• INHANCE Reverse Glenoid Peripheral Posts (K221467)
• Enovis'2 (DJO)
• Reverse® Shoulder Prosthesis (K051075, K111629, K092873)
• Turon® Shoulder System (K080402)
• AltiVate™ Anatomic Shoulder System (K162024)
• AltiVate™ Anatomic Augmented Glenoid (K213387)
• Smith+Nephew's3
• Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)
• Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• AETOS Total Shoulder System (K220847, K230572)
• AETOS Reverse Shoulder System (K220847, K230572)
• Lima's
• SMR™ Shoulder System (K100858)
• SMR™ Reverse Shoulder System (K110598)
• SMR™ Modular Glenoid (K113254) (K143256)
• SMR™ 3-Pegs Glenoid (K130642)
• SMR™ TT Metal Back Glenoid (K133349)
• SMR™ 40mm Glenosphere (K142139)
• SMR™ TT Augmented 360 Baseplate (K220792)
• SMR™ TT Hybrid Glenoid (K220792)
• PRIMA TT Glenoid (K222427)

Software:
SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

• a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient.
• Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

The provided text describes a 510(k) submission for the Materialise Shoulder System™, Materialise Shoulder Guide and Models, and SurgiCase Shoulder Planner. It indicates that this is a special 510(k) submission, meaning it's for a modification to a previously cleared device. Therefore, much of the performance data refers back to the predicate device and prior clearances.

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

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

The document does not explicitly state quantitative acceptance criteria or a direct table showing "acceptance criteria vs. reported device performance" for this specific 510(k) submission. Instead, for this special 510(k), the performance data mainly focuses on demonstrating that the changes (addition of new implant components to the software and hardware compatibility) do not raise new questions of safety and effectiveness compared to the predicate device.

The "performance data (non-clinical)" section highlights that:

• Hardware: Previous testing for biocompatibility, cleaning, debris, dimensional stability, and packaging is applicable. Accuracy and performance of the system were "adequate to perform as intended." Previous simulated surgeries and cadaver testing on earlier cleared devices are considered applicable.
• Software: Software verification and validation were performed "against defined requirements" and "against user needs," following FDA guidance.

Since this is a special 510(k) for an incremental change (adding compatibility with specific new implants), it's implied that the acceptance criteria are met if these additions do not negatively impact the established safety and effectiveness of the existing device, and the software development process meets regulatory standards.

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

• Hardware (previous testing cited): The document mentions "previous simulated surgeries using rapid prototyped bone models" and "previous cadaver testing on previously cleared devices K153602 and K131559." It does not specify the sample size for these previous studies (e.g., number of bone models or cadavers) or their provenance (country of origin), nor does it state if they were retrospective or prospective.
• Software (verification and validation): The document states "Software verification and validation were performed," but does not specify a separate "test set" in the context of clinical data or specific performance metrics with sample sizes for this particular submission. The V&V activities would involve testing against requirements and user needs, which could include various test cases and scenarios, but these are not quantified here as a "test set" size.

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 information is not provided in the document. The studies cited for hardware ("simulated surgeries" and "cadaver testing") and software ("verification and validation") do not detail the involvement of experts in establishing ground truth, their number, or specific qualifications. The software's function is to assist surgeons in planning, implying surgeon input in its use, but not explicitly in establishing a ground truth for a test set described in this submission.

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

This information is not provided in the document.

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

The document does not mention any MRMC comparative effectiveness studies. The device (SurgiCase Shoulder Planner software component and Materialise Shoulder Guide and Models hardware component) is designed to assist surgeons in planning and component positioning, but the provided text does not contain data on whether human readers/surgeons improve with or without this specific AI assistance or effect sizes.

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

The document states that the SurgiCase Shoulder Planner is "intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components." It also mentions, "SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data." This indicates that the software is a human-in-the-loop device, where the surgeon is actively involved in the planning process and responsible for approving the plan. Therefore, a standalone (algorithm only) performance assessment, without human input, is unlikely to be the primary method of evaluation described or required for this type of device. The document does not provide such standalone performance data.

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

The document does not explicitly state the type of ground truth used for any specific test set related to this submission. For the hardware (guides and models), the "accuracy and performance" implies a comparison to a known standard or ideal, perhaps derived from anatomical models or surgical goals. For the software, "verification against defined requirements, and validation against user needs" suggests that the ground truth for V&V would be the successful adherence to these requirements and user expectations, which could involve internal expert review or adherence to pre-defined medical/engineering specifications. However, specific types of ground truth like pathology or long-term outcomes data are not mentioned.

8. The sample size for the training set

This information is not provided in the document. As the submission is for a special 510(k) updating compatibility, it's possible that the core algorithms were developed and trained previously, and details of their original training are not part of this specific submission. The focus here is on the impact of the changes to the device.

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

This information is not provided in the document. Similar to the training set size, the specifics of how the ground truth was established for the original training of any underlying algorithms are not included in this special 510(k).

Ask a specific question about this device

Hardware: The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans. The Materialise Shoulder Guide and Models are single use only. The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components: DePuy Synthes', Enovis' (DJO), Smith+Nephew's, Lima's, Stryker's.

Software: SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following: a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient. Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

The provided text describes the regulatory clearance for the Materialise Shoulder System™ and mentions performance data, but it does not contain a detailed study proving the device meets specific acceptance criteria in the format requested.

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting a comprehensive standalone study with detailed effectiveness metrics.

Here's an analysis of the information that can be extracted, and what is missing based on your request:

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: Not explicitly stated in a quantitative manner for the performance of the AI component (SurgiCase Shoulder Planner) or the hardware (Materialise Shoulder Guide and Models) beyond ensuring it performs "as intended" and maintains accuracy.
• Reported Device Performance: The document states that "Testing verified that the accuracy and performance of the system is adequate to perform as intended." However, no specific performance metrics (e.g., accuracy, precision, sensitivity, specificity, or error margins) are provided for either the software for planning or the hardware for guiding.

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

• Test Set Sample Size: Not specified for the software component (SurgiCase Shoulder Planner).
• Data Provenance: Not specified for any software testing.
• For Hardware: It refers to "simulated surgeries using rapid prototyped bone models and previous cadaver testing." No specific number of models or cadavers is provided, nor is the country of origin or whether it was retrospective or prospective.

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

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

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

• Not specified.

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

• No MRMC study is mentioned. The document focuses on the planning and guidance aspect for surgeons, but not on a comparative study of human readers (surgeons) with and without AI assistance for diagnosis or planning accuracy.

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

• A standalone performance evaluation of the software's planning functionality is implied through the statement "Software verification and validation were performed, and documentation was provided following the 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'" However, no specific metrics or study details are provided. The software is described as a "planning tool used to generate a pre-surgical plan" and for "assisting the surgeon in positioning shoulder components," suggesting a human-in-the-loop workflow.

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

• Ground Truth Type: Not explicitly stated for the software. For the hardware, the use of "rapid prototyped bone models and previous cadaver testing" implies a physical ground truth for accuracy validation.

8. The sample size for the training set:

• The document does not mention a training set sample size, which is typical for AI/ML models. This suggests the software functionality described (planning, visualization, measurement) might not be based on deep learning/machine learning that requires explicit training data in the same way as, for example, an image classification algorithm. It seems to be a rules-based or physics-based planning software.

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

• As no training set is mentioned, the method for establishing its ground truth is also not provided.

In summary:

The provided text from the FDA 510(k) summary states that non-clinical performance testing indicates the device is as safe and effective as its predicate. It mentions software verification and validation and previous hardware testing (biocompatibility, sterility, cleaning, debris, dimensional stability, packaging, simulated surgeries, cadaver testing). However, it lacks the specific quantitative acceptance criteria and detailed study results (such as sample sizes, expert qualifications, clear performance metrics, ground truth establishment for software, and formal comparative effectiveness study results) that are typically expected when describing a study proving specific acceptance criteria in detail. This information is usually found in separate, more detailed technical documentation submitted to the FDA, not in the public 510(k) summary.

Ask a specific question about this device

Hardware:
The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.
The Materialise Shoulder Guide and Models are single use only.
The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

• Depuy Synthes'
• GLOBAL® APG+ Shoulder System (K052472)
• DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077, K203694)
• GLOBAL® STEPTECH® APG Shoulder System (K092122)
• INHANCE™ Anatomic Shoulder System (K202716)1
• INHANCE™ Reverse Shoulder System (K212737)
• Enovis'2 (DJO)
• Reverse® Shoulder Prosthesis (K051075, K111629, K092873)
• Turon® Shoulder System (K080402)
• AltiVate™ Anatomic Shoulder System (K162024)
• AltiVate™ Anatomic Augmented Glenoid (K213387)
• Smith+Nephew's 3
• Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)
• Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• Lima's
• SMR™ Shoulder System (K100858)
• SMRTM Reverse Shoulder System (K110598)
• SMRTM Modular Glenoid (K113254) (K143256)
• SMR™ 3-Pegs Glenoid (K130642)
• SMR™ TT Metal Back Glenoid (K133349)
• SMRTM 40mm Glenosphere (K142139)
• SMRTM TT Augmented 360 Baseplate (K220792)
• SMR™ TT Hybrid Glenoid (K220792)
• Stryker's
• ReUnion RSA Reverse Shoulder System (K183039)
• Reunion TSA Total Shoulder Arthroplasty System (K183039)

Software:
SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

• a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient.
• Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patientspecific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the preoperative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

This document is a 510(k) premarket notification for the Materialise Shoulder System™, Materialise Shoulder Guide and Models, and SurgiCase Shoulder Planner. It asserts substantial equivalence to a previously cleared predicate device (K220452).

The provided text does not contain detailed acceptance criteria or the specific study that proves the device meets those criteria for the software component (SurgiCase Shoulder Planner) in the context of AI/ML performance metrics.

The document primarily focuses on demonstrating substantial equivalence based on:

• Intended Use: The device is a patient-specific medical device to assist in shoulder component placement during total anatomic and reverse shoulder replacement surgery. The software component, SurgiCase Shoulder Planner, is a pre-surgical planner for simulation and assistance in positioning shoulder components.
• Technological Characteristics: The subject device has similar fundamental technologies, device functionality, and software technology (same code base, design, verification, and validation methods) as the predicate device.
• Performance Data (Non-Clinical):
  • Hardware: States previous testing for biocompatibility, cleaning, debris, dimensional stability, and packaging are applicable and demonstrate substantial equivalence. Mentions testing verified accuracy and performance, and applicability of simulated surgeries and cadaver testing from previous clearances.
  • Software: States that "Software verification and validation were performed, and documentation was provided following the 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.' This includes verification against defined requirements, and validation against user needs."

Therefore, it is not possible to extract the requested information regarding AI/ML-specific acceptance criteria and performance study details from this document. The document describes a traditional 510(k) clearance process, not one with specific AI/ML performance metrics as would be expected for an AI-driven diagnostic or prognostic device. The software "assists" in planning and visualization, it does not appear to perform automated diagnostic or prognostic functions for which detailed performance metrics (like sensitivity, specificity, AUC) would typically be required for FDA clearance.

Based on the provided text, I can only provide the following information as much as possible:

1. A table of acceptance criteria and the reported device performance:
* Acceptance Criteria: Not explicitly stated in the document in terms of quantitative performance metrics for the software's "assistance" function. The acceptance criteria seem to be related to demonstrating substantial equivalence in intended use, technological characteristics, and non-clinical performance (including verification and validation against defined requirements and user needs for the software).
* Reported Device Performance:
* Hardware: "Testing verified that the accuracy and performance of the system is adequate to perform as intended." No quantitative metrics are provided.
* Software: "Software verification and validation were performed... This includes verification against defined requirements, and validation against user needs." No quantitative metrics are provided. The document highlights that the software technology differences (addition of one implant component, easier visualization of muscle elongation) "do not affect the safety or effectiveness, or that they do not raise any new issues regarding to the safety and effectiveness compared to the predicate device."

2. Sample size used for the test set and the data provenance:
* Sample Size: Not specified for software performance validation.
* Data Provenance: Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
* Not specified. The software is a planning tool to which a surgeon provides input and approves. Ground truth in the context of AI/ML models (e.g., for diagnosis) is not applicable here as the software's function is not a diagnostic one based on the description.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
* Not applicable as no such study is described for the software.

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 described. The software's role is described as assisting in planning and visualization, not as an AI providing interpretations that would be compared to human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
* Not applicable. The software is explicitly described as a "pre-surgical planner" that "allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data." It's a human-in-the-loop system for planning, not a standalone diagnostic algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
* Not applicable in the AI/ML diagnostic sense. The "ground truth" for the software's functionality would be its adherence to specified design requirements and user needs, ensuring it accurately represents anatomical structures and allows for proper planning as intended, rather than a clinical ground truth for a diagnostic output.

8. The sample size for the training set:
* Not specified. The document does not describe a machine learning model that would require a distinct training set in the conventional sense. The "training" for such software would typically involve its development and internal testing against requirements.

9. How the ground truth for the training set was established:
* Not applicable, as no external training set with established ground truth (e.g., clinical labels) is mentioned for a machine learning model.

Ask a specific question about this device

Hardware: The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans. The Materialise Shoulder Guide and Models are single use only. The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components: Depuy Synthes', DJO's, Smith+Nephew's, Lima's, Stryker's.

Software: SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following: a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient. Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graftspace between implant and bone, based on the pre-operative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

The provided text is a 510(k) summary for the Materialise Shoulder System™, which includes the Materialise Shoulder Guide and Models (hardware) and the SurgiCase Shoulder Planner (software). This submission is for an extension of compatibility with additional Lima's Implant components, not a new device requiring a full de novo performance study. Therefore, the information regarding acceptance criteria and performance studies is limited and focuses on showing equivalence to the predicate device.

Here's an analysis based on the provided text, highlighting what is (and isn't) present:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes the performance data in a qualitative manner, emphasizing equivalence to the predicate and existing testing. It does not provide a quantitative table of specific acceptance criteria (e.g., in terms of accuracy metrics, sensitivity, specificity) and corresponding performance outcomes for the newly added functionalities. Instead, it relies on the established performance of the predicate and the assertion that the changes do not affect safety or effectiveness.

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

• Software Validation: The document states that "Software verification and validation were performed, and documentation was provided following the 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'" However, it does not specify the sample size used for the test set (number of cases/patients) or the data provenance (e.g., country of origin, retrospective/prospective). The validation is described as "verification against defined requirements, and validation against user needs," but no details on the specific data used for this validation are provided in this summary.
• Hardware Testing: For hardware, it mentions "simulated surgeries using rapid prototyped bone models and previous cadaver testing on previously cleared devices K153602 and K131559." Again, sample sizes (e.g., number of models or cadavers) are not provided. The data provenance is implied to be from previous testing of predicate/cleared devices, but no specific details are given.

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

This information is not provided in the document. Given that the submission focuses on substantial equivalence for an expanded compatibility, explicit ground truth establishment by experts for specific new performance metrics is not detailed. The "approved glenoid pre-surgical plan" by a "qualified surgeon" for generating guides suggests expert involvement in the planning process, but not in a formal ground truth assessment for a test set.

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

This information is not provided. As no formal multi-reader ground truth establishment is described for a test set, an adjudication method would not be applicable in the context of the information given.

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 mentioned. The device is a surgical planning tool and patient-specific instrumentation, not an AI diagnostic aid for human readers in the traditional sense. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this device's stated purpose and is not included in the submission summary.

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

• The software component, SurgiCase Shoulder Planner, is described as assisting in the positioning of shoulder components and allowing the surgeon to "visualize, measure, reconstruct, annotate and edit pre-surgical plan data." The output is a "pre-surgical plan data file." This indicates a human-in-the-loop process where the surgeon interacts with and approves the plan.
• While software verification and validation were performed, the summary does not explicitly describe a "standalone" performance study of the algorithm only in isolation from human interaction for clinical decision-making. Its function is to facilitate human planning, not replace it.

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

• For the software, the ground truth for validation is implied to be against "defined requirements" and "user needs," which likely translates to the accuracy of planned measurements or component placements compared to a reference standard (e.g., expert-defined ideal parameters, possibly based on anatomical landmarks from CT images). However, the specific type of ground truth (e.g., expert consensus on optimal placement on a gold standard model) is not explicitly stated as pathology or outcomes data.
• For the hardware, "simulated surgeries using rapid prototyped bone models and previous cadaver testing" would involve assessing the accuracy of guide placement and the resulting pin positioning relative to the pre-surgical plan. The "ground truth" here would thus be defined by the pre-surgical plan itself and the anatomical accuracy of the physical model/cadaver.

8. The sample size for the training set:

• The document is a 510(k) summary for a substantial equivalence claim, primarily for extending compatibility. It describes software "design and verification and validation," implying a traditional software development lifecycle. It does not mention a training set in the context of machine learning or AI models, as this is not presented as an AI-driven device with a learning component.

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

• As no training set for a machine learning model is mentioned, this information is not applicable/provided.

Ask a specific question about this device

The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.

The Materialise Shoulder Guide and Models are single use only.

The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

• Depuy Synthes'
  • GLOBAL® APG+ Shoulder System (K052472)
  • DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077, K203694)
  • GLOBAL® STEPTECH® APG Shoulder System (K092122)
  • INHANCETM Anatomic Shoulder System (K202716)
  • INHANCE™ Reverse Shoulder System (K212737)
• DJO's
  • Reverse® Shoulder Prosthesis (K051075, K111629, K092873)
  • Turon® Shoulder System (K080402)
  • AltiVate™ Anatomic Shoulder System (K162024)
• Smith & Nephew's
  • Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)
  • Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• Lima's
  • SMRTM Shoulder System (K100858)
  • SMRTM Reverse Shoulder System (K110598)
  • SMRTM Modular Glenoid (K113254) (K143256)
  • SMR™ 3-Pegs Glenoid (K130642)
  • SMRTM TT Metal Back Glenoid (K133349)
  • SMR™ 40mm Glenosphere (K142139)
• Stryker's .
  • ReUnion RSA Reverse Shoulder System (K183039)
  • Reunion TSA Total Shoulder Arthroplasty System (K183039)

SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

a software component, branded as SurgiCase Shoulder Planner. This software is . a planning tool used to generate a pre-surgical plan for a specific patient.

Materialise Shoulder Guide and Models, which are a patient-specific quide and . models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific quides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft model serves as a visual reference for the surgeon in the OR.

I am sorry, but the provided text primarily consists of an FDA 510(k) clearance letter and summary for the Materialise Shoulder System. While it describes the device, its indications for use, and technological characteristics compared to a predicate device, crucial details regarding the acceptance criteria and the study proving the device meets those criteria (such as specific performance metrics, sample sizes for test sets, ground truth establishment, or clinical study designs like MRMC studies) are not present in the provided document.

The "Performance Data (non-clinical)" section briefly mentions software verification and validation, but it does not provide the specific "acceptance criteria" for performance or the details of the "study that proves the device meets the acceptance criteria" in the format requested. It mainly relies on demonstrating substantial equivalence to a predicate device based on similar technology and previous testing.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study proving the device meets them using only the information given in the input text. The information required for the table and the detailed study description is simply not provided in this regulatory document.

Ask a specific question about this device

SurgiCase Viewer is intended to be used as a software interface to assist in visualization of treatment options.

SurgiCase Viewer provides functionality to allow visualization of 3D data and to perform measurements on these 3D data, which should allow a clinician to evaluate and communicate about treatment options.

SurgiCase Viewer is intended for use by people active in the medical sector. When used to review and validate treatment options, SurgiCase Viewer is intended to be used in conjunction with other diagnostic tools and expert clinical judgment.

The SurgiCase Viewer can be used by a medical device/service manufacturer/provider or hospital department to visualize 3D data during the manufacturing process of the product/service to the end-user who is ordering the device/service. This allows the end-user to evaluate and provide feedback on proposals or intermediate steps in the manufacturing of the device or service.

The SurgiCase Viewer is to be integrated with an online Medical Device Data System which is used to process the medical device or service and which is responsible for case management, user management, authorization, authentication, etc.

The data visualized in the SurgiCase Viewer is controlled by the medical device manufacturer using the SurgiCase Viewer in its process. The Device manufacturer will create the 3D data to be visualized to the end-user and export it to one of the dedicated formats supported by the SurgiCase Viewer. Each of these formats describe the 3D data in STL format with additional meta-data on the 3D models. The SurgiCase Viewer does not alter the 3D data it imports and its functioning is independent of the specific medical indication/situation or product/service it is used for. It's the responsibility of the Medical device company using the SurgiCase Viewer to comply with the applicable medical device regulations.

The provided text describes the 510(k) submission for the "SurgiCase Viewer" device (K213684). However, it does not contain the specific details required to fully address all parts of your request related to acceptance criteria, test set specifics, expert ground truth establishment, MRMC studies, or training set details. This document primarily focuses on demonstrating substantial equivalence to a predicate device.

The study presented here is a non-clinical performance evaluation comparing the new SurgiCase Viewer with its predicate (K170419) and a secondary reference device (K183105).

Here's a breakdown of what can be extracted and what is missing, based on your questions:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with numerical performance metrics. Instead, it states that the device was validated to determine substantial equivalence based on:

• Intended Use: "Both the subject device as well as the predicate device have the same intended use; They are both intended to be used as a software interface to assist in visualization and communication of treatment options."
• Device Functionality: The new device was compared to the predicate in terms of features like 3D view navigation, visualization options, measuring, and annotations. For new functionalities (medical image visualization, VR visualization), it states "The abovementioned technological differences do not impact the safety and effectiveness of the subject device for the proposed intended use as is demonstrated by the verification and validation plan."
• Medical Images Functionality (compared to Mimics Medical K183105): "Both functionality produce the same results in: Contrast adjustments, Interactive image reslicing, 3D contour overlay on images."
• Measurement functionality: "Measurement functionality on images was compared with already existing functionality on the 3D models and shown to provide correct results both on images and 3D."

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

• Sample Size: Not explicitly stated. The document refers to "verification and validation" and "performance testing" but does not provide details on the number of cases or images used in these tests.
• Data Provenance: Not explicitly stated (e.g., country of origin). It refers to "medical images functionality" and "3D models" but doesn't specify if these were from retrospective patient data, simulated data, etc. The study is described as "non-clinical testing."

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

• Experts: Not explicitly stated. The validation involved "end-users," but their specific number, roles, or qualifications are not provided.
• Ground Truth Establishment: Not explicitly detailed. The comparison against the predicate and reference device functionalities implies that their established performance served as a form of "ground truth" for the new device's functions.

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

• Not explicitly stated. There is no mention of a formal reader adjudication process.

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 study described. This submission focuses on the device's substantial equivalence in functionality and safety, not on human reader performance improvement with AI assistance. The device's stated indication is "to assist in visualization of treatment options," implying a tool for clinicians, but not an AI-driven diagnostic aid that would typically undergo MRMC studies.

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

• The context suggests a standalone functional assessment of the software's capabilities (e.g., whether it correctly performs contrast adjustments, measurement calculations, etc.) in comparison to the predicate and reference device. It's not an AI algorithm with a distinct "performance" metric like sensitivity/specificity, but rather a functional software application.

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

• For the functional comparison: The "ground truth" seems to be the established, correct functioning of the predicate and reference devices for equivalent features, and the defined requirements for new features. For instance, if the Mimics Medical device correctly performs "contrast adjustments," the SurgiCase Viewer needs to produce the "same results." For measurements, it needs to provide "correct results." This isn't a traditional clinical ground truth like pathology for a diagnostic AI.

8. The sample size for the training set:

• Not applicable / Not mentioned. This device description does not indicate the use of machine learning or AI models that require a "training set" in the conventional sense. It's described as a software interface for visualization and measurements.

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

• Not applicable. (See point 8).

In summary, the provided document demonstrates that the SurgiCase Viewer is substantially equivalent to existing cleared devices based on a functional and software validation process. It assures that new functionalities do not negatively impact safety or effectiveness and that shared functionalities perform comparably. However, it does not detail the type of rigorous clinical performance study (e.g., with patient data, expert readers, and quantitative statistical metrics) that would be common for AI/ML-driven diagnostic devices.

Ask a specific question about this device

The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.

The Materialise Shoulder Guide and Models are single use only.

The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

· Depuy Synthes'
o GLOBAL® APG+ Shoulder System (K052472),
o DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077, K203694)
o GLOBAL® STEPTECH® APG Shoulder System (K092122)
o Ignite Anatomic Shoulder System (K202716) (rebranded to INHANCE™ Anatomic Shoulder System))
• DJO's
o Reverse® Shoulder Prosthesis (K051075, K111629, K092873),
o Turon® Shoulder System (K080402)
o AltiVate™ Anatomic Shoulder System (K162024)
· Smith & Nephew's (Integra's)2
o Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)
o Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• Lima's
o SMRTM Shoulder System (K100858),
o SMRTM Reverse Shoulder System (K110598),
o SMR™ Modular Glenoid (K113254) (K143256),

• o SMR™ 3-Pegs Glenoid (K130642),
  o SMR™ TT Metal Back Glenoid (K133349),
• o SMRTM 40mm Glenosphere (K142139).
  · Stryker's
  o ReUnion RSA Reverse Shoulder System (K183039)
  o Reunion TSA Total Shoulder Arthroplasty System (K183039).

Surgicase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System™ is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

• a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient.
• Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft serves as a visual reference for the surgeon in the OR.

The Materialise Shoulder Guide and Models must only be used within the intended use of the compatible components.

The provided text is a 510(k) summary from the FDA for a medical device called the "Materialise Shoulder System™". While it describes the device, its intended use, and states that non-clinical performance data indicates substantial equivalence to a predicate device, it does not contain the specific details required to answer all parts of your request regarding acceptance criteria and a study proving device performance.

Here's an analysis of what can be extracted and what is missing:

What's Available:

• Device Name: Materialise Shoulder System™, Materialise Shoulder Guide and Models, SurgiCase Shoulder Planner
• Purpose of the "Study": The document focuses on demonstrating substantial equivalence to a predicate device (K193560), rather than a specific clinical study with defined acceptance criteria for novel claims. The performance data presented are primarily non-clinical tests to support this substantial equivalence.
• Type of Ground Truth: For the "Hardware," it mentions "simulated surgeries using rapid prototyped bone models and previous cadaver testing." For the "Software," it mentions "Software verification and validation were performed and documentation was provided following the 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'" This implies validation against defined requirements and user needs, but not necessarily a clinical ground truth like pathology or outcomes data.
• Data Provenance (Implied): The company, Materialise N.V., is based in Belgium. The non-clinical tests mentioned would likely have been conducted by or for the manufacturer. The previous cadaver testing would likely have been retrospective or specifically for previous clearances.

What's Missing (and why based on the document type):

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device. For this type of submission, extensive clinical studies with new acceptance criteria, expert adjudication, MRMC studies, or large training datasets for AI (if applicable, though this device seems more rule-based/software-assisted planning) are often not required if substantial equivalence can be demonstrated through non-clinical means and comparison to established predicate devices.

Therefore, the following information is not provided in the document:

1. A table of acceptance criteria and the reported device performance: The document states that testing "verified that the accuracy and performance of the system is adequate to perform as intended" and that the subject device "is as safe, as effective, and performs as well as the predicate device," but it does

Ask a specific question about this device

Hardware:

The Materialise Shoulder Guide and Models are intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans.

The Materialise Shoulder Guide and Models are single use only.

The Materialise Shoulder Guide and Models can be used in conjunction with the following total and reverse shoulder implants systems and their respective compatible components:

· Depuy Synthes'

• o GLOBAL® APG+ Shoulder System (K052472),
• o DELTA XTEND™ Reverse Shoulder System (K120174, K062250, K183077)
• o GLOBAL® STEPTECH® APG Shoulder System (K092122).

• DJO's

• o Reverse® Shoulder Prosthesis (K051075, K111629, K092873).
• o Turon® Shoulder System (K080402)
• o AltiVate™ Anatomic Shoulder System (K162024)
• · Integra's

o Titan™ Total Shoulder System (K100448, K112438, K142413, K152047)

• o Titan™ Reverse Shoulder System (K130050, K161189, K173717, K181999)
• Lima's
  • o SMRTM Shoulder System (K100858),
  • o SMRTM Reverse Shoulder System (K110598),
  • o SMRTM Modular Glenoid (K113254) (K143256),
  • o SMR™ 3-Pegs Glenoid (K130642),
  • o SMR™ TT Metal Back Glenoid (K133349),
  • o SMRTM 40mm Glenosphere (K142139).

· Stryker's

• o ReUnion RSA Reverse Shoulder System (K183039)
• o Reunion TSA Total Shoulder Arthroplasty System (K183039).

Software:

SurgiCase Shoulder Planner is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder orthopedic surgery. The software is used to assist in the positioning of shoulder components. SurgiCase Shoulder Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The software leads to the generation of a surgery report along with a pre-surgical plan data file which can be used as input data to design the Materialise Shoulder Guide and Models.

Materialise Shoulder System is a patient-specific medical device that is designed to be used to assist the surgeon in the placement of shoulder components during total anatomic and reverse shoulder replacement surgery. This can be done by generating a pre-surgical shoulder plan and, if requested by the surgeon, by manufacturing a patient-specific glenoid guide and models to transfer the glenoid plan to surgery. The device is a system composed of the following:

• a software component, branded as SurgiCase Shoulder Planner. This software is a planning tool used to generate a pre-surgical plan for a specific patient.
• Materialise Shoulder Guide and Models, which are a patient-specific guide and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Patient-specific glenoid guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the glenoid plan to surgery. The Materialise Shoulder Guide is designed and manufactured to fit the anatomy of a specific patient. A bone model of the scapula is delivered with the Materialise Shoulder Guide. A graft model can be delivered with the Materialise Shoulder Guide. The graft model visualizes the graft-space between implant and bone, based on the pre-operative planning of the surgeon. The graft serves as a visual reference for the surgeon in the OR.

The Materialise Shoulder Guide and Models must only be used within the intended use of the compatible components.

The provided text does not contain detailed acceptance criteria or a specific study that proves the device meets those criteria in a quantitative research sense. The document is a 510(k) premarket notification summary from the FDA, focusing on demonstrating substantial equivalence to a predicate device rather than presenting formal study results against predefined acceptance metrics.

However, based on the information provided, we can infer some "acceptance criteria" through the lens of substantial equivalence and list reported device performance related to this equivalence.

Here's an attempt to extract and frame the information according to your request, acknowledging the limitations of the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

Since explicit numerical acceptance criteria are not stated, we will infer them based on the substantial equivalence argument made by the manufacturer. The reported performance is based on the claim of similarity to the predicate device and the results of verification and validation activities mentioned.

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

The document mentions "previous simulated surgeries using rapid prototyped bone models and previous cadaver testing on previously cleared devices K153602 and K131559" which are considered applicable to the current device. However, no specific sample sizes (number of bone models or cadavers) for these tests are provided in this summary.

The provenance of this data (e.g., country of origin, retrospective/prospective) is not explicitly stated. It can be inferred that these were laboratory-based tests conducted typically by the manufacturer or a third-party testing facility.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth in the context of the simulated surgeries or cadaver testing. The software validation involved "validation against user needs," implying input from intended users (surgeons), but the details are absent.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method used for evaluating the performance of the device in the context of the "simulated surgeries" or "cadaver testing."

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

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study is mentioned in the provided text. The submission focuses on substantial equivalence based on technological similarity and prior testing, not on human reader performance improvement with AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

The software component, "SurgiCase Shoulder Planner," is a planning tool that assists a surgeon. It "allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data." This implies a continuous "human-in-the-loop" interaction for final plan approval. While software verification and validation were performed, the reported performance is within the context of assisting a surgeon, not as a standalone diagnostic or treatment decision-making algorithm. Therefore, a purely standalone (algorithm only without human-in-the-loop performance) study is not explicitly described or claimed. The software verification and validation would involve assessing the algorithm's output accuracy against its intended function (e.g., measurements, reconstructions), but this is not directly presented as "standalone performance" in the clinical decision-making sense.

7. The Type of Ground Truth Used

For the hardware (guidance system), the ground truth for "accuracy and performance" would likely be established through:

• Measurement against physical standards: For dimensional accuracy.
• Intraoperative positioning verification: During simulated surgeries or cadaver tests, assessing how well the guide facilitates the intended pin placement relative to anatomical landmarks. This would be a technical ground truth based on the precision of the physical guides.

For the software (SurgiCase Shoulder Planner), the ground truth for "validation against user needs" would likely involve:

• Expert Consensus/Clinical Expertise: Surgeons reviewing the generated plans, measurements, and reconstructions against their professional judgment and potentially 3D models or other imaging data to deem them clinically acceptable and accurate. This would involve expert consensus on the correctness of the planning outputs.

8. The Sample Size for the Training Set

The document describes premarket notification for a medical device cleared via substantial equivalence, not an AI/ML algorithm that undergoes explicit "training." While the software component has a "code base," it is described as using "exactly the same methods for design and verification and validation as the predicate device" rather than being a deep learning model trained on a dataset. Therefore, the concept of a "training set" in the context of machine learning does not apply as described in this document.

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

As the concept of a "training set" for a machine learning model is not applicable here, the question of how its ground truth was established is not relevant to this document. The software's "ground truth" (i.e., correctness of its functions and outputs) is established through traditional software verification and validation against defined requirements and user needs, as mentioned in point 7.

Ask a specific question about this device

SurgiCase Viewer is intended to be used as a software interface to assist in visualization and communication of treatment options.

SurgiCase Viewer provides functionality to visualize 3D data and to perform measurements on these 3D data, which should allow a clinician to evaluate and communicate about treatment options.

SurgiCase Viewer is intended for use by people active in the medical sector. When used to review and validate treatment options, SurgiCase Viewer is intended to be used in conjunction with other diagnostic tools and expert clinical judgment.

The SurgiCase Viewer can be used by a medical device/service manufacturer/provider or hospital department to visualize 3D data during the manufacturing process of the end-user who is ordering the device/service. This allows the end-user to evaluate and provide feedback on proposals or intermediate steps in the manufacturing of the device or service.

The SurgiCase Viewer is to be integrated with an online Medical Device Data System which is used to process the medical device or service and which is responsible for case management, authorization, authentication, etc.

The data visualized in the SurgiCase Viewer is controlled by the medical device manufacturer using the SurgiCase Viewer in its process. The Device manufacturer will create the 3D data to the end-user and export it to one of the dedicated formats supported by the SurgiCase Viewer. Each of these formats describe the 3D data in STL format with additional meta-data on the 3D models. The SurgiCase Viewer does not alter the 3D data it imports and its functioning is independent of the specific medical indication or product/service it is used for. It's the responsibility of the Medical device company using the SurgiCase Viewer to comply with the applicable medical device regulations.

The Materialise SurgiCase Viewer is a software interface intended for the visualization and communication of treatment options. The provided document is a 510(k) premarket notification summary, which focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed study results on specific acceptance criteria and performance metrics of the device itself.

Based on the provided text, detailed acceptance criteria and the study proving the device meets them, in the typical format of clinical or standalone performance studies, are not extensively described. The document primarily highlights its non-clinical testing for substantial equivalence.

Here's an attempt to extract and synthesize the requested information, noting where specific details are not available in 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 performance metrics like sensitivity, specificity, accuracy, or effect sizes, which are typically seen in clinical performance studies of AI/imaging devices. Instead, the "Performance Data" section refers to "Non-clinical tests" conducted to validate the application for its intended use and determine substantial equivalence.

2. Sample Size for the Test Set and Data Provenance

The document states "Non-clinical tests" were performed. However, it does not specify the sample size used for any test set (e.g., number of cases, number of 3D models). It also does not mention the data provenance (e.g., country of origin, retrospective or prospective nature) as it refers to non-clinical testing, which typically involves technical verification and validation rather than studies on patient data.

3. Number of Experts and Qualifications for Ground Truth

The document does not mention the use of experts to establish ground truth for a test set. This is consistent with its focus on non-clinical testing and substantial equivalence rather than a clinical performance evaluation against expert consensus.

4. Adjudication Method for the Test Set

As no expert ground truth or clinical test set is described, there is no mention of an adjudication method (e.g., 2+1, 3+1, none).

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

The document does not describe an MRMC comparative effectiveness study comparing human readers with and without AI assistance. Therefore, no effect size for human improvement is provided.

6. Standalone (Algorithm Only) Performance Study

The document does not present a standalone performance study in terms of typical clinical metrics (e.g., sensitivity, specificity) for the algorithm itself. The "non-clinical tests" relate to the device's functional performance and its equivalence to predicates.

7. Type of Ground Truth Used

The document does not specify a "ground truth" type in the context of expert consensus, pathology, or outcomes data. The validation described is focused on functional and performance equivalence during "non-clinical tests," implying a technical or engineering validation against specified requirements or predicate device behavior.

8. Sample Size for the Training Set

The document does not mention a training set sample size. This aligns with the description of "SurgiCase Viewer" as a software interface for visualization and measurements, suggesting it might not be a machine learning or AI algorithm that requires a traditional training set in the same way. It's more of a tool that processes and displays pre-existing 3D data.

9. How Ground Truth for the Training Set Was Established

As no training set is mentioned or implied in the context of machine learning, the document does not describe how ground truth for a training set was established.

Ask a specific question about this device