Search Results

The SMR Reverse Shoulder System is indicated for primary, fracture or revision total shoulder replacement in a grossly rotator cuff deficient joint with severe arthropathy (disabled shoulder). The patient's joint must be anatomically and structurally suited to receive the selected implants and a functional deltoid muscle is necessary to use the device.

The SMR TT Hybrid Glenoid Reverse Baseplate must not be used in cases of excessive glenoid bone loss and/or when bone graft is needed.

The Modular SMR Shoulder System allows the assembly of components in various humeral and glenoid constructs. The constructs are intended for cemented and uncemented use as specified in the following table.

In the Reverse shoulder the humeral construct consists of the humeral stem, the reverse humeral body and the reverse liner. On the humeral side the fixation of the humeral stem determines if the construct is cemented or uncemented.

The Reverse glenoid consists of a metal back/connector/glenosphere construct or of a peg/baseplate/glenosphere construct.

The subject SMR Reverse HP Shoulder System is a line extension to the predicate SMR Shoulder System (K223876) consisting of Reverse HP crosslinked UHMWPE glenospheres and Co-Cr-Mo liners. The components are available in one diameter with various options to accommodate varying patient anatomy.

Based on the provided FDA 510(k) clearance letter for the SMR Reverse HP Shoulder System, here's an analysis of the acceptance criteria and the study proving the device meets them:

It's important to note that this document is a 510(k) clearance, which is primarily a declaration of substantial equivalence to a previously cleared predicate device, rather than a full, de novo approval that would detail extensive clinical performance studies with specific statistical acceptance criteria for novel claims. The focus here is on demonstrating that the new device (SMR Reverse HP Shoulder System) is as safe and effective as existing legally marketed devices, rather than proving a new level of clinical efficacy.

Therefore, many of the specific details you've asked for, such as precise quantitative acceptance criteria for clinical performance (e.g., accuracy, sensitivity, specificity, or effect size for AI assistance), adjudication methods, or detailed expert qualifications for ground truth establishment, are typically not found in a 510(k) summary, as they are not generally required for demonstrating substantial equivalence for an orthopedic implant.

The "acceptance criteria" for a 510(k) device primarily revolve around demonstrating that the new device performs as intended and is as safe and effective as its predicate. This is primarily done through non-clinical (mechanical) testing and reference to the predicate's established clinical history.

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the SMR Reverse HP Shoulder System are implicit in the demonstration of substantial equivalence to its predicate devices. The performance testing aims to show that the new components function equivalently to, or better than, the predicate components within the intended use.

1. Table of Acceptance Criteria and Reported Device Performance

Study Proving Device Meets Acceptance Criteria

The study described is primarily a non-clinical performance study combined with a post-market clinical data review for demonstrating substantial equivalence.

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

• Test Set (Non-clinical): The document states "Mechanical testing was performed on worst case components or constructs." This implies a limited sample size based on engineering principles (e.g., statistical power calculations for specific test types or industry standards for mechanical testing). Specific numbers are not provided, as is typical for 510(k) engineering tests.
• Data Provenance (Clinical): "Post-market clinical data from outside the United States on the subject and predicate device were provided in this submission." This indicates a retrospective collection of data from clinical use, not a prospective, controlled clinical trial specifically designed for this submission. The exact country of origin within "outside the United States" is not specified, nor is the specific sample size, though it is described as "patient-level radiographs, outcome measures, and safety data."

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

• Non-clinical: Ground truth is established by engineering standards and specifications (e.g., ISO, ASTM). The "experts" would be the engineers and technicians performing and assessing the mechanical tests against these predefined standards. Their qualifications are implicit in their ability to conduct and interpret these tests, but not explicitly stated in terms terms like "mechanical engineer with 10 years experience."
• Clinical: For the post-market clinical data, the "ground truth" refers to patient outcomes and safety information. This data is observed in real-world clinical practice, typically by treating physicians. There is no mention of a separate panel of experts specifically adjudicating this post-market data for "ground truth" purposes in the context described.

4. Adjudication Method for the Test Set:

• Non-clinical: The "adjudication" is against the pre-defined engineering standards and performance specifications for each mechanical test. This is typically a pass/fail determination based on quantitative measurements. No human-expert consensus "adjudication method" (like 2+1, 3+1) is described or typically applicable to component mechanical testing.
• Clinical: For the post-market clinical data, there's no mention of an adjudication method by external experts. The data would have been collected as part of routine clinical care or existing registries, and then compiled and analyzed by the manufacturer for the submission.

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 was done. This device is an orthopedic implant, not a diagnostic imaging AI algorithm. Therefore, MRMC studies and the concept of "human readers improving with AI assistance" are not applicable to the SMR Reverse HP Shoulder System.

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

• Not applicable. As stated above, this is an orthopedic implant, not an AI algorithm.

7. The Type of Ground Truth Used:

• Non-clinical: The ground truth for mechanical testing is based on established engineering principles and international standards (ISO, ASTM) for orthopedic implants. These standards define the expected performance and limits for various mechanical properties.
• Clinical: The "ground truth" for the clinical data is real-world patient outcomes, safety events, and radiographic assessments collected during post-market use of the predicate device and the subject device (where applicable) outside the US. These are actual clinical observations rather than expert consensus on a test set.

8. The Sample Size for the Training Set:

• Not applicable for a 510(k) orthopedic implant. Training sets are relevant for machine learning algorithms. The design and validation of this mechanical implant do not involve "training sets" in this context. The "training" for the device would be the iterative design and development process, informed by biomechanical principles and material science, leading up to the final testing.

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

• Not applicable. See point 8.

In summary, the FDA 510(k) clearance for the SMR Reverse HP Shoulder System relies heavily on demonstrating engineering equivalence and material compliance through non-clinical testing, supplemented by a review of existing post-market clinical data for the predicate and related devices. It is a process focused on showing that the new device is "substantially equivalent" to an already cleared device, rather than a de novo approval process that would require extensive novel clinical efficacy studies with sophisticated statistical methodologies often seen for new drug or AI algorithm approvals.

Ask a specific question about this device

Software: The Precision AI Planning Software is intended to be used as a pre-surgical planner for simulation of surgical interventions for shoulder joint arthroplasty. The software is used to assist in the positioning of shoulder components by creating a 3D bone construct of the joint and allows the surgeon to visualize, measure, reconstruct, annotate and edit presurgical 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 Precision AI Shoulder Guide and Biomodels.

Hardware: The Precision AI Planning System Guides and Biomodels are intended to be used as patient-specific surgical instruments to assist in the intraoperative positioning of shoulder implant components used with total and reverse shoulder arthroplasty by referencing anatomic landmarks of the shoulder that are identifiable on preoperative CT-imaging scans. The Glenoid Guide is used to place the k-wire and the Humeral Guide is used to place humeral pins for humeral head resection. The Precision AI Guides and Biomodels are indicated for single use only. The Precision AI Surgical Planning System is indicated for use on adult patients that have been consented for shoulder joint arthroplasty. Both humeral and glenoid guides are suitable for a delto-pectoral approach only. The Precision AI Surgical Planning System is indicated for total and reverse shoulder arthroplasty using the following implant systems and their compatible components: Enovis and Lima.

The Precision AI Surgical Planning 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 guides and models to transfer the plan to surgery. The subject device is a system composed of the following: The Precision AI Surgical Planning System Software will create a 3D construct/render of the patient's shoulder joint for the surgeon to plan the operatively then create a physical Patient Specific Instrument (or Guide), using 3D printing by selective laser sintering. The patient's CT scan images are the design input for this to be created and are auto segmented via a locked, or static, artificial intelligence algorithm. The surgeon can visualise the deformity of the diseased joint, on this 3D render and CT scan images, and determine the inherent deformity of the joint. They are then able to virtually place the artificial implants in an optimal position to correct the measured deformity for that specific patient. The Precision AI Guides, 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 guide and models will be manufactured if the surgeon requests patient-specific guides to transfer the plan to surgery.

The provided text is an FDA 510(k) summary for the Precision AI Surgical Planning System (PAI-SPS). It describes the device and its intended use, but it does NOT contain specific acceptance criteria, detailed study designs, or performance results in terms of metrics like sensitivity, specificity, accuracy, or effect sizes for human reader improvement.

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.' This includes verification against defined requirements and validation against user needs." It also mentions that "Design verification and validation testing demonstrated that the PAI-SPS meets all design requirements and is as safe and effective as its predicate device (K233992)."

However, it does not explicitly lay out the acceptance criteria (e.g., "model must achieve 90% accuracy") or the results against those criteria. It focuses more on demonstrating substantial equivalence to a predicate device (PAI-SPS K233992) by showing that the technology and intended use are similar, with the main differences being the addition of compatibility with more implant systems.

Therefore, I cannot fully complete the requested table and answer all questions based solely on the provided text. I will provide information based on what is available and indicate where information is missing.

Description of Acceptance Criteria and Study to Prove Device Meets Criteria

Based on the provided FDA 510(k) summary, the PAI-SPS device is being cleared primarily through demonstrating substantial equivalence to an already cleared predicate device (PAI-SPS, K233992). The key claim for equivalence rests on similar intended use, fundamental scientific technology, design, functionality, operating principles, and materials, with the primary difference being expanded compatibility with additional implant systems.

The document implicitly suggests that the "acceptance criteria" are tied to demonstrating that these technological differences "do not raise any different questions of safety and effectiveness." The studies cited are primarily focused on software verification and validation, ensuring the new compatible implant systems do not negatively impact the established safety and effectiveness.

Here is a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The provided document does not explicitly state quantitative acceptance criteria (e.g., minimum accuracy percentages, specific error bounds) or detailed performance metrics. The performance is largely framed as demonstrating that the device "meets all design requirements and is as safe and effective as its predicate device."

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

• The document does not specify the sample size for any test set (e.g., for software validation or hardware accuracy).
• Data Provenance: Not explicitly stated for specific test sets. Given the company is "Precision AI Pty Ltd" in Australia, and the document discusses "previous cadaver testing and composite bone model testing," it's likely a mix of lab-based/simulated data and potentially some retrospective clinical imaging data for initial AI development/testing, but this is not detailed. The document implies that new testing was not extensively conducted for this submission, relying heavily on the predicate device's prior validation and the minor changes to compatibility.

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

• The document does not specify the number of experts or their qualifications used to establish ground truth for any test set.
• It mentions that the software allows a "qualified surgeon" to approve pre-surgical plan data, implying that expert surgical review is part of the workflow.

4. Adjudication Method for the Test Set

• The document does not specify any adjudication method (e.g., 2+1, 3+1) for establishing ground truth or evaluating test results.

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

• No, an MRMC comparative effectiveness study was not explicitly mentioned or described. The focus of this 510(k) is substantial equivalence based on technological similarity and expanded compatibility, not a comparative study against human readers or performance improvement with AI assistance.

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

• The document states that the AI algorithm performs "auto segmentation via a locked, or static, artificial intelligence algorithm." While this indicates a standalone AI component, the document does not provide standalone performance metrics for this AI segmentation. The overall system is described as a "pre-surgical planner" where the surgeon can "visualize, measure, reconstruct, annotate and edit pre-surgical plan data," suggesting a human-in-the-loop workflow.

7. The Type of Ground Truth Used

• For software, the implicit ground truth appears to be expert consensus or approved surgical plans for judging the accuracy of the software's representations and planning capabilities. The document states "The software allows a qualified surgeon to visualize, measure, reconstruct, annotate, edit and approve pre-surgical plan data."
• For hardware, "previous cadaver testing and composite bone model testing" were used, implying physical measurements against a known standard or "true" position established in these models.

8. The Sample Size for the Training Set

• The document does not specify the sample size used for the training set for the AI segmentation algorithm.

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

• The document does not specify how the ground truth for the AI training set was established. It only mentions that the AI algorithm for auto-segmentation is "locked, or static," implying it was trained previously.

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)
• 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

The SMR Stemless Anatomic is indicated for total primary or revision shoulder joint replacement in patients suffering from disability due to:

· non-inflammatory degenerative joint disease including osteoarthritis;

• revision of previous surgeries of the shoulder that do not compromise the fixation (such as a failed SMR resurfacing implant);

· glenoid arthrosis without excessive glenoid bone loss: A1, A2 and B1 according to Walch classification (SMR TT Hybrid Glenoid only).

The SMR Stemless Anatomic is intended for uncemented use.

The SMR Stemless Anatomic is a modular system comprised of a stemless core and humeral head adaptor taper. The modular components are available in various sizes and are interchangeable allowing for independent sizing and positioning. The SMR humeral heads were previously cleared (K161476, K100858), and the SMR Stemless Anatomic is compatible with the previously cleared Cemented SMR metal back Glenoid Components (K113254, K133349, K143256), Cemented SMR all polyethylene glenoid components (K100858, K130642, K153722), and SMR TT Hybrid Glenoid System (K163397).

This document is a 510(k) clearance letter from the FDA for a medical device called the "SMR Stemless Anatomic." It's not a study report of an AI/ML powered medical device, and therefore does not contain the information requested in the prompt regarding acceptance criteria, study methodologies for AI performance, sample sizes, expert qualifications, or ground truth establishment relevant to an AI/ML product.

The document discusses performance testing for a mechanical orthopedic implant, specifically a shoulder joint prosthesis, covering aspects like fatigue, micromotion, and pull-out strength. It also mentions "Clinical Data" related to the device's success in patients, comparing it to a predicate device. This is a traditional medical device clearance, not an AI/ML software as a medical device (SaMD) or AI-powered medical device.

Therefore, I cannot extract the requested information (table of acceptance criteria with AI performance, sample sizes for AI test sets, expert details for AI ground truth, MRMC studies, etc.) from this document. The concepts and methodologies described in the prompt are specific to the evaluation and clearance of AI/ML-driven medical devices, which this document does not concern.

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

General indications: The LINK Embrace Shoulder System - Reverse Configuration is intended for reverse total shoulder arthroplasty.

Indications: Primary, fracture, or revision total shoulder arthroplasty in a grossly rotator cuff deficient joint with severe arthropathy. A functional deltoid muscle is necessary, and the patient's joint must be anatomically suited to receive the implants.

The Reverse Glenoid Baseplate component is intended for cementless fixation with the addition of bone screws.

The Humeral Stems Standard with CaP (HX) and Short with CaP (HX) are intended for cementless fixation.

The Humeral Stems Standard without CaP (HX) and Short without CaP (HX) are intended for cementless fixation.

The Humeral Fracture Stems and Proximal Bodies are intended for cementless fixation.

The Modular Stems 75mm are intended for cemented or cementless fixation.

The Modular Stems, fully corundum blasted, are intended for cementless fixation.

The Modular Stems, fully polished, are intended for cemented fixation.

This system adds modular humeral stem components to the LINK Embrace Shoulder System – Reverse Configuration, comprised of Proximal Bodies and Modular Stems. The modular Proximal Bodies (Ti6A4V) are available in several sizes and heights. The Proximal Bodies feature a spiked surface, and m-l and a-p holes for suture fixation. The Proximal Bodies feature a proximal modular taper connection for assembly to the existing Reverse Tray components. The Proximal Bodies feature a distal modular taper connection for assembly to a modular stem.

The modular stems (Ti6Al4V) are available in different diameters and lengths as well as different surface options for cemented or cementless fixation.

The provided text is a 510(k) summary for the LINK® Embrace Shoulder System - Reverse Configuration. This document describes a medical device, specifically a shoulder prosthesis, and its substantial equivalence to previously cleared devices. It does not contain information about an AI/ML (Artificial Intelligence/Machine Learning) device or any study that proves such a device meets acceptance criteria.

Therefore, I cannot extract the requested information regarding acceptance criteria and a study proving an AI device meets them, as this information is not present in the provided text.

The document focuses on:

• Device Description: A shoulder joint replacement system, specifically an update adding modular humeral stem components.
• Indications for Use: When and for whom the device is intended.
• Comparison to Predicate Devices: Demonstrating that the new device is "substantially equivalent" to existing, legally marketed devices, primarily by comparing materials,
  sterilization, packaging, and general design principles.
• Performance Testing: Mentioning non-clinical performance tests (Range of Motion analysis, Fatigue testing with Fretting/Corrosion assessment, and post-fatigue disassembly tests)
  to show mechanical safety and performance, but these are for the physical implant, not an AI component.
• No Clinical Testing: Explicitly states that clinical performance testing was not required to demonstrate substantial equivalence for this device.

In summary, the provided text describes a conventional physical medical implant, not an AI/ML-driven device.

Ask a specific question about this device

The SMR Shoulder System is intended for partial or total, primary or revision shoulder joint replacement.

The SMR Anatomic Shoulder System is indicated for partial or total, primary or revision shoulder joint replacement in patients suffering from disability due to:

• non-inflammatory degenerative joint disease including osteoarthritis and avascular necrosis;
• . inflammatory degenerative joint disease such as rheumatoid arthritis;
• treatment of acute fractures of the humeral head that cannot be treated with other fracture fixation methods;
• revision of a failed primary implant; in case of SMR Short Stems only if sufficient bone stock remains); .
• cuff tear arthropathy (CTA Heads only); .
• glenoid arthrosis without excessive glenoid bone loss: A1, A2 and B1 according to Walch classification (SMR TT Hybrid Glenoid only). .

The SMR Reverse Shoulder System is indicated for primary, fracture or revision total shoulder replacement in a grossly rotator coff deficient joint with severe arthropathy (disabled shoulder). The patients joint must be anatomically suited to receive the selected implants and a functional deltoid muscle is necessary to use the device.

The SMR TT Hybrid Glenoid Reverse Baseplate must not be used in cases of excessive glenoid bone loss and/or when bone graft is needed.

The Modular SMR Shoulder System allows the assembly of components in various humeral and glenoid constructs are intended for cemented and uncemented use as specified in the following table.

In the Anatomic shoulder the humeral consists of the humeral stem, the humeral body, the adaptor taper and the humeral head. In the Reverse shoulder the humeral consists of the humeral stem, the reverse humeral body and the reverse liner. On the humeral side the fixation of the humeral stem determines if the construct is cemented or uncemented.

The Anatomic glenoid construct consists of an all polyethylene glenoid with metal peg or a metal back assembled with a liner; the Reverse glenoid consists of a metal back/connector/glenosphere construct or of a peg/baseplate/glenosphere construct. On the glenoid side, the fixation of the all polyethylene glenoid with metal peg or the metal back determines if the construct is cemented or uncemented.

The SMR 140° Reverse Humeral Bodies (SMR 140° Reverse Humeral Body, SMR 140° Short Reverse Humeral Body, SMR 140° Finned Reverse Humeral Body) are manufactured from Ti6Al4V alloy (ASTM F1472 - ISO 5832-3); they are for tapercoupling with previously cleared Humeral extension (K113523), SMR CTA Head Adaptor for Reverse Humeral Body (K131112), Reverse Liners (K110598, K142139) and Humeral stems (K100858, K101263, K111212, K191963).

This document is a 510(k) premarket notification for the SMR 140° Reverse Humeral Body, a component of a shoulder replacement system. As such, it does not contain information about acceptance criteria or a study proving that an AI device meets acceptance criteria.

The document describes a medical device (SMR 140° Reverse Humeral Body for shoulder replacement) and its substantial equivalence to predicate devices, supported by non-clinical mechanical testing. It explicitly states that clinical testing was not necessary to demonstrate substantial equivalence.

Therefore, the requested information points regarding AI acceptance criteria and studies (sample size, data provenance, expert ground truth, adjudication, MRMC studies, standalone performance, ground truth type for training/test sets, and training sample size) are not applicable to this document.

Ask a specific question about this device

The SMR Shoulder System is intended for partial or total, primary or revision shoulder joint replacement.

The SMR Anatomic Shoulder System is indicated for partial or total, primary or revision shoulder joint replacement in patients suffering from disability due to:

• non-inflammatory degenerative joint disease including osteoarthritis and avascular necrosis;
• inflammatory degenerative joint disease such as rheumatoid arthritis;
• treatment of acute fractures of the humeral head that cannot be treated with other fracture fixation methods;
• revision of a failed primary implant; in case of SMR Short Stems only if sufficient bone stock remains;
• cuff tear arthropathy (CTA Heads only);
• glenoid arthrosis without excessive glenoid bone loss: A1, A2 and B1 according to Walch classification (SMR TT Hybrid Glenoid only).

The SMR Reverse Shoulder System is indicated for primary, fracture or revision total shoulder replacement in a grossly rotator cuff deficient joint with severe arthropathy (disabled shoulder). The patient's joint must be anatomically and structurally suited to receive the selected implants and a functional deltoid muscle is necessary to use the device.

The SMR TT Hybrid Glenoid Reverse Baseplate must not be used in cases of excessive glenoid bone loss and/or when bone graft is needed.

The Modular SMR Shoulder System allows the assembly of components in various humeral and glenoid constructs. The constructs are intended for cemented use as specified in the following table.

In the Anatomic shoulder the humeral construct consists of the humeral stem, the humeral body, the adaptor taper and the humeral head. In the Reverse shoulder the humeral construct consists of the humeral stem, the reverse humeral body and the reverse liner. On the humeral side the fixation of the humeral stem determines if the construct is cemented or uncemented.

The Anatomic glenoid construct consists of an all polyethylene glenoid, a polyethylene glenoid with metal peg or a metal back assembled with a liner; the Reverse glenoid consists of a metal back/connector/glenosphere construct or of a peg/baseplate/glenosphere construct.

On the glenoid side, the fixation of the all polyethylene glenoid, the polyethylene glenoid with metal peg or the metal back determines if the construct is cemented or uncemented.

The 45mm length SMR Finned Short Stems are available in 13 diameters and are for coupling with previously cleared Reverse Humeral Bodies (K110598) or Humeral Bodies (K100858, K101263); they are manufactured from Ti6Al4V alloy (ASTM F1472 - ISO 5832-3) and are characterized by a male taper.

The provided text is a 510(k) Premarket Notification from the FDA regarding LimaCorporate S.p.A.'s SMR Finned Short Stems. It details the device's intended use, description, and comparison to predicate devices, focusing on demonstrating substantial equivalence for a medical device that is a physical orthopedic implant.

Crucially, this document does not describe an AI/software as a medical device (SaMD) or any device that relies on algorithms for diagnostic or therapeutic decisions. Therefore, the concepts of acceptance criteria for algorithm performance, sample sizes for test sets, establishment of ground truth by experts, MRMC studies, or standalone algorithm performance are not applicable to this submission.

The "study that proves the device meets the acceptance criteria" in this context refers to non-clinical (mechanical) testing for the physical implant, not a clinical trial involving patient data and algorithm performance.

Here's a breakdown based on the provided document, addressing the prompt's categories where applicable, and explicitly stating when information is R/NA (Refers to Not Applicable) due to the nature of the device:

Acceptance Criteria and Device Performance (for a physical orthopedic implant)

There isn't a direct "acceptance criteria table" for algorithm performance as would be seen in an AI/SaMD submission. Instead, the acceptance criteria are met through mechanical testing that demonstrates the new device performs similarly to or better than predicate devices in terms of structural integrity and function.

Detailed breakdown of the study (non-clinical testing for a physical implant):

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

   • See the table above. These are implicit criteria for mechanical performance of an orthopedic implant for substantial equivalence.

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

   • Sample Size: Not explicitly stated in the document in terms of number of physical stems tested. It refers to "worst case components or constructs."
   • Data Provenance: This refers to the testing of physical samples of the manufactured SMR Finned Short Stems. "Worst case components or constructs identified through FE analysis" were tested. This is a form of prospective, in-vitro testing. (R/NA for geographic provenance as it's mechanical testing of manufactured parts).

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

   • R/NA: This is not an AI/SaMD submission requiring expert consensus for ground truth on medical images or diagnoses. The "ground truth" for a physical implant's performance is derived from standardized mechanical testing protocols and engineering principles.

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

   • R/NA: This concept applies to human assessment of data, often in AI/SaMD studies to resolve discrepancies. It is not relevant for mechanical testing of a physical implant.

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:

   • R/NA: This is specifically for AI/SaMD devices. No such study was performed or required as this is a physical medical device. The document explicitly states: "Clinical testing was not necessary to demonstrate substantial equivalence of the new SMR Finned Short Stems to the predicate devices."

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

   • R/NA: This is for AI/SaMD devices. The device is a physical shoulder implant.

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

   • Ground Truth Type: For a physical implant, the "ground truth" is established by engineering standards and mechanical properties. This includes successful completion of "fatigue-fretting behaviour" and "evaluation of residual torque of the safety screw and push-out force of the coupling between stem and humeral body" based on established engineering test methods and design specifications.

8. The sample size for the training set:

   • R/NA: This is for AI/SaMD devices. This device does not have a "training set." The design and "worst case components" for mechanical testing might be identified through engineering analysis (e.g., Finite Element Analysis as mentioned "FE analysis"), but this is not an AI training process.

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

   • R/NA: As there is no training set for this physical device, this question is not applicable.

Ask a specific question about this device