Search Results

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to assist in pre-operative planning and/ or in guiding the marking of bone and/or guide surgical instruments in non-acute, non-joint replacing osteotomies

· For adult patients; in upper extremity orthopedic surgical procedures and orthopedic surgical procedures around the knee.

· For pediatic patients 7 years of age and older; in orthopedic surgical procedures involving the radius and ulna.

SurgiCase Guides are intended for single use only.

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to transfer a pre-surgical plan to surgeries involving osteotomies in upper extremity orthopedic surgical procedures and orthopedic surgical procedures around the knee.

For pediatric patients 7 years of age and older, it is intended to be used in osteotomies involving the radius and ulna.

The SurgiCase Orthopaedics system is composed of two components: SurgiCase Connect (software) and SurgiCase Guides (hardware).

SurgiCase Connect is a medical device for Materialise and a surgeon for pre-surgical simulation of surgical treatment options. This includes transferring, visualizing, measuring, and editing medical data.

The SurgiCase Guides are patient specific templates that are designed and manufactured based on a pre-surgical software plan for a specific patient. In surgery these guides are used to assist a surgeon in guiding the marking of bone and/or guiding surgical instruments to cut and drill according to the pre-surgical plan.

All guides are individually designed and manufactured for each patient using a design and manufacturing process with strict procedures and work instructions. Part of this process is a scientific Stability Model which measures the sensitivity of a guide to movement during surgery. The use of this Stability Model provides a way to find the most stable position of the base plate on the individual patient's anatomy for accurate guiding of surgical instruments. The Stability Model is anatomy independent, thus it can be applied to any bony structure in upper and lower extremity surgical procedures.

The provided text is a 510(k) summary for the Materialise N.V. Surgicase Orthopaedics system (K163156). It describes a Class II medical device intended for surgical planning and guiding instruments, particularly for osteotomies. The submission expands the intended use to include pediatric patients aged 7 years and older, specifically for procedures involving the radius and ulna.

Based on the provided text, the acceptance criteria and study proving the device meets those criteria can be summarized as follows:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly present a table of quantitative acceptance criteria with corresponding performance metrics. Instead, it focuses on demonstrating substantial equivalence to the predicate device (K132290), particularly for the new pediatric patient population. The primary "acceptance" is tied to the guide's fit despite bone growth in pediatric patients.

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

• Test Set (for "Fit Tests"): The text mentions "grown, 3D-printed, pediatric bone models." It does not specify the numerical sample size for these models. The provenance is implied to be from "pediatric clinical cases" that were used to simulate growth.
• Retrospective Analysis: "Retrospective analysis of US and OUS pediatric clinical cases" was conducted. The specific sample size for this analysis is not provided. The data provenance is stated as "US and OUS" (Outside US), indicating a mix of international data, and it was "retrospective."

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

The document does not mention the use of experts to establish ground truth for the "fit tests" on 3D-printed models. The evaluation of guide fit on these models appears to be an objective measurement against defined criteria for "maximal allowed growth."

For the retrospective clinical cases, there's no mention of experts establishing ground truth or their qualifications. The analysis "helped to further support the safety and short-term efficacy," suggesting a review of clinical outcomes rather than establishing a gold standard for specific measurements performed by the device itself.

4. Adjudication Method for the Test Set:

No adjudication method (e.g., 2+1, 3+1) is described for the "fit tests" or the retrospective analysis, as these are not studies involving subjective interpretations requiring consensus.

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

No MRMC comparative effectiveness study involving human readers with and without AI assistance is mentioned. The device described (SurgiCase Orthopaedics system) is a surgical planning and guiding system, not an AI diagnostic tool primarily evaluated for human reader improvement.

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

The "fit tests" on 3D-printed models and the determination of "useful life" can be considered an assessment of the device's performance (specifically the guide's physical fit) in a standalone manner, independent of a human surgeon's real-time interaction during surgery, but based on the system's design and manufacturing outputs. The "Stability Model" is also described as a scientific model for determining stable placement, which would be a standalone algorithmic component.

7. The Type of Ground Truth Used:

• For "Fit Tests": The ground truth for the fit tests appears to be defined by a "maximal allowed growth" criterion, which was determined through simulating growth on 3D-printed bone models derived from pediatric clinical cases. This is a synthetic or simulated ground truth based on anatomical measurements.
• For Retrospective Analysis: The "safety and short-term efficacy" in the retrospective analysis implies clinical outcomes (e.g., successful procedure, absence of complications related to the device) as the ground truth, rather than a specific measurement.

8. The Sample Size for the Training Set:

The document does not mention a "training set" in the context of an AI/machine learning model. The device components described are software for planning and hardware (guides). The "Stability Model" is described as a "scientific Stability Model," not explicitly as a machine learning model that would require a training set. The "design and manufacturing process with strict procedures and work instructions" implies a more traditional engineering approach rather than an AI-driven one.

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

Since no distinct "training set" for an AI model is described, there's no information on how its ground truth was established. The "useful life" period calculation was based on a "literature study" covering bone growth and the results of the "fit tests" on 3D-printed models.

Ask a specific question about this device

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to assist in pre-operative planning and/or in guiding the marking of bone and/or guide surgical instruments in non-acute, non-joint replacing osteotomies for upper extremity orthopedic surgical procedures and osteotomies around the knee.

The system is to be used for adult patients.

SurgiCase Guides are intended for single use only.

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to transfer a pre-surgical plan to the surgery with osteotomies on upper extremity orthopedic procedures anound the knee.

The SurgiCase Orthopaedics system is components: SurgiCase Connect (software) and SurgiCase Guides (hardware).

SurgiCase Connect is a medical device for Materialise and a surgeon for pre-surgical simulation of surgical treatment options. This includes transfering, visualizing, measuring, annotating and editing medical data.

The SurgiCase Guides are patient specific templates that are designed and manufactured based on a pre-surgical software plan for a specific patient. In surgery these guides are used to assist a surgeon in guiding the marking of bone and/or guiding surgical instruments to cut and drill according to the pre-surgical plan.

All guides are individually designed and manufactured for each patient using a design and manufacturing process with strict procedures and work instructions to guarantee guides that consistently perform in a safe and effective way. Part of this process is a scientific Stability Model which measures the sensitivity of a guide to movement during surgery. The use of this Stability Model ensures a stable position on the patient's anatomy for accurate guiding of surgical instruments. The Stability Model is anatomy independent, thus it can be applied to any bony structure in upper extremity surgical procedures and osteotomies around the knee.

Here's a breakdown of the acceptance criteria and the study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

| Acceptance Criteria Category | Specific Test/Study | Reported Device Performance and Acceptance |
| :--------------------------- | :------------------------------------------------ |
| Accuracy | Bone Model Tests | "All results were within the preset acceptance criteria." (Specific numerical criteria not provided) |
| Accuracy | Cadaveric Tests | "All results were within the preset acceptance criteria." (Specific numerical criteria not provided) |
| Safety & Effectiveness | Biocompatibility Test | "Testing verified that the accuracy and performance of the device is adequate to perform as intended." |
| Safety & Effectiveness | Sterilization Dimensional Stability Test | "Testing verified that the accuracy and performance of the device is adequate to perform as intended." |
| Safety & Effectiveness | Cleaning Validation Test | "Testing verified that the accuracy and performance of the device is adequate to perform as intended." |
| Safety & Effectiveness | Packaging and Shipment Test | "Testing verified that the accuracy and performance of the device is adequate to perform as intended." |
| Stability/Fit | Scientific Stability Model | "Ensures the most stable position on the patient's anatomy for accurate guiding of surgical instruments." |
| Software Functionality | Internal and External User Testing & Observations | "Results from this verification and validation testing demonstrate the device's safety and effectiveness is substantially equivalent to the predicate device." |
| Clinical Efficacy | Retrospective Analysis of Clinical Cases (Europe) | "Confirms the subject device's safety and effectiveness is substantially equivalent to the predicate device for use as intended based on surgeon evaluation of expected outcome." |

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

• Bone Model Tests: "On a series of femoral and tibial models" (Specific number of models not provided).
• Cadaveric Tests: "On a series of cadaveric specimens" (Specific number of specimens not provided).
• Retrospective Clinical Cases: "Retrospective analysis of clinical cases performed in Europe" (Specific number of cases not provided).

3. Number of Experts Used to Establish Ground Truth and Qualifications

• For the bone model and cadaveric tests, the "pre-operative planned versus achieved corrected models/specimens were compared." This implies a comparison to a pre-defined plan or standard, rather than a consensus among external experts. The qualifications of who established the "pre-operative plan" and conducted the comparison are not explicitly stated, but it would typically be engineers or qualified personnel involved in the device development.
• For the retrospective clinical cases, "surgeon evaluation of expected outcome" was used. The number and specific qualifications of these surgeons are not provided, other than them being clinical users in Europe.

4. Adjudication Method for the Test Set

• The document implies a comparison of achieved results against "preset acceptance criteria" for the non-clinical tests. This suggests a direct measurement against a standard, rather than a multi-expert adjudication process.
• For the retrospective clinical cases, the ground truth was based on "surgeon evaluation of expected outcome," which might implicitly involve some level of individual surgeon judgment rather than a formal adjudication panel. No specific adjudication method like 2+1 or 3+1 is mentioned.

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

• No MRMC comparative effectiveness study is mentioned that assesses how much human readers improve with AI vs without AI assistance. The device is a surgical planning and guiding system, not an AI for image interpretation that would typically involve human readers.

6. Standalone (Algorithm Only) Performance Study

• A standalone performance was implicitly conducted for the SurgiCase Connect software component through "internal and external user testing and observations" and verification against specifications.
• The SurgiCase Guides were validated through "bone model tests" and "cadaveric tests," which involved applying the guides according to a pre-operative plan and comparing the achieved corrected models/specimens to the planned ones. This represents a standalone performance assessment of the guide's accuracy in transferring the surgical plan.

7. Type of Ground Truth Used

• Non-clinical tests (Bone models, Cadavers): "Pre-operative planned" outcomes served as the ground truth against which the achieved corrected models/specimens were compared. This is an engineered or defined ground truth.
• Retrospective Clinical Study: "Surgeon evaluation of expected outcome" served as the ground truth. This is a form of expert clinical judgment/outcome data.

8. Sample Size for the Training Set

• The document does not provide explicit information on the sample size used for a "training set." The device is primarily a software system for planning and physical guides for execution, rather than a machine learning algorithm that typically undergoes a separate supervised training phase with a dedicated training set. The descriptions focus on verification and validation against specifications and clinical use.

9. How Ground Truth for the Training Set Was Established

• As no explicit training set is mentioned in the context of a machine learning algorithm, the method for establishing its ground truth is not applicable or described in this document. The "training" for such a system would involve software development, engineering, and iterative testing/refinement against design specifications and user feedback, rather than a formal ground truth for a machine learning model.

Ask a specific question about this device

The Match Point System™ is intended to be used as a surgical instrument to assist in the intraoperative positioning of glenoid components used with total and reverse shoulder arthroplasty procedures which utilize anatomic landmarks that are identifiable on preoperative CT or MRI medical images.

The Match Point System™ can be used with the following total and reverse shoulder implant systems and their respective compatible components: Encore Shoulder System (K051075), Turon™ to RSP Conversion Shell (K111629), Turon™ Shoulder System (K080402) and Reverse® Shoulder prosthesis (K092873).

The Match Point System™ Guides are intended for single use only.

The Match Point System™ consists of a software component, SurgiCase Connect and a hardware component, Match Point System™ guide, and is designed to assist the surgeon in the placement of glenoid components.

The Match Point System is for use within the intended use of the compatible components.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

• design, intended use, functionality, technology, material and performance characteristics for the Signature Personalized Patient Care System - Acetabular Guide System;
• intended use and functionality for the conventional instrumentation for shoulder arthroplasty (central drill guide). |
  | Accuracy and performance adequate for intended use. | "Accuracy performance testing was performed in a cadaveric setting to determine substantial equivalence. Testing verified that the accuracy and performance of the system is adequate to perform as intended." |
  | Guide use, positioning, and accuracy at borders. | "Accuracy performance testing was performed on rapid prototyped models to verify guide use, positioning, and accuracy of the shoulder system at its borders for use." |
  | Safety and effectiveness. | "Non-clinical testing was sufficient to demonstrate safety and effectiveness of the device as intended." |

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

• Test Set Sample Size: The document does not specify a numerical sample size for the "cadaveric setting" or "rapid prototyped models" used in the non-clinical tests.
• Data Provenance: The tests were non-clinical, involving a "cadaveric setting" and "rapid prototyped models." The country of origin for this data is not specified. The tests were presumably prospective as they were specifically conducted for this submission.

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

• The document does not provide information on the number of experts or their qualifications used to establish ground truth for the non-clinical tests. The tests focused on objective measurements of accuracy and performance in a controlled environment, likely using established anatomical references or engineering specifications rather than expert consensus on subjective interpretations.

4. Adjudication Method for the Test Set

• The document does not specify an adjudication method. Given the nature of the non-clinical accuracy and performance testing, it's likely that measurements were taken and compared against predefined engineering tolerances or anatomical landmarks, rather than requiring expert adjudication of subjective assessments.

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

• No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The provided text indicates that "Non-clinical testing was sufficient to demonstrate safety and effectiveness of the device as intended," and it explicitly states "No Clinical Data" was required. Therefore, no studies comparing human readers with and without AI assistance (which is what the software component does) were performed or reported.

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

• A standalone performance assessment of the software component (SurgiCase Connect), in terms of its ability to generate the preoperative plan with a certain level of accuracy prior to surgeon modification, is not explicitly detailed as a standalone study. The description implies the software component (SurgiCase Connect) generates an initial plan which is then "fine-tune[d] and approve[d]" by a qualified surgeon. The accuracy testing seems to be for the entire system (software + guide) in transferring the approved plan.

7. The Type of Ground Truth Used

• In the context of the non-clinical accuracy performance testing:
  • For the cadaveric setting, the ground truth would likely be established anatomical landmarks and precise measurements taken relative to these landmarks.
  • For the rapid prototyped models, the ground truth would likely be the precise engineering specifications and measurements of the model, which represent the ideal planned scenario.
  • Neither "expert consensus," "pathology," nor "outcomes data" are mentioned as the ground truth for these tests. The ground truth for these tests would be based on objective, quantifiable physical measurements against known standards.

8. The Sample Size for the Training Set

• The document does not specify a training set sample size. This device appears to be a medical device software that assists in planning and manufacturing a physical guide, rather than a machine learning model that typically requires a large training set. The "software component" (SurgiCase Connect) seems to be based on algorithms and anatomical modeling principles rather than statistical learning from a dataset.

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

• Since there's no mention of a traditional machine learning "training set," there's no information on how its "ground truth" was established. The software's functionality is described as generating a plan based on "medical imaging data" and "surgical technique of the respective implant system," implying a rule-based or model-driven approach rather than data-driven machine learning.

Ask a specific question about this device

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to assist in pre-operative planning and/or in guiding the marking of bone and/or guide surgical instruments in non-acute, non-joint replacing osteotomies for upper extremity orthopedic surgical procedures.

The system is to be used for adult patients.

SurgiCase Guides are intended for single use only.

The SurgiCase Orthopaedics system is composed of two components: SurgiCase Connect (software) and SurgiCase Guides (hardware).

The SurgiCase Orthopaedics system is intended to be used as a surgical instrument to transfer a pre-surgical plan to the lower and upper extremity during orthopaedic surgical procedures.

SurgiCase Connect is a medical device for Materialise and a surgeon for pre-surgical simulation and evaluation of surgical treatment options. This includes transferring, visualizing, measuring, annotating and editing medical data.

The SurgiCase Guides are patient specific templates that are based on a pre-surgical software plan and are designed to fit a specific patient. All guides are individually designed and manufactured for each patient using a design and manufacturing process with strict procedures and work instructions to guarantee guides that consistently perform in a safe and effective way. In surgery these guides are used to assist a surgeon in guiding the marking of bone and/or guiding surgical instruments according to the pre-surgical plan.

Here's an analysis of the provided text regarding the acceptance criteria and study for the SurgiCase Orthopaedics system:

The provided 510(k) summary (K112389) for the SurgiCase Orthopaedics system does not explicitly detail specific acceptance criteria with quantifiable metrics for device performance (e.g., "accuracy of +/- 1mm") nor does it describe a formal clinical or standalone comparative study with human readers or a detailed statistical analysis of performance against such criteria.

Instead, the submission focuses on demonstrating substantial equivalence to predicate devices through a comparison of intended use, materials, and performance characteristics, and relies on non-clinical testing for validation. This is a common approach for certain types of medical devices, especially when establishing equivalence to existing technology.

However, based on the limited information provided, we can infer some aspects and present what is available:

1. Table of Acceptance Criteria and Reported Device Performance

As mentioned, specific quantifiable acceptance criteria are not explicitly stated in this document. The "performance" described is more qualitative and relates to successful completion of non-clinical tests to demonstrate safety and effectiveness, and accuracy adequate to perform as intended.

2. Sample Size for the Test Set and Data Provenance

The document states: "SurgiCase Guides were validated through non-clinical studies using bone models and cadaver specimens."

• Sample Size for Test Set: Not specified. The number of bone models and cadaver specimens used is not provided.
• Data Provenance: The validation was non-clinical, using bone models and cadaver specimens. The country of origin for these specimens is not mentioned, nor whether the data was retrospective or prospective (though for non-clinical lab testing, "prospective" would be the more fitting description of how the tests were conducted).

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not provided in the document. Since the validation was entirely non-clinical using bone models and cadaver specimens, the concept of "experts establishing ground truth" in the diagnostic imaging sense (e.g., radiologists reviewing images) does not directly apply here. Instead, ground truth would be physical measurements and objective assessments against known parameters of the models/specimens, likely performed by engineers, technicians, and potentially surgeons involved in the study design.

4. Adjudication Method for the Test Set

This information is not applicable/provided. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies involving human readers or expert review of data where there might be disagreements. Since the validation was non-clinical with bone models and cadavers, and no human reader interpretation of images is described as part of the primary validation for the stated performance, an adjudication method is not relevant.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The document does not mention any studies involving human readers, either with or without AI assistance, or comparisons between them. The focus is on the device's standalone performance in non-clinical settings.

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

Yes, implicitly. The non-clinical validation tests using bone models and cadaver specimens assess the performance of the SurgiCase Guides (hardware) and the SurgiCase Connect software (algorithm for planning/design) in isolation from a live surgical scenario involving a human surgeon's real-time interaction. The software is validated for its intended use, and the guides are tested for accuracy. This can be considered a form of standalone performance assessment as it evaluates the device's ability to "perform as intended" without human intervention in the measurement of its accuracy.

7. The Type of Ground Truth Used

The ground truth for the non-clinical validation was likely based on:

• Physical measurements: Precise measurements taken on the bone models and cadaver specimens to assess the accuracy of the guides and the outcomes of the simulated procedures. This would involve comparing the guided cuts/markings to the pre-surgical plan.
• Known parameters of the models: For engineered bone models, the "ground truth" of anatomical features and target osteotomy locations would be precisely known.
• Biocompatibility standards: For biocompatibility, the ground truth would be established regulatory standards and test results.
• Sterilization efficacy: For sterility, established protocols and detection limits.

It is not pathology, expert consensus in a diagnostic sense, or outcomes data from real patients.

8. The Sample Size for the Training Set

This information is not provided in the document. The filing describes the product as an "Image processing system and software for simulating/evaluating implant placement and surgical treatment options." While image processing software often involves machine learning that requires training data, the document does not specify any ML/AI components in detail or reference a training set. The descriptions point more towards conventional computational geometry and visualization software. If a machine learning component were present, its training data size and provenance would be crucial.

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

Since information about a training set or specific machine learning components is not provided, how its ground truth was established is also not described.

Ask a specific question about this device

The SurgiCase system is intended for use as a software interface and image segmentation system for the transfer of imaging information from a medical scanner such as a CT scanner or a Magnetic Resonance Imaging scanner. It is also intended as pre-operative software for simulating / evaluating implant placement and surgical treatment options.

SurgiCase Connect for iPad is a component of the SurgiCase system and intended to be used as a software interface to assist in pre-operative planning by simulation / evaluation of surgical treatment options.

The Materialise SurgiCase system is a software medical device to transfer and to segment imaging information from a medical scanner such as a CT or MRI scanner. It allows for presurgical simulation and evaluation of implant placement and surgical treatment options.

SurgiCase Connect is a medical device for pre-surgical simulation and evaluation of surgical treatment options. This includes transferring, visualizing and editing medical data. .

Based on a pre-surgical software plan the patient specific templates - SurgiCase Guides can be manufactured to fit a specific patient. SurgiCase Guides are not a part of this premarket notification submission.

The provided text is a 510(k) summary from Materialise N.V. regarding their SurgiCase system, specifically focusing on the new component, SurgiCase Connect for iPad. The core of the submission is to demonstrate substantial equivalence to a predicate device (SurgiCase K073449).

The document explicitly states:

• Clinical testing: Not applicable.

This means that a clinical study with acceptance criteria and reported device performance, as typically understood in a clinical trial context, was not performed for this submission. The device is being cleared based on its substantial equivalence to a predicate device through non-clinical testing.

Therefore, I cannot provide the detailed information requested regarding acceptance criteria and the study proving the device meets them, because such a study (clinical or performance study with defined acceptance criteria and results) is not described in this 510(k) summary.

The submission focuses entirely on demonstrating substantial equivalence through non-clinical testing, primarily asserting that the new component (SurgiCase Connect for iPad) has equivalent intended use, performance characteristics, design, and function to the predicate SurgiCase system.

Ask a specific question about this device

SurgiCase Guides are intended to be used as surgical tools to transfer a pre-operative plan to the surgery. The devices are intended to guide the marking of bone and/or guide surgical instruments in mandibular and maxillofacial surgical procedures.

SurgiCase Guides are intended for single use only.

The SurgiCase Guides are patient specific devices or templates that are based on a preoperative software planning and are designed to fit a specific patient. These templates are used to assist a surgeon in transferring this pre-operative plan to the surgery by guiding the marking of bone and/or guiding surgical instruments.A standardized design and manufacturing process with detailed procedures and work instructions allows manufacturing patient-specific templates that consistently perform in a safe and effective way during surgery.

The SurgiCase Guides are based on a software planning generated using the previously cleared SurgiCase software (K073449).

SurgiCase is software for pre-operative simulation and evaluation of implant placement and surgical treatment options, based on imaging information from a medical scanner such as a CT scanner or a Magnetic Resonance Imaging (MRI) scanner. The SurgiCase software was previously reviewed under K073449 and is not submitted for review in this 510k submission. References to the software are included to give a complete overview on the guide design process.

The provided text does not contain detailed information about specific acceptance criteria with quantifiable metrics, a formal study demonstrating the device meets these criteria, or granular details about test sets, ground truth establishment, or multi-reader multi-case studies typically associated with AI/ML device evaluations.

The document describes a 510(k) submission for "SurgiCase Guides," which are patient-specific surgical templates based on pre-operative software planning. The performance data section broadly mentions "non-clinical tests such as quantitative validation using bone models and cadaveric specimens" were performed and "verified that the accuracy and performance of the system is adequate to perform as intended." However, it does not provide the specific acceptance criteria or the results of these tests in a quantifiable manner.

Here's an analysis of the requested information based on the provided text:

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

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

• Sample size: Not specified. The document mentions "bone models and cadaveric specimens" but does not give the number of models or specimens used.
• Data provenance: Not specified.

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

• Not applicable/Not specified. The term "ground truth" as typically used in AI/ML evaluation referring to expert-annotated data is not mentioned. The device is a surgical guide system, and its validation involves physical accuracy on models/cadavers, not interpretation of images by experts.

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

• Not applicable/Not specified. Adjudication methods are typically relevant for cases where multiple experts provide annotations that need to be reconciled to establish a ground truth for a test set in AI/ML contexts. This is not described for a physical device validation.

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, an MRMC comparative effectiveness study is not mentioned. This type of study is usually conducted for AI-powered diagnostic or assistive tools where human readers are involved in interpreting data with and without AI. The SurgiCase Guides are physical surgical tools, not AI for human interpretation.

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

• The document implies that the "quantitative validation using bone models and cadaveric specimens" focused on the physical accuracy of the guides themselves, which could be considered a form of standalone performance of the device. However, it's not an "algorithm only" performance because the device itself is a physical object designed to guide surgical instruments. The software used to design the guides (SurgiCase software K073449) was previously cleared and is not the subject of this 510(k) submission.

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

• The "ground truth" in this context would likely refer to the actual surgical plan (as transferred to the models/cadavers) or ideal anatomical positioning, against which the guided surgical actions were compared for accuracy. The document mentions "quantitative validation," suggesting objective measurements of accuracy were taken, but the specific nature of this "ground truth" (e.g., precise measurements of osteotomy planes or screw placement from a gold standard) is not detailed.

8. The sample size for the training set

• Not applicable/Not specified. Surgical guides are precisely manufactured to a patient's anatomy based on imaging and a pre-operative plan. There is no "training set" in the sense of machine learning model development mentioned for the SurgiCase Guides themselves. The underlying SurgiCase software (K073449) generates the plan, but its "training" details are not part of this submission.

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

• Not applicable/Not specified. As there is no "training set" described for the SurgiCase Guides, the establishment of ground truth for such a set is not discussed.

Ask a specific question about this device