(106 days)
Intended Use
CORIOGRAPH Pre-Op Planning and Modeling Services are intended to provide preoperative planning for surgical procedures based on patient imaging, provided that anatomic landmarks necessary for generating the plan are identifiable on patient imaging scans.
Indications for Use
The CORIOGRAPH Pre-op Planning and Modeling Services are indicated for use for the following procedures:
- · Unicondylar Knee Replacement (UKR)
- · Total Knee Arthroplasty (TKA)
- · Primary Total Hip Arthroplasty (THA)
The subject CORIOGRAPH Hip Pre-Op Plan and CORIOGRAPH Modeler are medical function modules within the CORIOGRAPH Pre-Op Planning and Modeling Services are additional offerings being introduced by Blue Belt Technologies, Inc. to allow for pre-operative planning for surgical procedures based on patient imaging for primary total hip arthroplasty (THA). The CORIOGRAPH Hip Pre-Op Plan system will utilize Smith and Nephew personnel to generate patient specific bone models and preoperative plans for primary THA which will be viewable and editable on CORIOGRAPH Modeler 1.0. Together, CORIOGRAPH Hip Pre-Op Plan and CORIOGRAPH Modeler are the subject of this submission.
The acceptance criteria for the CORIOGRAPH Pre-Op Planning and Modeling Services V2.0 were demonstrated through verification and validation testing, and summative usability testing. The provided document does not explicitly list numerical acceptance criteria values for metrics like accuracy, sensitivity, or specificity. Instead, it broadly states that testing demonstrated the safety and effectiveness of the software applications and that all design inputs were met.
Acceptance Criteria and Reported Device Performance
Note: The document does not provide specific quantitative acceptance criteria or detailed performance metrics. It indicates that the device met its design inputs and was found to be safe and effective.
| Acceptance Criteria Category | Reported Device Performance (as stated in document) |
|---|---|
| Verification and Validation Testing | Demonstrated the safety and effectiveness of the software applications used in CORIOGRAPH Pre-Op Planning & Modeling Services V2.0. All design inputs were met. |
| Summative Usability Testing | Demonstrated that participating surgeons were able to use the subject device safely and effectively in a simulated use environment. |
| Credibility Evaluation | Demonstrated that the kinematic models and Activities of Daily Living (ADLs) utilized in the subject device are clinically relevant. |
Study Details:
-
Sample size used for the test set and the data provenance:
- The document mentions "sumative usability testing" was performed, indicating a test set was used, but does not specify the sample size for the test set.
- The document does not specify the data provenance (e.g., country of origin, retrospective or prospective) for the data used in testing.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document implies that "participating surgeons" were involved in the summative usability testing, but does not state the number of experts used to establish ground truth or their specific qualifications (e.g., years of experience, subspecialty).
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- The document does not describe any specific adjudication method used for the test set.
-
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 a multi-reader multi-case (MRMC) comparative effectiveness study or report any effect size for human reader improvement with AI assistance. The study focuses on the device's ability to generate pre-operative plans and its usability.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- The document states that the software applications underwent "verification and validation testing," implying a standalone component to ensure functional correctness. However, it also highlights "summative usability testing" with "participating surgeons," which indicates human-in-the-loop performance was also evaluated, particularly for the overall service. It is not explicitly stated whether fully standalone performance was evaluated as a separate metric without any human involvement.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the "credibility evaluation," the document states it "demonstrated that the kinematic models and Activities of Daily Living (ADLs) utilized in the subject device are clinically relevant." This suggests clinical relevance or expert opinion/consensus as a form of ground truth for these aspects. For the outputs of the pre-operative planning, the implied ground truth is agreement with surgical principles and objectives, likely assessed by participating surgeons during usability testing.
-
The sample size for the training set:
- The document does not specify the sample size for the training set. It describes the device as providing "Pre-Op Planning and Modeling Services" based on patient imaging and does not detail a machine learning model's training process or associated dataset sizes.
-
How the ground truth for the training set was established:
- Since the document does not explicitly mention a training set or machine learning components in terms of specific algorithms that require labeled training data (beyond general software development and functionality), it does not describe how ground truth for a training set was established. The "services" aspect implies that the system is used by human personnel (Smith and Nephew personnel, as stated in device description) to generate plans, meaning the "training" might refer to the development and refinement of these human-led processes and software functionalities under established surgical guidelines.
N/A