(127 days)
The Salto Talaris PSI System is intended to be used as patient specific surgical planning and instrumentation to assist in the positioning of total ankle replacement components intraoperatively, and in guiding bone cutting. The Salto Talaris PSI System is intended for use with Smith + Nephew's Salto Talaris Total Ankle System and its cleared indications for use.
3D Systems' Salto Talaris Ankle PSI System consists of patient specific outputs including surgical guides, anatomical models, and case reports. The Salto Talaris Ankle PSI System guides are made from biocompatible nylon and surgical grade stainless steel and are designed to fit the contours of the patient's distal tibial and proximal talar anatomy. The surgical guides in combination with the Smith+Nephew Salto Talaris Total Ankle System instruments, facilitate the positioning of Salto Talaris Total Ankle Prostheses.
The provided text is a 510(k) summary for the Salto Talaris Ankle PSI System. It describes the device, its intended use, and a summary of non-clinical testing. However, it does not contain the detailed information necessary to fully answer all aspects of your request, particularly regarding specific acceptance criteria, expert qualifications, adjudication methods, details of ground truth establishment, or specific sample sizes for training and testing sets in the context of an AI-based system.
The Salto Talaris Ankle PSI System is described as patient-specific surgical planning and instrumentation to assist in positioning total ankle replacement components and guiding bone cutting. This device primarily involves physical surgical guides and anatomical models derived from CT data, rather than a standalone AI algorithm for diagnosis or image analysis. Therefore, some of the requested information, such as an MRMC comparative effectiveness study with AI assistance or standalone algorithm performance, is not directly applicable to this type of device as typically described for AI/ML-based diagnostic software.
Here's a breakdown of the available information based on your request:
1. Table of acceptance criteria and the reported device performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Mechanical Integrity (post-processing) | Met all acceptance criteria. |
| Debris Generation | Met all acceptance criteria. |
| Inter-Designer Variability analysis | Met all acceptance criteria. |
| Implant Alignment Accuracy (cadaveric comparison) | Accuracy shown to be similar to standard instrumentation for the Salto Talaris Total Ankle System. |
| Guide Usability (cadaveric comparison) | Functionality shown to be similar to standard instrumentation for the Salto Talaris Total Ankle System. |
The document states that the Salto Talaris Ankle PSI System met all acceptance criteria for mechanical integrity, debris generation, and inter-designer variability analysis. For implant alignment accuracy and guide usability, cadaveric comparison testing showed similarity to standard instrumentation. The specific quantitative acceptance criteria values (e.g., specific thresholds for mechanical integrity or debris generation, or a numerical range for alignment accuracy) are not provided in this summary.
2. Sample size used for the test set and the data provenance
The document mentions "Non-clinical cadaveric comparison testing." However, it does not specify the sample size (number of cadavers or cases) used for this test set, nor does it provide information about the data provenance (e.g., country of origin, retrospective or prospective).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide this information. Since the device involves surgical guides and bone cutting, "ground truth" in this context would likely relate to anatomical measurements or surgical outcomes, potentially assessed by orthopedic surgeons. However, no details on experts or their qualifications are given.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
The document does not specify any adjudication method.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance
An MRMC comparative effectiveness study of the type typically performed for AI/ML diagnostic software (where human readers evaluate cases with and without AI assistance) was not mentioned and is unlikely to be applicable based on the device description. This device provides physical guides for surgery, not AI-based image analysis for diagnosis. The non-clinical cadaveric testing compared the device to standard instrumentation, not to human readers using or not using AI.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
The device is described as "patient specific surgical planning and instrumentation to assist in the positioning... and in guiding bone cutting." This inherently implies a "human-in-the-loop" scenario (a surgeon using the guides). The "non-clinical cadaveric comparison testing" assessed the performance of the device in use, which is a form of standalone performance for the instrumentation itself but not in the context of an AI algorithm without human interaction for diagnosis or interpretation. The document does not describe a standalone algorithm performance test in the way it would be applied to AI/ML diagnostic software.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the cadaveric comparison testing, the "ground truth" implicitly relates to implant alignment accuracy and guide usability, compared against the results achieved using standard (non-PSI) instrumentation. The summary doesn't explicitly state how this ground truth was definitively established (e.g., by highly accurate post-operative CT measurements validated by multiple experts), but it refers to comparison rather than an absolute ground truth method.
8. The sample size for the training set
The document describes the device as being "designed with CT-based methods to produce patient-specific instrumentation." This suggests a design process based on anatomical data, but there is no mention of a "training set" in the context of an AI/ML algorithm. The device is a custom-manufactured surgical guide, not a learned AI model.
9. How the ground truth for the training set was established
Since there's no mention of a "training set" for an AI/ML algorithm, this question is not applicable in the context of the provided document. The "design" information would likely come from anatomical studies, engineering specifications, and clinical experience with total ankle arthroplasty, rather than a formal "ground truth" establishment for an AI training set.
§ 888.3110 Ankle joint metal/polymer semi-constrained cemented prosthesis.
(a)
Identification. An ankle joint metal/polymer semi-constrained cemented prosthesis is a device intended to be implanted to replace an ankle joint. The device limits translation and rotation in one or more planes via the geometry of its articulating surfaces and has no linkage across-the-joint. This generic type of device includes prostheses that have a talar resurfacing component made of alloys, such as cobalt-chromium-molybdenum, and a tibial resurfacing component made of ultra-high molecular weight polyethylene and is limited to those prostheses intended for use with bone cement (§ 888.3027).(b)
Classification. Class II.