(161 days)
The KLS Martin Individual Patient Solutions (IPS) Planning System is intended for use as a software system and image segmentation system for the transfer of imaging information from a medical scanner such as a CT based system. The input data file is processed by the IPS Planning System and the result is an output data file that may then be provided as digital models or used as input to a rapid prototyping portion of the system that produces physical outputs including anatomical models, guides, splints, and case reports for use in maxillofacial surgery. The IPS Planning System is also intended as a pre-operative software tool for simulating / evaluating surgical treatment options.
The KLS Martin Individual Patient Solutions (IPS) Planning System is a collection of software and associated additive manufacturing (rapid prototyping) equipment intended to provide a variety of outputs to support reconstructive and orthognathic surgeries. The system uses electronic medical images of the patients' anatomy (CT data) with input from the physician, to manipulate original patient images for planning and executing surgery. The system processes the medical images and produces a variety of patient specific physical and/or digital output devices which include anatomical models, guides, splints and case reports.
The provided text describes the KLS Martin Individual Patient Solutions (IPS) Planning System and its regulatory clearance (K182789) by the FDA. However, it does not contain information about a study proving the device meets specific acceptance criteria in the context of an AI/algorithm's performance.
Instead, the document is a 510(k) summary demonstrating substantial equivalence to a predicate device (K181241), primarily to expand the patient population to include pediatric subgroups. The core of the device is a planning system involving commercial off-the-shelf (COTS) software and additive manufacturing for physical outputs, with human-in-the-loop interaction from trained employees/engineers and physicians.
Therefore, most of the requested information regarding AI acceptance criteria, performance metrics, sample sizes, ground truth establishment, expert adjudication, and MRMC studies is not present in the provided document. The device, as described, is not an AI algorithm in the sense that it performs automated diagnostic or treatment recommendations independently based on image analysis with defined metrics. It's a system to assist human planning processes.
Here's an analysis based on the information available in the document, and a clear indication of what is not available.
Acceptance Criteria and Device Performance (as far as applicable from the document)
The document focuses on demonstrating substantial equivalence, not on acceptance criteria for a freestanding AI algorithm's performance. The "performance" described is primarily related to material properties, biocompatibility, and sterilization, and the functioning of the software as a tool for human planning.
| Acceptance Criteria (Inferred from Substantial Equivalence and Safety/Performance) | Reported Device Performance (from document) |
|---|---|
| Material Degradation (Polyamide Guides) | Subject polyamide guides can withstand multiple sterilization cycles without degradation and can maintain 85% of its initial tensile strength. Demonstrates shelf life of 6 months. (p.10) |
| Titanium Device Equivalency | Additively manufactured titanium devices are equivalent to, or better than, titanium devices manufactured using traditional (subtractive) methods, leveraging data from reference device K163579. (p.10) |
| Biocompatibility | Biocompatibility endpoints (cytotoxicity, sensitization, irritation, chemical/material characterization) for both polyamide and titanium manufactured devices met pre-defined acceptance criteria (leveraged from predicate K181241 and reference K163579). (p.10) |
| Sterility Assurance Level (SAL) | Achieved an SAL of 10^-6 for each output device using the biological indicator (BI) overkill method for steam sterilization. Validations for polyamide and titanium leveraged from predicate K181241 and reference K163579. (p.10) |
| Pyrogenicity (Endotoxin Levels) | Endotoxin levels were below the USP allowed limit for medical devices and met pyrogen limit specifications, leveraging data from reference device K163579 for titanium. (p.10) |
| Software Functionality and Validation | Quality and on-site user acceptance testing provided objective evidence that all software requirements and specifications were implemented correctly and completely and are traceable to system requirements. Testing from risk analysis showed conformity with pre-defined specifications and acceptance criteria. Software documentation demonstrates mitigation of potential risks and performance as intended. (p.11, p.14) |
| Safety and Effectiveness in Pediatric Subpopulations | A risk assessment based on FDA guidance and supporting peer-reviewed clinical literature was performed. The conclusion is that expanding the patient population to neonates, infants, and children does not identify new issues of safety or effectiveness and the device is substantially equivalent to the predicate. (p.5, p.11, p.14) Note: This is a risk assessment and literature review, not a new clinical performance study. |
Information NOT Available in the Document (as it pertains to an AI/Algorithm performance study):
-
Sample size used for the test set and data provenance:
This information is not provided. The study performed was primarily non-clinical (material testing, biocompatibility, sterilization) and a risk assessment for pediatric use, not a clinical trial evaluating algorithm performance on a test set of patient data. -
Number of experts used to establish the ground truth for the test set and their qualifications:
Not applicable, as no dedicated test set for evaluating AI/algorithm performance against a ground truth is described. The system relies on physician input and interaction with trained employees/engineers for planning, not on an autonomous algorithmic output that requires expert adjudication for ground truth. -
Adjudication method for the test set:
Not applicable for the same reasons as above. -
If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
No, an MRMC comparative effectiveness study was not done. The document explicitly states: "Clinical testing was not necessary for the determination of substantial equivalence." (p.11, p.14). The device is a planning system with human-in-the-loop, not an AI intended to improve human readers' performance directly. -
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
No, a standalone algorithm performance study was not described. The device is presented as a "software system and image segmentation system" where "trained employees/engineers... manipulate data and work with the physician to create the virtual planning session." (p.4, p.13) The core function described is human-assisted planning and production of physical models, not an autonomous algorithmic output. -
The type of ground truth used:
Ground truth in the context of an AI algorithm's diagnostic or predictive performance is not relevant here, as no such AI is described. The "ground truth" for the device's function would relate to the accuracy of the generated physical models and plans relative to the patient's anatomy and surgical intent, which is managed through human interaction and validation within the system's intended use. -
The sample size for the training set:
Not applicable. The document refers to "commercially off-the-shelf (COTS) software applications" (p.4, p.13) which implies existing, validated software tools are being used, not a newly developed AI model requiring a separate training set. -
How the ground truth for the training set was established:
Not applicable, as no new training set for an AI model is described.
§ 872.4120 Bone cutting instrument and accessories.
(a)
Identification. A bone cutting instrument and accessories is a metal device intended for use in reconstructive oral surgery to drill or cut into the upper or lower jaw and may be used to prepare bone to insert a wire, pin, or screw. The device includes the manual bone drill and wire driver, powered bone drill, rotary bone cutting handpiece, and AC-powered bone saw.(b)
Classification. Class II.