Search Results

The ProtoMED DigiGuide 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 DigiGuide System and the result is an output data file that is used as the input to a rapid prototyping portion of the system that produces physical outputs including templates for use in maxillofacial surgery. The DigiGuide System is also intended as a pre-operative software tool for simulating/evaluating surgical treatment options.

The ProtoMED DigiGuide System consists of a digital surgical plan (DigiPlan), applicable DigiGuide Templates, and optional anatomical models in order to plan and implement a maxillofacial surgery.

The ProtoMED DigiGuide System is primarily concerned with the manufacturing process and the dimensional accuracy of the physical outputs (models and templates) derived from digital imaging data. The provided document does not detail specific acceptance criteria or a study related to the clinical or diagnostic performance of a software algorithm in a human-in-the-loop or standalone scenario as might be expected for an AI/ML powered medical device. Instead, the focus is on process validation, material biocompatibility, and sterilization, which are standard for manufacturing medical devices.

Therefore, many of the typical questions for AI/ML device performance summarized in the table below cannot be directly answered from this document.

Acceptance Criteria and Reported Device Performance

Study Details (as far as can be gleaned from the document):

The document describes Verification and Validation testing rather than a traditional "study" in the context of clinical or diagnostic performance.

1. Sample size used for the test set and the data provenance:

   • The document mentions "use STL files from patient anatomy as input" for validation. However, it does not specify the number of patient cases or STL files used in this testing.
   • The data provenance (e.g., country of origin, retrospective/prospective) is not specified. It is likely retrospective, using existing patient CT scans.

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

   • No information is provided about experts used to establish a "ground truth" for a test set in the traditional sense of diagnostic accuracy.
   • The development of the "DigiPlan" involves a "physician in conjunction with company technicians," and later, "ProtoMED engineers, technicians, and the physician" for virtual movement of anatomy. This implies clinical input in the creation of the plan, but not necessarily for independent ground truth assessment of a test set.

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

   • No adjudication method is described as there isn't a stated independent expert review or ground truth establishment for a test set.

4. 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 comparative effectiveness study was conducted or described. The device is a planning and manufacturing system for surgical guides, not an AI-assisted diagnostic tool for human readers.

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

   • No standalone performance study of an algorithm is described in terms of diagnostic or clinical accuracy. The "DigiGuide System" involves a collaborative process between company technicians/engineers and a physician, and its performance is assessed via dimensional accuracy and equivalency, not standalone algorithmic output interpretation.

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

   • The "ground truth" for the dimensional accuracy of the outputs appears to be the input STL files of patient anatomy and the ability to demonstrate "dimensional and clinical equivalency" through "overlay of parts for comparison analysis." This is effectively comparing the manufactured product to the digital design.

7. The sample size for the training set:

   • No information is provided on a "training set" as this is not an explicitly AI/ML software development where a model is trained on data. The software processes input data, but there's no mention of a learning algorithm requiring a training set.

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

   • Not applicable, as no training set is described.

Ask a specific question about this device

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 computerized tomography (CT) medical scan. 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 and case reports for use in the marking of cranial surgery. The IPS Planning System is also intended as a pre-operative software tool for simulating 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 cranial 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, and case reports for use in the marking of cranial bone in cranial surgery.

The KLS Martin Individual Patient Solutions (IPS) Planning System is a software system and image segmentation system used for transferring imaging information from a CT scan. The system processes input data to produce output data files, which can be digital models or physical outputs like anatomical models, guides, and case reports for cranial surgery. It is also a pre-operative software tool for simulating surgical treatment options.

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document does not explicitly state the sample sizes used for the non-clinical performance tests (tensile, bending, biocompatibility, sterilization, pyrogenicity, software V&V). The data provenance for these tests is internal to the manufacturer, as they were "performed on the subject polyamide guides," "conducted on devices manufactured from polyamide," and for titanium, "leveraged from the reference device." This indicates the studies were likely conducted in a controlled lab or manufacturing environment. The studies are not described as retrospective or prospective clinical studies, but rather as non-clinical engineering and material performance tests.

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

This information is not applicable. The device is a planning and segmentation system that outputs digital models or physical guides/anatomical models. The acceptance criteria and performance data described relate to the physical and software characteristics of these outputs (e.g., material strength, sterility, software functionality), not to a diagnostic or treatment outcome for which expert ground truth would be established from patient data. The process involves a physician providing input for model manipulation and interactive feedback, but this is part of the planning workflow, not establishing ground truth for a test set in the context of algorithm performance.

4. Adjudication Method for the Test Set:

This information is not applicable, as the described studies are non-clinical performance tests focused on material properties, sterility, and software functionality, not on qualitative assessments requiring adjudication from expert readers.

5. 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."

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

Yes, the "Software Verification and Validation" section describes testing of individual software applications. This indicates a standalone assessment of the software's performance in implementing requirements and specifications, separate from a human-in-the-loop clinical scenario.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.):

For the non-clinical tests:

• Tensile & Bending Testing: Ground truth is based on established engineering standards and material science principles (e.g., 85% retention of initial tensile strength after sterilization, comparison to traditional manufacturing methods).
• Biocompatibility Testing: Ground truth refers to pre-defined acceptance criteria in accordance with ISO 10993-1.
• Sterilization Testing: Ground truth is based on achieving a sterility assurance level (SAL) of $10^{-6}$ as per ISO 17665-1:2006.
• Pyrogenicity Testing: Ground truth is based on meeting USP allowed limits for endotoxin levels (< 2.15 EU/device) and pyrogen limit specifications.
• Software Verification & Validation: Ground truth is defined by "all software requirements and specifications" and "pre-defined specifications and acceptance criteria" derived from user requirements and risk analysis.

8. The Sample Size for the Training Set:

The document does not mention a training set. This device is described as utilizing a collection of software and additive manufacturing equipment for planning and producing physical outputs based on patient CT data, not a machine learning model that would require a dedicated training set. The software applications used (Materialise Mimics, Geomagic® Freeform Plus™) are "comedically off-the-shelf (COTS) software applications," implying they were developed and validated independently, prior to their integration into this system.

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

This information is not applicable, as there is no mention of a training set for a machine learning algorithm in the context of this device.

Ask a specific question about this device