Search Results

The Longeviti Static Cranial Implants are designed and manufactured individually for each patient to correct bony voids and/or defects of the cranium.

The Longeviti PMMA Static Cranial Implants are patient specific, implantable prosthetic cranioplasty plates intended to correct and/or restore bony voids and/or defects of the cranium. The implants are manufactured from polymethyl methacrylate materials and are designed using the patient's CT scan data. The devices are provided sterile and can be fixated to cranial bone using commercially available fasteners. Typical maximum single plate sizes do not exceed a total surface area of 411 cm2 and should have a nominal thickness of 4mm, not to exceed 5mm, to ensure physical integrity.

The provided documents are a 510(k) Premarket Notification from the FDA to Longeviti Neuro Solutions, LLC for their Longeviti PMMA Static Cranial Implant. This document does not contain information about an AI/ML-driven medical device or any study proving a device meets acceptance criteria related to AI/ML performance.

The content focuses on:

• Substantial Equivalence: The FDA's determination that the Longeviti PMMA Static Cranial Implant is substantially equivalent to legally marketed predicate devices (OsteoSymbionics Patient Specific Cranial Plate K133082 and OsteoSymbionics Patient Specific Cranial Implant K072601).
• Device Description: The device is a patient-specific, implantable prosthetic cranioplasty plate manufactured from polymethyl methacrylate (PMMA) materials using patient CT scan data.
• Indications for Use: To correct bony voids and/or defects of the cranium.
• Testing Summary: Primarily focused on sterilization validation (ISO-14937) and mechanical strength tests (ASTM D638-03, D790-03, D4812-06) to demonstrate material equivalence to the predicate device.

Therefore, I cannot fulfill your request as the provided text does not contain any of the information required to describe acceptance criteria or a study related to an AI/ML device's performance. There is no mention of an algorithm, AI, machine learning, test sets, ground truth establishment, expert review, MRMC studies, or standalone algorithm performance.

Ask a specific question about this device

The MedCAD AccuShape™ PEEK Patient Specific Cranial Implant is designed individually for each patient and intended to correct defects / replace bony voids in the cranial skeleton.

The MedCAD AccuShape™ PEEK Patient Specific Cranial Implant devices are individually sized and shaped implantable prosthetic cranioplasty plates intended to correct defects / replace voids in the cranial skeleton of a specific patient. The implants are designed using the patient's CT imaging data and precision manufactured from implantable grade polyether-ether-ketone (PEEK) material. The devices have a nominal thickness of 3mm, ranging from 2-5mm depending on the anatomical location. The device can be supplied as one or as multiple parts due to material constraints and/or the complexity of the device, with each part ranging in size from 10 x 10 (mm) to 200 x 200 (mm). The implants are provided with 2mm drainage holes spaced 10 mm apart from center to center with an edge margin of 10 mm. The devices are non-pyrogenic and are provided non-sterile for sterilization by the physician prior to implantation. The implants are attached to the native bone with commercially available cranioplasty fasteners.

This document describes the MedCAD AccuShape™ PEEK Patient Specific Cranial Implant, a device intended to correct defects or replace bony voids in the cranial skeleton. It is a Class II device (21 CFR 882.5330).

1. Table of Acceptance Criteria and Reported Device Performance

The provided text describes a 510(k) summary, which focuses on establishing substantial equivalence to predicate devices rather than setting specific performance acceptance criteria like diagnostic accuracy or sensitivity/specificity for an AI algorithm. In this context, "acceptance criteria" are related to demonstrating that the new device shares the same fundamental characteristics and safety/effectiveness profile as the legally marketed predicate devices.

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

This is not an AI/CADe type device that uses a "test set" in the conventional sense of evaluating an algorithm's performance on a dataset of patient images. Instead, this device is a patient-specific cranial implant. The "testing" involves demonstrating the physical and biological characteristics of the material and the manufacturing process, and confirming that the final product adheres to design specifications comparable to predicate devices.

• Sample Size for Non-Clinical Tests: Not explicitly stated as a number of patient cases. The description mentions "Biological laboratory tests including thorough sterilization validation have been conducted" and "Precision measurements have validated the dimensional accuracy and stability of the devices. In addition, material testing has been performed to demonstrate structural integrity." These are likely tests on material samples and manufactured devices, rather than a patient image test set.
• Data Provenance: Not applicable in the context of patient image data. The "data" here would be laboratory test results and manufacturing quality control data.

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

This is not applicable as there is no "test set" of patient cases for which an AI algorithm is generating a result that needs comparison to an expert-established ground truth. The device itself is the physical implant, designed and manufactured based on a patient's CT data. The "ground truth" for this type of device relates to engineering specifications, material properties, and biological compatibility.

4. Adjudication Method for the Test Set

Not applicable for a physical implant device where performance is established through non-clinical testing of materials and manufacturing processes, rather than an AI algorithm's output on a diagnostic test set.

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

Not applicable. This device is an implantable medical device, not an AI-assisted diagnostic or assistive tool for human readers interpreting medical images.

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

Not applicable. This is not an AI algorithm. Its design uses CAD (Computer-Aided Design) based on patient CT data, which is a common engineering process for custom implants, not an autonomous AI system delivering a diagnostic output.

7. The Type of Ground Truth Used

The "ground truth" for this device is based on engineering specifications, material science standards, and biological testing standards. Specifically:

• Confirmation of manufacturing precision and dimensional accuracy against design specifications.
• Validation of material properties (strength, stiffness, elasticity, density) against established PEEK material standards and predicate device characteristics.
• Demonstration of biocompatibility and sterility against recognized biological testing standards.

8. The Sample Size for the Training Set

Not applicable. This device does not involve machine learning or an AI algorithm that requires a "training set." The design process uses a patient's individual CT data, not a pre-trained model.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device