FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

Comminuted fractures of the calcaneus
Post-traumatic osteoarthritis and/or poor function resulting from calcaneal fracture sequelae
Osteoarthritis of the posterior subtalar joint, or
Valgus flatfoot deformities

Device Description

The CalcaNail is orthopaedic nail for the repair of articular fractures of the calcaneus. The device consists of an orthopedic titanium 12 mm nail available in 3 lengths (65 mm, 75 mm and 85 mm) for subtalar arthrodesis. The system also includes a series of 5 mm cannulated screws for fixation available in 17 lengths (24 mm - 80 mm)

AI/ML Overview

This document is a 510(k) premarket notification for the CalcaNail Orthopedic Arthrodesis Nail, a medical device for subtalar arthrodesis. The information provided outlines the device, its intended use, and its comparison to predicate devices, but it does not contain acceptance criteria for device performance in the typical sense of a clinical trial or performance study on a new AI/software device. Instead, the "study" described is a biomechanical bench test and an engineering simulation comparing the CalcaNail to existing predicate devices for substantial equivalence.

Here's an analysis of the provided text based on your request, with the understanding that this is a hardware device submission, not an AI/software performance study. Therefore, many of your requested points related to AI/software performance metrics, ground truth, and expert evaluation are not directly applicable.

Acceptance Criteria and Device Performance (Based on presented data)

Since this is a hardware device submission and not a software/AI performance study, there aren't "acceptance criteria" in terms of sensitivity, specificity, or AUC. Instead, the acceptance criteria are implicit in demonstrating substantial equivalence to predicate devices through mechanical performance. The "reported device performance" refers to the results of the biomechanical and engineering tests.

Acceptance Criteria (Implicit for Substantial Equivalence)	Reported Device Performance
Biomechanical Stability	The CalcaNail showed better primary stability at the chosen experimental set-up of a standardized calcaneal fracture compared to the standard Synthes calcaneal locking plate (K991407).
Rigidity	The engineering simulation demonstrated that the CalcaNail provided much greater rigidity than the FHI cannulated screws (K070617) used routinely in rear foot deformity surgery, when comparing moments of inertia of the smallest cross-sections.
Material Equivalence	Manufactured from titanium, similar to predicate devices.
Intended Use Equivalence	Subtalar arthrodesis for comminuted calcaneus fractures, post-traumatic osteoarthritis, osteoarthritis of posterior subtalar joint, and valgus flatfoot deformities, which is similar to predicate devices (Synthes calcaneal locking plate K991407, FHI cannulated screws K070617, NewDeal Panta Nail K091788) all indicated for use in the foot, ankle, and calcaneus, including subtalar arthrodesis.
Safety and Effectiveness	Bench testing and device description confirm that the subject CalcaNail demonstrates no new issues of safety or effectiveness compared to predicate devices for treating old and recent fractures of the heel bone joint and hind foot deformity surgery.

Study Proving Device Meets Acceptance Criteria:

The study proving the device meets the implicit acceptance criteria for substantial equivalence consists of two parts:

Biomechanical Bench Testing: This involved a direct comparison of the CalcaNail to a predicate device in terms of mechanical stability.
Engineering Simulation: This involved a comparison of rigidity between the CalcaNail and another predicate device using engineering principles.

Detailed Information for Each Point (as far as extract allows):

Sample size used for the test set and the data provenance:
- Biomechanical Testing: "Seven pairs of (total of 14) enzymatically corroded human calcaneal and talar bones" were used.
- Data Provenance: The origin of the human bones is not specified (e.g., country of origin). The study appears to be prospective (bench test designed for this submission), not retrospective clinical data.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This is not applicable as the "test set" consists of physical bones and engineering models, not data requiring expert interpretation for ground truth in the context of an AI/software device. The integrity of the bones and the setup of the biomechanical test would typically be managed by engineers and biomechanics experts, but these are not "ground truth experts" in the clinical sense.
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not applicable. This concept pertains to resolving discrepancies among expert readers in clinical data annotation, which is not relevant for a biomechanical bench test or engineering simulation.
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, a multi-reader multi-case comparative effectiveness study was not done. This is a hardware device, not an AI/software diagnostic tool.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- No. This concept is for AI algorithms. The "standalone" performance here relates to the inherent mechanical properties of the nail itself.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the biomechanical test, the "ground truth" is the measured mechanical stability of the construct under simulated loading conditions.
- For the engineering simulation, the "ground truth" is the calculated moment of inertia and derived rigidity based on established engineering principles and material properties.
- Neither of these involves clinical expert consensus, pathology, or outcomes data.
The sample size for the training set:
- Not applicable. This is a medical device (hardware) submission, not an AI/machine learning model where a "training set" would be used. The design of the nail is based on engineering principles and knowledge, not data training.
How the ground truth for the training set was established:
- Not applicable, as there is no "training set" in the context of an AI/ML model for this hardware device. The device design is based on engineering and anatomical considerations.

Summary

Regulation Number and Section

§ 888.3020 Intramedullary fixation rod.

(a)
Identification. An intramedullary fixation rod is a device intended to be implanted that consists of a rod made of alloys such as cobalt-chromium-molybdenum and stainless steel. It is inserted into the medullary (bone marrow) canal of long bones for the fixation of fractures.(b)
Classification. Class II.