Search Results

The Nextremity Solutions DuoHex™ CH Cannulated Hammertoe System is intended for small bone reconstruction limited to inter-phalangeal repair and fusion of the lesser toes.

The DuoHex™ CH Cannulated Hammertoe System consists of a two-part cannulated bone screw implant construct. The screw implants are provided in various sizes. The proximal screw implant diameters range from 2.75mm to 4.2mm. The middle screw implant diameters range from 2.75mm to 5.0mm in increments of 0.75mm. The proximal and distal screw implants are manufactured from Ti-6Al-4V ELI conforming to ASTM F136. The system offers an optional fixation method using a Kirschner wire (K-wire) in conjunction with the screw implants for additional fixation and temporary stabilization. The K-Wire is intended to be removed at the discretion of the physician upon joint fusion. The k-wires provided are manufactured from 316 Stainless Steel conforming to ASTM F138. The system includes the necessary surgical site preparation and insertion instruments.

This document describes a medical device, the DuoHex™ CH Cannulated Hammertoe System, and its clearance by the FDA based on substantial equivalence to predicate devices. It does not present clinical performance data or studies against specific acceptance criteria for AI/ML-driven medical devices.

Therefore, I cannot provide the details requested in your prompt for acceptance criteria and study data for an AI/ML device. The provided text is a 510(k) summary for a non-AI/ML medical device (bone screw system) and primarily relies on mechanical testing and comparison to existing products for substantial equivalence.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• The document explicitly states: "Clinical testing was not necessary to demonstrate substantial equivalence of the DuoHex™ CH Cannulated Hammertoe System to the predicate device." This means no clinical study was performed to "prove the device meets the acceptance criteria" in the way you've described for an AI/ML system.
• The device is a "Bone Screw System" for hammertoe correction, a mechanical implant, not an AI/ML diagnostic or therapeutic guidance tool.
• The "Non-Clinical Testing" section describes mechanical and material tests (axial pull-out strength, torque to failure, static/dynamic 3-point bend tests) and endotoxin testing, not performance metrics like sensitivity, specificity, or AUC as would be relevant for an AI/ML system.

To answer your request, if this were an AI/ML device, and assuming a hypothetical scenario where the document would contain the necessary information, a typical response would look like this (but again, this is NOT supported by the provided text):

Hypothetical Acceptance Criteria and Study for an AI/ML-Driven Hummer Toe Diagnostic System (Illustrative - NOT based on the provided document)

Let's imagine, for the sake of demonstrating the structure, that the DuoHex™ CH system included an AI component that diagnosed hammertoe severity from medical images.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The actual document does not contain any such performance metrics as it's for a mechanical device.

2. Sample Size and Data Provenance

• Test Set Sample Size: 500 patient cases (e.g., foot X-rays)
• Data Provenance: Retrospective data collected from multiple clinical sites across the United States and Europe (e.g., Germany, UK).

Note: The actual document does not mention any test set or data provenance in this context.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: 3 independent orthopedic radiologists.
• Qualifications: Each radiologist had at least 15 years of experience specializing in musculoskeletal imaging, with a focus on foot and ankle pathologies. All were board-certified in their respective countries.

Note: The actual document does not mention any experts for ground truth establishment.

4. Adjudication Method for Test Set

• Adjudication Method: 2+1 Adjudication. If at least two out of three experts agreed on a diagnosis (e.g., severity of hammertoe), that was considered the provisional ground truth. In cases of disagreement (e.g., 1-1-1 split), a fourth senior orthopedic surgeon (with 25+ years experience) acted as a tie-breaker/final adjudicator.

Note: The actual document does not mention any adjudication method.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was an MRMC study done? Yes.
• Effect Size of Human Reader Improvement:
  • Without AI assistance: Average diagnostic accuracy of human readers was 78%.
  • With AI assistance (AI-assisted read): Average diagnostic accuracy of human readers improved to 89%.
  • Effect Size: The AI assistance led to an average increase of 11 percentage points in diagnostic accuracy for human readers (p < 0.001, 95% CI: [9.5%, 12.5%]). This represents a significant improvement in reader performance.

Note: The actual document does not mention any MRMC study or AI assistance.

6. Standalone Algorithm Performance

• Was standalone performance done? Yes.
• Standalone Performance Metrics:
  • Sensitivity: 91.8%
  • Specificity: 86.5%
  • AUC: 0.92

Note: The actual document does not mention any standalone algorithm performance.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus based on clinical examination, high-resolution MRI scans, and follow-up surgical pathology reports when available for definitive confirmation of hammertoe severity and presence.

Note: The actual document does not mention any ground truth type in this context.

8. Sample Size for the Training Set

• Training Set Sample Size: 10,000 anonymized patient cases (X-rays, medical reports).

Note: The actual document does not mention any training set.

9. How Ground Truth for Training Set Was Established

• Ground Truth for Training Set: Established by an internal team of 10 experienced orthopedic specialists (orthopedic surgeons and radiologists) who labeled the image data and associated clinical information. A subset of these labels (10%) was independently reviewed by a senior specialist for quality assurance. Data was semi-automatically labeled using a pre-trained model and then manually refined and verified by the experts.

Note: The actual document does not mention ground truth for a training set.

In conclusion, the provided FDA clearance letter and 510(k) summary are for a mechanical bone screw system and do not contain any information related to AI/ML device performance, acceptance criteria, or clinical studies of the type you are asking about.

Ask a specific question about this device