(54 days)
This device is intended for medical purposes to apply pressure to prominent regions of an infant's cranium to improve cranial symmetry or shape. To treat infants from three to eighteen months of age with moderate to severe non-synostotic positional plagiocephaly, including plagiocephalic-, brachycephalic-, scaphocephalic-shaped heads.
The DOC Band is a cranial orthosis used to treat positional or deformational plagiocephaly in infants from 3 to 18 months of age. The devices works by applying a gentle holding pressure to the prominent regions of an infants' skull while leaving room for growth in the adjacent flattened regions. The orthosis is made from a three-dimensional (3D) digital model of an infants' cranium acquired with the C3D - Cranial Imaging System™. This system was developed to capture an accurate, 3D image of an infants' head shape. It is based upon the well-established field of photogrammetry, and utilizes structured light and triangulated CCD cameras to digitally reproduce the 3D model. The system uses a noncoherent (i.e. non-laser light) light source, and captures a complete 3D image of the infants' head-shape, including the face and top of the head, in 1/180th of a second with an accuracy of +/- 0.5 mm. During acquisition, a 3D photograph of the child is also captured and precisely laid over the model for confirmation of the patient's identity. The digital model is then sent electronically to Cranial Technologies who creates a positive model using computer aided machining software and a 5-axis CNC mill. The positive model is then used to create the DOC Band, which is fit clinically and monitored as described in K-964992.
This document describes the DOC Band, a cranial orthosis (helmet) used to treat positional plagiocephaly in infants. The provided text, however, does not contain a study that proves the device meets specific acceptance criteria in the manner typically described for modern medical devices, especially AI-driven ones. Instead, it focuses on demonstrating substantial equivalence to a previously cleared device.
Here's an analysis based on the provided text, addressing your points where possible, and highlighting what is not present:
Missing Information: It is crucial to understand that the provided text is a 510(k) summary (from 2002) for the DOC Band. This type of submission relies heavily on demonstrating substantial equivalence to a predicate device, rather than providing detailed, de novo clinical study results against predefined acceptance criteria, particularly for performance metrics like sensitivity, specificity, or improvement with AI assistance. The focus here is on the safety and effectiveness of the orthosis itself and the imaging system used to create it, not on an algorithm's diagnostic performance for which "acceptance criteria" and "study results" in the AI sense would be reported.
1. Table of Acceptance Criteria and Reported Device Performance
Because this is a substantial equivalence submission for a physical medical device (a cranial orthosis) and an imaging system for its creation, not an AI diagnostic algorithm, the typical "acceptance criteria" and "performance" metrics (like sensitivity, specificity, AUC) you'd expect are not present.
The key "performance" mentioned for the C3D - Cranial Imaging System™ (which creates the 3D model for the DOC Band) is its accuracy:
| Acceptance Criteria / Performance Metric | Reported Device Performance |
|---|---|
| C3D - Cranial Imaging System™ Accuracy | +/- 0.5 mm |
Note: The DOC Band itself is described as substantially equivalent to prior versions, implying it meets the same safety and effectiveness standards as those established devices. The "performance" of the DOC Band is the clinical outcome of correcting cranial asymmetry, but the document does not quantify this with specific acceptance criteria (e.g., "reduce asymmetry by X% in Y% of patients"). It relies on the clinical evidence of the predicate device (K-964992).
Relevant Sections from the Text:
- VII. Description: "The system uses a noncoherent (i.e. non-laser light) light source, and captures a complete 3D image of the infants' head-shape, including the face and top of the head, in 1/180th of a second with an accuracy of +/- 0.5 mm."
- X. Substantial Equivalence: "The DOC Band is substantially equivalent and virtually identical to the original DOC Band described in K964992..."
- XI. Clinical Discussion and Literature references and reprints: "Clinical Discussion and Literature references and reprints showing the safety and effectiveness of this device when used under the Special Controls prescribed by the FDAwere provided in the original 510(k)-K964992."
2. Sample size used for the test set and the data provenance
Not applicable/Not provided in this document. This submission document does not detail a "test set" for an algorithm's performance. The "accuracy of +/- 0.5 mm" for the C3D imaging system is stated as a specification, likely derived from internal testing or engineering validation, not a clinical test set in the context of AI performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable/Not provided in this document. No "test set" in the AI sense is described. The ground truth for the overall device effectiveness (the DOC Band) is the historical clinical acceptance of "safety and effectiveness" as shown in the predicate 510(k) (K-964992) and literature references, which would implicitly involve clinical experts.
4. Adjudication method for the test set
Not applicable/Not provided in this document. No "test set" requiring adjudication for an algorithm is described.
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.
No. The device is a physical orthosis and an imaging system. It is not an AI diagnostic tool intended to assist human readers in interpreting medical images or data. Therefore, an MRMC study and effects of AI assistance are not relevant to this submission.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
No. The C3D - Cranial Imaging System™ is a data acquisition device, not a standalone diagnostic algorithm. The DOC Band itself is a treatment device, not an algorithm.
7. The type of ground truth used
For the C3D - Cranial Imaging System™: The "accuracy of +/- 0.5 mm" (for 3D imaging) would likely be established against a physical measurement standard or a high-precision reference model through engineering validation, rather than an expert consensus or pathology in a clinical sense.
For the DOC Band: The "safety and effectiveness" referenced in the predicate 510(k) (K964992) would be based on clinical outcomes (e.g., improvement in cranial symmetry/shape) as observed by clinicians. This would be a form of outcomes data or expert clinical assessment from prior studies.
8. The sample size for the training set
Not applicable/Not provided in this document. No training set for an AI algorithm is mentioned as the C3D system is based on photogrammetry, which is a well-established field, not a machine learning model that requires a "training set" in the modern AI sense.
9. How the ground truth for the training set was established
Not applicable/Not provided in this document. No training set described.
§ 882.5970 Cranial orthosis.
(a)
Identification. A cranial orthosis is a device that is intended for medical purposes to apply pressure to prominent regions of an infant's cranium in order to improve cranial symmetry and/or shape in infants from 3 to 18 months of age, with moderate to severe nonsynostotic positional plagiocephaly, including infants with plagiocephalic-, brachycephalic-, and scaphocephalic-shaped heads.(b)
Classification. Class II (special controls) (prescription use in accordance with § 801.109 of this chapter, biocompatibility testing, and labeling (contraindications, warnings, precautions, adverse events, instructions for physicians and parents)).