(73 days)
Blue Sky Bio Computerized Orthodontic Bracket System is a software system intended for use as an aid in orthodontic treatment planning to correct malocclusions in orthodontic patients. For use by dental professionals trained in orthodontic treatment, including radiographic analyses and treatment planning. Blue Sky Bio Computerized Orthodontic Bracket System is intended for use with commercially available brackets currently used in standard orthodontic treatment. The end product is an indirect bonding tray for use by the dental professional to place multiple brackets at the same time.
The device consists of proprietary software that calculates the ideal position of the dental brackets based on the dental impressions and or 3D models supplied by the patient's orthodontist. Commercially available brackets are used as part of the system.
The Blue Sky Bio Computerized Orthodontic Bracket System is a software system intended to aid in orthodontic treatment planning. The information provided outlines the device's substantial equivalence to a predicate device, but does not provide specific acceptance criteria or a dedicated study proving performance against those criteria. Instead, it describes general testing for accuracy and software verification.
Here's a breakdown of the available information based on your questions:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Inferred) | Reported Device Performance |
|---|---|
| Accuracy of Data Transfer | "All samples met the performance criteria." |
| Verified by scanning and digitizing physical models and comparing scanned 3D models with 3D models generated by the software. | |
| Accurate Bracket Placement | "Testing was conducted verifying that the treatment plan performed in the software resulted in accurate placement of the brackets and corresponded to the treatment plan in Blue Sky Bio software." |
| Software Verification and Validation | "Software verification and validation testing were conducted... Documentation was provided as recommended by FDA's Guidance..." (The software was considered a "moderate" level of concern). |
Note: The document does not explicitly state numerical acceptance criteria (e.g., specific thresholds for deviation in bracket placement). The performance is reported as meeting general criteria or being confirmed.
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The document does not specify the sample size used for the performance testing or software verification and validation. It only mentions "All samples met the performance criteria." The data provenance (country of origin, retrospective/prospective) is also not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)
This information is not provided. The method for establishing ground truth for the "accurate bracket placement" or "accuracy of data transfer" testing is not detailed in terms of expert involvement or qualifications.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
This information is not provided. The document describes internal testing and software verification, but no external expert adjudication process is detailed.
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
There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study being performed. The device is a software system for treatment planning, not an AI for diagnostic interpretation by human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The performance testing described ("Testing was conducted verifying that the treatment plan performed in the software resulted in accurate placement of the brackets") appears to be a standalone assessment of the software's ability to generate an accurate treatment plan. However, the system is always intended for use by dental professionals "as an aid in orthodontic treatment planning," implying that human-in-the-loop is part of its intended use. The "accuracy of data transfer" testing also seems to be a standalone evaluation of the software's data handling.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document implies the ground truth for the "accuracy of data transfer" was established by comparison with scanned physical models and 3D models generated by the software, likely based on predetermined, ideal bracket positions. For the "accurate bracket placement," the ground truth was also based on the "treatment plan in Blue Sky Bio software," suggesting an internal consistency check against the planned outcome, which is initially informed by the clinician's detailed treatment plan. There's no mention of external validation against pathology or patient outcomes data.
8. The sample size for the training set
This information is not provided. The document focuses on performance testing and software verification, not on the details of algorithm training. Given it's a "Computerized Orthodontic Bracket System" and not explicitly termed an "AI" or "machine learning" system, it might be a rules-based or CAD-like system, rather than one requiring a large training dataset for a learning algorithm.
9. How the ground truth for the training set was established
This information is not provided, as details about a training set are absent.
§ 872.5470 Orthodontic plastic bracket.
(a)
Identification. An orthodontic plastic bracket is a plastic device intended to be bonded to a tooth to apply pressure to a tooth from a flexible orthodontic wire to alter its position.(b)
Classification. Class II.