Search Results

The HIT Clear Aligner system is indicated for the treatment of malocclusion in patients with permanent dentition. The HIT Clear Aligner system positions teeth by way of continuous gentle force.

A dental health care professional (e.g., orthodontist or dentist), using a standard personal computer prescribes the HIT Clear Aligner system based on an assessment of the patient's teeth, determines a course of treatment with the system, takes molds of the patient's teeth, and completes a prescription form.

The modification of the primary predicate device is a software system for orthodontic diagnosis and treatment simulation, HDH Treatment Planning software, utilized by CDB to design a series of plastic trays intended to gradually realign the patient's teeth in accordance with the physician's prescription. The software uses 3D scanned orthodontic models of a patient's dentition as input files serving as a base for diagnosing the orthodontic treatment needs, analyzing, inspecting, measuring, and simulating tooth movements, thereby allowing to create virtual treatment plans. The output of the treatment plan may be downloaded as files in STL format, a standard stereolithographic file format, or OBJ format, a standard 3D image format, for fabrication of dental casts, which may be used to fabricate sequential aligner trays or retainers.

The prescribing physician reviews and approves the treatment plan before the molds are produced. Once approved, CDB produces the trays, which are formed of clear, thin, thermoformed, copolyester plastic. The trays sent back to the dental health care professional, who then provides them to the patient, confirming fit and design. Over a period of months, additional trays are provided sequentially to the patient by the dental health professional to gradually move the target teeth to the desired position. The dental care professional monitors treatment from the moment the first aligner is delivered to when the final aligner is delivered. The trays are held in place by pressure and can be removed by the patient at any time.

This FDA 510(k) summary provides limited information regarding the acceptance criteria and the study proving the device meets those criteria, as it focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone performance study with specific acceptance criteria.

However, based on the provided text, here's what can be extracted and inferred:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics like sensitivity, specificity, accuracy, or quantitative measurements. Instead, it describes "performance testing" in a more general sense, specifically a "process qualification" to verify the accuracy of the final product.

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 a distinct "test set" sample size or data provenance for a performance study. The "process qualification" and "verification and validation testing" are mentioned, but details about the size and nature of the data used for these tests are absent. The focus is on the impact of the software modification rather than a new clinical performance study.

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 study described is a "process qualification" and software functional verification, not a clinical study involving expert interpretation for ground truth establishment. The prescribing physician reviews and approves the treatment plan, but this is part of the clinical use, not specifically ground truth establishment for a test set.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

This information is not provided, as a formal clinical test set requiring adjudication of ground truth is not 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

A multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned in this document. The device is a system for producing aligners, and the software component is for treatment planning, not for aiding human readers in diagnosis or interpretation that would typically be the subject of an MRMC study.

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

A standalone performance evaluation of the algorithm itself is implicitly suggested by the "Software testing has been performed within the process qualification procedure to verify the function of the HIT Clear Aligner". However, the document does not provide details on specific standalone metrics (e.g., accuracy of tooth movement prediction in a simulated environment) or quantitative results for the algorithm without human oversight. The software provides "calculation displaying the recommended sequential aligners staging" but its standalone predictive accuracy isn't quantified.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

For the "process qualification" and "verification and validation testing," the "ground truth" would implicitly be the preestablished specifications from the original submission (K191823) and the intended function of the software as designed. The software uses 3D scanned orthodontic models as input, and the output (STL/OBJ files for fabrication) is reviewed and approved by the "prescribing physician." Therefore, a combination of design specifications and expert (physician) review/approval forms the basis of verifying the system's output.

8. The sample size for the training set

This information is not provided. The document describes a software system for planning, not explicitly a machine learning model that would require a distinct "training set." If the software uses machine learning, the details of its training are not disclosed.

9. How the ground truth for the training set was established

This information is not provided, as a training set for a machine learning model is not explicitly mentioned or described as part of this submission.

Ask a specific question about this device