Search Results

The SimPlant Immediate Smile System is intended for use in treatment planning and placement of dental implants, in order to restore masticatory function.

The SimPlant Immediate Smile System is intended for use in treatment planning and placement of dental implants, in order to restore masticatory function. The SimPlant Immediate Smile System enables a predictable dental implant restoration procedure according to case planning done by the clinician.

The SimPlant Immediate Smile System enables a provisional prosthesis to be produced prior to and attached in the same session as implant installation.

The SimPlant Immediate Smile System includes SimPlant software that provides a method of importing medical imaging information from radiological imaging systems such as a Computer Tomography (CT) or Magnetic Resonance Imaging (MRI) to a computer file that is usable in conjunction with other diagnostic tools and expert clinical judgment. Visual representations of the imaged anatomical structures (e.g. the jaw) are derived, allowing for a three-dimensional assessment of the patient without patient contact. SimPlant enables the clinician to plan the dental implant positions including orientations pre-operatively in a virtual, 3D environment. The case planning can be used to produce patient specific SurgiGuide guides, thus transferring the virtual case planning into physical tools enabling the intra-operative preparation of the implant sites for the installation of implants in accordance to the virtual case planning.

The SimPlant Immediate Smile System is based upon knowledge of the locations and orientations of the implants prior to surgery. This knowledge enables the production of a SurgiGuide surgical guide. Aided by the SurgiGuide surgical guide, the implant sites can be prepared and the dental implants placed in the predetermined locations, enabling the immediate installation of the custom-made prefabricated provisional Immediate Smile bridge.

The SimPlant Immediate Smile System is a medical device intended for use in treatment planning and placement of dental implants. The device includes SimPlant software for image processing and pre-operative planning, and enables the production of patient-specific SurgiGuide surgical guides and prefabricated provisional Immediate Smile bridges.

Here's an analysis of the acceptance criteria and study data provided:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes and Data Provenance

• Test Set (Clinical Evaluation):
  • Sample Size: 20 patients
  • Data Provenance: Clinical setting, "different countries" (retrospective or prospective not specified, but the phrase "Case follow-up was done after 12 weeks" suggests it was a prospective study).
• Test Set (Bench Top Testing / Engineering Tests):
  • Specific sample sizes for individual bench tests (e.g., number of bridges for fracture, number of abutments for pull-out) are not provided, only the general statement that "Several Engineering tests and evaluations were undertaken."
• Training Set: Not explicitly mentioned in the provided text. The software validation refers to testing against "specifications," but a distinct "training set" for an AI/algorithm is not discussed in the context of this device. This suggests the device is likely rule-based or uses traditional image processing, rather than a machine learning model that requires a labeled training set in the modern sense.

3. Number of Experts and Qualifications for Ground Truth

• Clinical Evaluation: 11 doctors from different countries. Their specific qualifications (e.g., experience level, specialization beyond "doctor") are not detailed.
• Bench Top Testing / Engineering Tests: Not applicable, as ground truth for these tests is based on physical measurements and engineering specifications, not expert interpretation.
• Software Validation: "The software is validated together with end-users." The number and qualifications of these "end-users" are not specified.

4. Adjudication Method for the Test Set

• Clinical Evaluation: The text states, "Clinical feedback was gathered for all cases relative to the usability, aesthetic result and adequacy of the material properties of the system components. Predefined acceptance thresholds were met for all criteria indicative for the system safety and effectiveness." This implies that the feedback from the 11 doctors was aggregated and compared against predefined thresholds. There's no mention of a formal adjudication method (like 2+1 or 3+1 consensus) for individual cases or disagreements among the doctors.
• Bench Top Testing / Software Validation: Not applicable, as these tests rely on objective measurements and predefined specifications.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study to measure the effect size of human readers improving with AI vs. without AI assistance was not reported. The study focused on the clinical evaluation of the system (including the software and physical components) by doctors in a clinical setting, rather than comparing human reader performance with and without the AI component. The device is for treatment planning and guide fabrication, not for diagnostic interpretation by human readers.

6. Standalone Performance Study

• Yes, a standalone performance assessment of the algorithm/software (without direct human-in-the-loop performance measurement) was conducted through "Software Validation" and "bench top performance testing."
  • Software Validation: "The software is thoroughly tested in accordance with documented test plans and in accordance to internal software development and testing procedures. This test plan is derived from the specifications and ensures that all controls and features are functioning properly. The software is validated together with end-users."
  • Bench Top Performance Testing: This included evaluations of the connection dimensions, predicted micro-movement, and cement bonding, which are standalone assessments of the physical components designed or influenced by the software.

7. Type of Ground Truth Used

• Clinical Evaluation: Clinical feedback from 11 doctors and follow-up data (after 12 weeks) served as the primary ground truth for usability, aesthetic results, material adequacy, and overall safety and effectiveness. This is a form of expert assessment/outcomes data.
• Bench Top Testing / Engineering Tests: Ground truth was based on engineering specifications, physical measurements, and predictive models (e.g., for micro-movement).
• Software Validation: Ground truth was based on predefined specifications for software functionality and controls.

8. Sample Size for the Training Set

• Not explicitly mentioned. The nature of the device (treatment planning software and physical guides) suggests it might not rely on a machine learning model that typically uses a "training set" in the same way as, for example, an image classification AI. The software is described as using "medical imaging information" to derive "visual representations of the imaged anatomical structures," implying a more traditional computational geometry and image processing approach.

9. How the Ground Truth for the Training Set Was Established

• Not applicable, as a distinct training set and its associated ground truth establishment method are not described for this device. The software's functionality is validated against specifications that presumably stem from anatomical knowledge and clinical requirements.

Ask a specific question about this device