Search Results

SIMPLANT Online Case Review and SIMPLANT Editor are indicated for use as medical front-end software that can be used by medically trained people for the purpose of visualizing gray value images. These are intended for use as preoperative software programs for generating and reviewing plans for dental implant placement and surgical treatment.

The proposed devices, SIMPLANT Online Case Review and SIMPLANT Editor, are software intended for pre-operative planning to generate and review plans for dental implant placement and surgical treatment, without patient contact.

SIMPLANT Online Case Review is a web application used for review and approval of dental implant plans provided by DENTSPLY Implants. SIMPLANT Online Case Review can also be used in combination with the desktop software application SIMPLANT Editor when an implant plan, provided by DENTSPLY Implants, is edited by the dental professional.

The software SIMPLANT Online Case Review and SIMPLANT Editor are used by dental professionals with clinical experience in implant surgery as well as training in medical image review.

Implant plans, in the format of SIMPLANT project files are created by DENTSPLY Implants and made available to the dental professional. The SIMPLANT project is created by DENTSPLY Implants using dental professional supplied patient image data, patient information and implants data developed by DENTSPLY Implants which are merged together. The SIMPLANT project is the basis for implant surgery planning by dental professionals.

The dental plan, which is the result of the dental implant planning process, can be used for manufacturing a surgical guide or for evaluation of treatment options by the dental professional during the implant surgery procedure.

This document describes the SIMPLANT Online Case Review and SIMPLANT Editor devices, focusing on their intended use as medical front-end software for dental implant planning and review. Unfortunately, the provided text does not contain the specific details about acceptance criteria or a dedicated study proving device performance against those criteria in a quantitative manner.

However, it does describe the software testing performed as part of the verification and validation process, which generally aims to ensure functionality and compatibility.

Here's an attempt to answer your questions based on the available information, with specific notes where information is missing:

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

The document does not explicitly state specific quantitative acceptance criteria for device performance (e.g., accuracy, precision as defined by a specific metric and threshold). It mentions that "Verification and validation testing confirms that all user needs and performance requirements according to the design input are fulfilled." This suggests that acceptance criteria would be tied to these "user needs and performance requirements," but these are not detailed in the provided text.

The "reported device performance" is described broadly as confirming "the functionality, safety and efficacy of the proposed devices" and that they are "substantially equivalent" to the predicate. No numerical performance metrics are given.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not provided in the document. The text states:

"The SIMPLANT project is created by DENTSPLY Implants using dental professional supplied patient image data, patient information and implants data developed by DENTSPLY Implants which are merged together."

This indicates that patient image data is used, but details on the size, origin, or nature (retrospective/prospective) of this data for the test set are absent.

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 in the document. The text mentions "dental professionals with clinical experience in implant surgery as well as training in medical image review" will use the software, but it doesn't specify if such experts were involved in establishing ground truth for testing, or if so, how many or their specific qualifications.

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

This information is not provided in the document.

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

This information is not provided in the document. The document focuses on the software as a tool for planning and review, implying human-in-the-loop, but does not describe any MRMC studies comparing human performance with and without the device. The device itself is described as "medical front-end software," not an AI-assisted diagnostic tool in the sense of providing automated interpretations.

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

The devices, SIMPLANT Online Case Review and SIMPLANT Editor, are described as "medical front-end software" and tools for "visualizing gray value images" and "generating and reviewing plans for dental implant placement and surgical treatment" by "medically trained people" and "dental professionals." This strongly suggests a "human-in-the-loop" application, not a standalone algorithm without human involvement. Therefore, a standalone performance study as typically understood for an AI algorithm is unlikely to have been performed or necessary for this type of device based on its description.

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

This information is not explicitly provided in the document. Given the nature of the device (pre-operative planning), ground truth would typically refer to the correctness of the implant plan or the visualizations. However, how this correctness was established for testing is not detailed.

8. The sample size for the training set

Given that SIMPLANT Online Case Review and SIMPLANT Editor are described as software for visualizing, generating, and reviewing plans, and their predicate's functions largely involve image processing and 3D modeling, it's unclear if a "training set" in the context of machine learning (AI) was even used. The document does not mention machine learning or AI models, but rather standard software development and verification processes.

If there were indeed any underlying machine learning components, the size of a training set is not provided.

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

As it's unclear if a training set for machine learning was used, the method for establishing its ground truth is also not provided. The "SIMPLANT project files are created by DENTSPLY Implants," based on "dental professional supplied patient image data, patient information and implants data." This describes the workflow for generating the project files that the devices then interact with, rather than how a training set for an AI model would be established.

Summary of what is present and what is missing:

• Acceptance Criteria/Performance Data: Not explicitly detailed with quantitative metrics. Performance is broadly stated as confirming functionality, safety, and efficacy, and achieving substantial equivalence.
• Sample Size (Test Set), Data Provenance: Not provided.
• Expert Ground Truth (Test Set): Not provided (number or qualifications).
• Adjudication Method: Not provided.
• MRMC Study: Not described.
• Standalone Performance: The devices are human-in-the-loop; a standalone algorithm study (without human involvement) is not described and likely not applicable in the typical sense for this device.
• Type of Ground Truth: Not explicitly stated.
• Sample Size (Training Set): Not provided, and it's unclear if a "training set" in the ML sense is applicable.
• Ground Truth (Training Set): Not provided.

The document primarily focuses on establishing "substantial equivalence" to a predicate device (Simplant 2011) based on similar indications for use and fundamental functions, along with general software verification and validation activities. The emphasis is on the software's role as a tool rather than its performance as an autonomous or AI-driven diagnostic system.

Ask a specific question about this device