Search Results

Smile Dx® is a computer-assisted detection (CADe) software designed to aid dentists in the review of digital files of bitewing and periapical radiographs of permanent teeth. It is intended to aid in the detection and segmentation of suspected dental findings which include: caries, periapical radiolucencies (PARL), restorations, and dental anatomy.

Smile Dx® is also intended to aid dentists in the measurement (in millimeter and percentage measurements) of mesial and distal bone levels associated with each tooth.

The device is not intended as a replacement for a complete dentist's review or their clinical judgment that takes into account other relevant information from the image, patient history, and actual in vivo clinical assessment.

Smile Dx® supports both digital and phosphor sensors.

Smile Dx® is a computer assisted detection (CADe) device indicated for use by licensed dentists as an aid in their assessment of bitewing and periapical radiographs of secondary dentition in adult patients. Smile Dx® utilizes machine learning to produce annotations for the following findings:

• Caries
• Periapical radiolucencies
• Bone level measurements (mesial and distal)
• Normal anatomy (enamel, dentin, pulp, and bone)
• Restorations

The provided FDA 510(k) Clearance Letter for Smile Dx® outlines the device's acceptance criteria and the studies conducted to prove it meets those criteria.

Acceptance Criteria and Device Performance

The acceptance criteria are implicitly defined by the performance metrics reported in the "Performance Testing" section. The device's performance is reported in terms of various metrics for both standalone and human-in-the-loop (MRMC) evaluations.

Here's a table summarizing the reported device performance against the implied acceptance criteria:

Table 1: Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

Copra Smile consists of machinable zirconia discs and blocks for preparation of single crowns, bridges with maximum of one pontic between two crowns and inlays, onlays and veneers.

Copra Supreme Hyperion consists of machinable zirconia discs and blocks for the preparation of full ceramic crowns, onlays and 3- and 4-unit bridges and inlay bridges (anterior and molar).

Pre-sintered zirconia blanks for the fabrication of individual dental restorations.

Copra Smile disks and blocks come in both white and pre-shaded in 0M1, 0M2, 0M3, A1-D4 and Joy Five-Nine in various sizes. Copra Supreme Hyperion disks and blocks come pre-shaded in 0M1, 0M2, 0M3, A1-D4 and Joy Five-Nine in various sizes.

The provided text describes a 510(k) premarket notification for dental zirconia blanks and does not contain information about a study proving the device meets acceptance criteria as typically found for AI/ML-enabled medical devices. The device in question, Copra Smile and Copra Supreme Hyperion, are "Porcelain Powder For Clinical Use" (Class II, Product Code: EIH), which are physical materials, not software or AI/ML components.

The "Testing Summary" in the document states:
"The physical properties of Copra Smile and Copra Supreme Hyperion were tested according to ISO 6872:2015 and all parameters meet the standard. A biocompatibility assessment of Copra Smile and Copra Supreme Hyperion was done in accordance with ISO 10993-1:2018."

This indicates that the acceptance criteria are adherence to the ISO 6872:2015 standard for physical properties of dental ceramics and ISO 10993-1:2018 for biocompatibility.

Here's the information, structured as requested, based on the provided text, with clarifications where details are not present for an AI/ML context:

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

Note: The detailed acceptance values within ISO 6872:2015 for "all parameters" are not explicitly listed in the document beyond Flexural Strength and Fracture Toughness. The document states that the physical properties of the subject devices, predicate, and reference devices all meet ISO 6872:2015.

2. Sample sized used for the test set and the data provenance

• Sample Size: The document does not specify the sample size for the physical properties and biocompatibility testing. This would typically be detailed in the test reports, which are summarized here.
• Data Provenance: Not explicitly stated, but the testing would typically be performed by the manufacturer or a contracted lab to generate data for submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This question is not applicable as this is not an AI/ML device requiring expert ground truth in the traditional sense. The "ground truth" here is established by the physical and chemical properties of the material and its biological interaction determined through standardized tests, rather than expert interpretation of images or other data.

4. Adjudication method for the test set

Not applicable as this is not an AI/ML device requiring adjudication of expert interpretations. The tests for physical properties and biocompatibility are objective, standardized measurements.

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

Not applicable. This is a physical dental material, not an AI-assisted diagnostic tool or software.

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

Not applicable. This is a physical dental material, not an algorithm.

7. The type of ground truth used

The "ground truth" for this device (Copra Smile and Copra Supreme Hyperion) is established by:

• Standardized Physical Property Measurements: Adherence to the specifications outlined in ISO 6872:2015 for dental ceramic materials (e.g., specific values for flexural strength, fracture toughness, chemical composition, microstructure).
• Biocompatibility Testing: Results from tests conducted according to ISO 10993-1:2018 to evaluate the biological response to the material.

8. The sample size for the training set

Not applicable. This is not an AI/ML device, so there is no training set. The "training" in manufacturing would relate to process control and material formulation development, not data-driven model training.

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

Not applicable, as there is no training set for an AI/ML model. The formulation and manufacturing parameters for the dental blanks would be established through material science research, development, and quality control processes to ensure the desired physical and chemical properties are achieved consistently.

Ask a specific question about this device

The Smileyscope System's Therapy Mode is a prescription-use intual reality system intended to provide adjunctive treatment based on guided relaxation and other evidence-based behavioral methods for patients aged 4-1 years who can cooperate and interact with the device at a developmentally appropriate level. The Smileyscope Therapy Mode is intended to temporarily reduce and/or manage pain and temporarily relieve acute procedural with needle procedures (e.g., venipuncture, IV placement, vaccination, port access, subcutaneous injections). The device is not intended to treat anxiety disorders or specific phobias (e.g. trypanophobia).

Smileyscope is an immersive virtual reality (VR) device, consisting of Hardware and Software components. In Smileyscope Therapy mode, the device delivers 3-dimensional virtual reality treatment based on guided relaxation and other evidence-based behavioral methods to temporarily reduce pain and temporarily relieve acute procedural anxiety in individuals undergoing needle procedures. This prescription-use device uses pre-loaded software on a proprietary hardware and software platform to deliver treatment. The Smileyscope device is supplied with a USB charger and USB cable to facilitate charging.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for the Smileyscope System (Therapy Mode):

Background Note: This document is a 510(k) summary, which often focuses on establishing substantial equivalence to a predicate device rather than presenting a full, detailed clinical study report. Therefore, some specific details about the study methodology (e.g., precise expert qualifications, detailed adjudication methods for ground truth) might not be explicitly stated in this type of summary.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the "Special Controls" applied to the predicate device, which the Smileyscope Therapy Mode aims to meet, and the "Clinical Performance Testing" results presented.

• Emergency Department study (N=123): Nil adverse effects in treatment arm.
• Outpatient Pathology study (N=129): 3 mild adverse effects in treatment arm.
  Overall, "safe, with no significant adverse effects." Adverse effects were mild (nausea, dizziness, headache, vomiting) and self-limiting. |
  | 2. Patient-contacting components are biocompatible. | Met: Biocompatibility evaluation performed per FDA guidance (ISO 10993-1:2018) for surface-contacting, limited duration (intact skin) components. Tests included Cytotoxicity, Sensitization, Intracutaneous Reactivity. |
  | 3. Software verification, validation, and hazard analysis performed. | Met: Documentation provided for "Minor" Level of Concern software, including requirements, traceability, revision history, V&V, hazard analysis, and cybersecurity. |
  | 4. Electromagnetic compatibility (EMC) and electrical, mechanical, and thermal safety testing performed. | Met: Conformance declared to harmonized standards (e.g., IEC 60950-1, EN 62368-1 for electrical safety; EN 301 489 series, EN 55032/55035 for EMC). |
  | 5. Labeling includes warnings for nausea/motion sickness, discomfort, and summary of clinical testing. | Implied Met: Labeling is listed as a migration measure for identified risks (nausea/motion sickness, discomfort, ineffective treatment, use error). A summary of clinical testing is provided in the 510(k) (and presumably in the actual labeling). |
  | II. Clinical Effectiveness Criteria (from study results): | |
  | Temporarily reduce and/or manage pain (primary effectiveness endpoint). | Met:
• Emergency Department study: Child Self-Rated Pain (Faces Pain Scale-Revised) reduction of -1.78 units with Smileyscope Therapy Mode vs. control (p=0.018).
• Outpatient Pathology study: Child Self-Rated Pain (Faces Pain Scale-Revised) reduction of -1.39 units with Smileyscope Therapy Mode vs. control (p=0.034). |
  | Temporarily relieve acute procedural anxiety (secondary effectiveness endpoint). | Met: Both studies "substantially reduced the secondary endpoint of procedural anxiety." (Specific quantitative results for anxiety are not provided in this summary table). |

2. Sample Size Used for the Test Set and Data Provenance

The "test set" here refers to the subjects in the clinical performance studies.

• Sample Size:

  • Emergency Department study: 123 (64 in Smileyscope Therapy Mode arm, 59 in Control arm).
  • Outpatient Pathology study: 129 (63 in Smileyscope Therapy Mode arm, 66 in Control arm).
  • Combined N = 252 (Enrollment N=254, but treatment group totals 252).

• Data Provenance:

  • Country of Origin: "Outside of the United States only". The specific countries are not mentioned in this summary.
  • Retrospective or Prospective: These were "randomized clinical studies" and referenced as "randomized controlled studies," implying a prospective design. Given that they are published in a peer-reviewed journal and were used for regulatory submission, this is a strong indication of prospective data collection.

3. Number of Experts Used to Establish the Ground Truth and Qualifications

• The summary does not explicitly state the number of experts or their qualifications for establishing ground truth, as the primary effectiveness endpoint was "Child Self-Rated Pain (Faces Pain Scale-Revised)." This is considered a patient-reported outcome (PRO).
• For the secondary endpoint of "procedural anxiety," again, no specific expert involvement for ground truth is mentioned. Procedural anxiety in children is often assessed using validated scales administered by trained researchers or clinicians, or through observational measures.

4. Adjudication Method for the Test Set

• The summary does not explicitly state an adjudication method (e.g., 2+1, 3+1, none) for the test set. Given that the primary endpoint was child self-rated pain, and the studies were randomized controlled trials, the outcome measure itself (Faces Pain Scale-Revised) is directly reported by the patient. Adjudication of such an endpoint by external experts is generally not performed.
• For other aspects of the study (e.g., adverse event reporting, study protocol adherence), there would have been standard clinical trial monitoring and oversight, but this is not detailed as a "ground truth" adjudication.

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

• No, an MRMC comparative effectiveness study was not done in the context of human readers with vs. without AI assistance.
• This device is a virtual reality behavioral therapy device, not an AI-powered diagnostic or assistive tool for human readers. Its primary function is to deliver therapeutic content directly to the patient to reduce pain and anxiety, rather than to assist a human in interpreting data or making a diagnosis. The studies compared the device's therapeutic effect against a control condition.

6. Standalone Performance (Algorithm Only)

• Yes, in essence, standalone performance was done for the "algorithm only" (the therapeutic virtual reality program). The studies measured the direct effect of the Smileyscope Therapy Mode on patients, where patients interacted solely with the device (software content running on specific hardware) and clinicians administered it.
• There was no "human-in-the-loop" component in the sense of a human interpreting AI output or making decisions based on AI assistance. The human (clinician) used the device as a tool, and the "performance" here refers to the device's therapeutic effect on the patient, which was measured directly in the clinical trials against a control.

7. Type of Ground Truth Used

• The primary ground truth used for effectiveness was patient-reported outcomes (PROs), specifically "Child Self-Rated Pain (Faces Pain Scale-Revised)."
• For safety, reported adverse events were the ground truth.

8. Sample Size for the Training Set

• The document does not mention a training set sample size. Because this device delivers virtual reality behavioral therapy, the "algorithm" is the behavioral therapy program itself, not a machine learning model that requires a separate training set in the typical sense.
• The development of the VR experience and its behavioral techniques would have been informed by existing evidence-based behavioral methods, but this is a different concept than a machine learning training set.

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

• As there's no explicit mention of a machine learning training set in the document, establishing ground truth for such a set is not applicable here.
• The "ground truth" for the device's therapeutic approach is implicitly based on "guided relaxation and other evidence-based behavioral methods" which are established practices in psychology and pain management. The clinical studies then validated if the VR delivery of these methods achieved the intended therapeutic effect.

Ask a specific question about this device

The SMILE external Trigeminal Nerve Stimulation (eTNS) System is indicated for treatment of pediatric Attention Deficit Hyperactivity Disorder (ADHD) as a monotherapy in patients ages 7 through 12 years old who are not currently taking prescription ADHD medications.

The device is to be used for patient treatment by prescription only and is intended to be used in the home under the supervision of a caregiver during periods of sleep.

Transcutaneous electrical nerve stimulator for Attention Deficit Hyperactivity Disorder. A transcutaneous electrical nerve stimulator for Attention Deficit Hyperactivity Disorder (ADHD) is a prescription device that stimulates transcutaneously or percutaneously through electrodes placed on the forehead.

The SMILE eTNS System treatment protocol is administered each night while the patient is sleeping, for 7-9 hours. The device is designed to provide non-invasive electrical stimulation of the trigeminal nerve.

The provided document is a 510(k) summary for the Nu Eyne Co., Ltd. SMILE device, a transcutaneous electrical nerve stimulator for Attention Deficit Hyperactivity Disorder (ADHD). This document focuses on demonstrating substantial equivalence to a predicate device (Monarch eTNS System), rather than presenting a clinical study where the device performance against specific acceptance criteria is measured for an AI/algorithm-driven device.

Therefore, the requested information regarding acceptance criteria, device performance, sample sizes, expert involvement, adjudication, MRMC studies, standalone performance, and ground truth establishment for an AI/algorithm is not available in this document.

The document details the device's technical specifications, indications for use, and a comparison to a predicate device to establish substantial equivalence. It also lists the non-clinical tests performed (electrical safety, EMC, performance, usability, and software validation according to relevant standards), which support the device's safety and effectiveness in general, but not a specific performance metric against a clinical acceptance criterion in the context of an AI/algorithm.

To directly answer your request based only on the provided text, I must state that the information is not present. This document describes a medical device clearance process focused on equivalence, not on the performance of a machine learning algorithm against a clinical endpoint with a dedicated test set and ground truth.

Ask a specific question about this device

The patient specific set of Clear Dental Aligners are indicated for the treatment of tooth malocclusion in patients having permanent dentition. These Aligners position teeth by way of continuous gentle force. These are for self-use by patient with monitoring of improvement by orthodontists.

The Clear Dental Aligners are thermoformed, orthodontic wearable & removable dental appliances that, when worn in the prescribed sequence and duration, progressively reposition the permanent malocclusion teeth. These aligners could be soft, medium, or hard as per prescription set by an orthodontist, and to exert the desired & continuous gentle force to progressively position the teeth. Each aligner is made of thermoforming BPA free material sheets.

The provided text, K223338, details the 510(k) premarket notification for the "Toothsi&SmileAligners" device. The document primarily focuses on demonstrating substantial equivalence to a predicate device ("ClearCorrect System, K113618") through comparison of specifications and bench testing.

Based on the provided text, there is no acceptance criteria or study that proves device performance against specific metrics relevant to AI/algorithm-driven medical devices (e.g., sensitivity, specificity, accuracy). The document outlines acceptance criteria and performance for non-clinical bench testing related to the physical properties and manufacturing of the aligners, not for an AI algorithm's diagnostic or predictive performance.

Therefore, I cannot fulfill the request to provide a table of acceptance criteria and reported device performance or details about AI-specific studies (sample sizes, expert ground truth, adjudication, MRMC, standalone performance, training set details) because the provided FDA submission document pertains to a physical medical device (orthodontic aligners) and not a software/AI-driven device requiring such performance metrics.

The "K223338" submission is for "Orthodontic Plastic Bracket" (Product Code NXC), which is a physical device that repositions teeth using continuous gentle force. The performance testing outlined (Table 2 on page 5) is for the physical aligners' properties:

• Surface finishing after polishing by two methods: Accepted
• Thickness of aligners after thermoforming with reference to aligner sheets: Accepted
• Aligner shape accuracy after mimicked use for 15 days: Accepted
• 3D Model shape accuracy for effectiveness of aligner punching as per treatment plan: Accepted

These are all physical engineering characteristic tests, not performance metrics for an AI or algorithm. The document explicitly states: "No comparative testing with predicate device was possible since clear dental aligners are patient specific devices made after treatment plan." and "The above four tests relate to safety (Sr. No 1 & 4) and performance (Sr. No 2, 3 and 4) of the clear aligners."

In summary, the provided document does not contain the information required to answer questions about acceptance criteria and study data for an AI/algorithm-driven device, as the submission is for a physical medical device.

Ask a specific question about this device

"Al Smile Aligner" is indicated for the alignment of teeth during orthodontic treatment of malocclusion.

"Al Smile Aligner" consists of a custom-made series of thin, clear plastic removable orthodontic appliances (aligners) that apply gentle pressure to teeth, gradually moving them into alignment.

A dentist or orthodontist assesses the patient to determine if the patient is a good candidate. Impressions are taken by the dental clinician and submitted to Nanjing Jiahe Dental Technology Co., Ltd along with the physician's prescription.

An FDA cleared dental software used for teeth alignment was used to design a series of plastic aligners intended to gradually realign the patient's teeth in accordance to the doctor's prescription.

Once the treatment plan is reviewed and approved by a dental health professional, each 3D model from the treatment plan is manufactured. The aligner travs are then manufactured by thermoforming a dental thermoplastic sheet over each model.

The "Al Smile Aligners" have the same technological characteristics as the predicate device, in that all the devices are made from commercially available plastic that is thermoformed to create a customized, patient-specific aligners are then used for minor tooth movement by way of continuous gentle force.

The provided text is a 510(k) Summary for the "Al Smile Aligner" and primarily focuses on demonstrating substantial equivalence to a predicate device ("iSMILE"). It outlines the device's description, indications for use, and a comparison with the predicate.

However, the document does not contain the information requested about acceptance criteria and a study proving the device meets those criteria (e.g., performance metrics like sensitivity, specificity, or accuracy for an AI-powered diagnostic device). The "Summary of Device Testing" section mentions "nonclinical performance tests" and "Laboratory Testing" (physical, chemical, mechanical properties, process validation, and mechanical property/elasticity according to ASTM standards), but these are related to the physical properties and manufacturing of the aligners, not the performance of an AI component in a diagnostic or treatment planning context as might be expected for an "AI Smile Aligner" if the "AI" referred to a diagnostic algorithm.

Given the context of "Al Smile Aligner" being aligners for orthodontic treatment and the description of the design process involving FDA-cleared dental software, it appears the "AI" in the device name might refer to the software used to design the aligners, rather than an AI performing a diagnostic task. The document specifically states: "An FDA cleared dental software used for teeth alignment was used to design a series of plastic aligners intended to gradually realign the patient's teeth in accordance to the doctor's prescription." This implies the AI/software is an internal design tool, and the focus of the 510(k) is on the physical aligner product's substantial equivalence.

Therefore, many of the requested items (e.g., sample size for test set, expert ground truth, MRMC study, standalone performance) are not applicable or not present in this type of 510(k) submission for a physical medical device (orthodontic aligners). The information provided focuses on the physical and material properties, and manufacturing process of the aligners themselves, not the clinical performance of an AI diagnostic or planning algorithm that is directly assisting a human.

Here's a breakdown of the requested information based on the provided text, indicating what is present and what is absent/not applicable:

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

• Not present. The document does not describe acceptance criteria for AI performance in terms of diagnostic metrics (e.g., sensitivity, specificity, accuracy). It mentions mechanical and material testing according to ASTM standards and ISO 10993 for biocompatibility, implying those standards serve as "acceptance criteria" for the physical product, but no specific numerical performance is reported in a table format for those tests. The claim is that the device "meets all the requirements" and confirms "design output meets design inputs and specifications."

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

• Not applicable/Not present. There is no "test set" described for evaluating AI performance in a clinical context. The tests performed are laboratory tests on the physical aligners.

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)

• Not applicable/Not present. No clinical AI evaluation or ground truth establishment is described. The "ground truth" for the aligners is the doctor's prescription and the physical/material specifications.

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

• Not applicable/Not present.

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

• Not applicable/Not present. This is not an AI diagnostic device for which human reader improvement would be measured. The AI is described as "FDA cleared dental software" used internally for design, not for direct clinical decision support provided to users of the "Al Smile Aligner" product.

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

• Not applicable/Not present. As above, the AI is not presented as a standalone diagnostic or clinical decision-making algorithm that the product's 510(k) seeks to clear for direct clinical use. It's a tool in the manufacturing process.

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

• Not applicable. The "ground truth" for the physical aligner production seems to be adherence to the dental clinician's prescription and established engineering/biocompatibility standards.

8. The sample size for the training set

• Not applicable/Not present. No information about a training set for an AI algorithm is provided.

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

• Not applicable/Not present.

Summary of what is covered in the document regarding "device performance":

The document focuses on the substantial equivalence of the physical aligner product to a predicate device. The "Summary of Device Testing" section mentions:

• Performance (physical, chemical, mechanical properties): The device "meets all the requirements for overall design... and performance results confirming that the design output meets the design inputs and specifications for the device."
• Process Validation: Validate the processes used for the design and manufacture of the customized aligners.
• Mechanical Properties & Elasticity: Studied following ASTM standards (ASTM D570, ASTM D638, ASTM D790, and ASTM D1525).
• Biocompatibility: Tested according to Good Laboratory Practices and ISO 10993 (Parts 3, 5, 10, 11). The device "Meet ISO 10993-1."
• Bench Testing and Process Validation: "Bench Testing and Process Validation" is listed in the comparison table as part of performance and is stated to be met by both the subject and predicate devices.

The "AI" in "Al Smile Aligner" refers to the software used for the design of the aligners, which is described as "An FDA cleared dental software used for teeth alignment." The 510(k) is for the physical aligner product itself, not for the "AI" software as a separate, new clinical decision support or diagnostic device. As such, the performance evaluation is centered on the physical attributes and manufacturing processes of the aligners, not on the clinical performance of an AI algorithm in a test set.

Ask a specific question about this device

The SmileSeries™ is a series of clear, lightweight, plastic appliances indicated for the correction of dental malocclusion in adult and adolescent patients with permanent dentition (i.e. all second molars). The SmileSeries™ positions teeth by way of continuous gentle force.

The SmileSeries™ is comprised of a series of clear, thin, thermoformed removable aligner trays that are designed to correct tooth malocclusions without the use of conventional wire and bracket orthodontic technology. SmileSeries™ aligners are provided non-sterile and are customized for each patient according to the dental clinician's prescription. The dental health professional (dentist/orthodontist) takes provides physical or scanned impressions of the patient's teeth to SmileSeries™. A digital setup of either the scanned impression or a scan of the physical impression is sent to the clinician for approval. Upon approval, molds are then created with 3D-printing technology and the clear aligners are thermoformed on the molds and laser marked. The finished, customized aligners are provided to the dental health care professional who provides them to the patient, confirming fit and design. The aligner trays are held in place by pressure and can be removed by the patients at any time.

This document is a 510(k) Premarket Notification from the FDA for the device "SmileSeries™" by Ordont Orthodontic Laboratories, Inc. The core of this submission is to demonstrate substantial equivalence to a previously cleared predicate device, not to prove that the device meets specific acceptance criteria through a clinical study in the way one might for a novel diagnostic AI algorithm.

Therefore, the requested information regarding "acceptance criteria" and "study that proves the device meets the acceptance criteria" in the context of performance metrics that would be applicable to an AI device (like sensitivity, specificity, MRMC studies, ground truth establishment by experts, etc.) is not present in this document.

Instead, this document describes a comparison to a predicate device based on intended use, technological characteristics, materials, and manufacturing processes, supported by bench testing for manufacturing accuracy and biocompatibility testing of the plastic material.

Here's how to address your points based on the provided document:

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

The document does not present quantitative performance acceptance criteria or reported performance results in the typical sense for a diagnostic device. Since SmileSeries™ is an orthodontic appliance (a physical device), the "acceptance criteria" revolve around demonstrating that it is substantially equivalent to a predicate device, meaning it is as safe and effective as a legally marketed device.

The "performance" is primarily shown through:

• Identical Indications for Use: The SmileSeries™ is used for the same purpose as the predicate.
• Similar Technological Characteristics: Same material (thermoformed plastic), similar manufacturing process (forming plastic sheets on models), and the same software used for planning.
• Successful Bench Testing: To validate the manufacturing process and ensure accuracy of the final aligner compared to the digital scan. No specific numerical results or benchmarks from this bench testing are provided in this summary, only that a "final report was part of the 510(k) package."
• Biocompatibility: The material meets requirements, referencing prior 510(k) submissions.

Table based on the document's comparison of characteristics:

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

This document describes bench testing for manufacturing accuracy, not clinical performance testing with a "test set" of patients or data, as would be common for an AI device. Therefore, a "sample size" in that context is not applicable or provided. The document states:

• "Bench testing was performed to validate the manufacturing process, to ensure the accuracy of the final thermoformed aligner compared to the initial digital scan."
• "A final report was part of the 510(k) package."

No details on the sample size of items tested, data provenance, or retrospective/prospective nature are provided for this bench testing in this summary.

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)

Not applicable. This device is an orthodontic appliance, not a diagnostic AI system requiring expert-derived ground truth for a test set. The validation focuses on manufacturing accuracy and material safety, not diagnostic performance.

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

Not applicable. As above, this is not a diagnostic study requiring adjudication of expert readings.

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

Not applicable. This is not an AI-assisted diagnostic device. The study performed was bench testing of the physical aligner and its manufacturing process, and biocompatibility testing of the material. The document explicitly states: "In vivo Animal and Human Clinical performance testing are not required for this device category."

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

Not applicable. This is not an algorithm-only device. The reference to software (Ortho Analyzer) is for treatment planning and 3D printing of models for the creation of the aligners, not for standalone diagnostic performance.

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

For the bench testing, the "ground truth" would implicitly be the initial digital scan or design specifications of the aligner, against which the accuracy of the final thermoformed aligner was compared. It's a comparison to a precise digital model, not a biological or clinical ground truth in the sense of disease presence.

8. The sample size for the training set

Not applicable. This refers to an AI training set, which is not relevant to this physical device submission.

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

Not applicable. As per point 8.

Ask a specific question about this device

SmileGuard™ light curable resin is indicated for the fabrication of orthodontic and dental appliances such as mouthguards, nightguards and splints.

The SmileGuard™ system combines the light-curable resin, for use with a scanner with design software, validated 3D printer and a curing unit. These components are used together during the additive manufacture of dental appliance splints/mouth guards. The light-curing resin is a proprietary composition of acrylate/methacrylate, methacrylated oligomers and monomers, photo initiators, colorants/dyes and absorbers. It is used by dental laboratories and dental practices to make customized bite splints, using the 3D-printer. The resin is filled in lightproof 1 kg PE bottles labeled and offered together with a programmed RFID chip (referred to as TAG), which is required for use with the validated EnvisionTEC 3D printers. The TAG contains information identifying the resin: material, name and amount. The SmileGuard™ resin is an alternative material to heat-curing and auto-polymerizing resins.

The provided text describes the 510(k) premarket notification for a device named "SmileGuard™", a light-curable resin for fabricating orthodontic and dental appliances. The document is primarily focused on demonstrating substantial equivalence to a predicate device (KeyPrint® KeySplint Soft™) through comparative testing of material properties, rather than an AI-driven medical device requiring clinical performance studies directly involving AI.

Therefore, many of the requested fields regarding acceptance criteria, study design for AI performance, sample sizes for test/training sets, expert adjudication, MRMC studies, and ground truth establishment for AI models are not applicable to this specific device and the information provided. The document focuses on the physical and chemical properties of the resin, its biocompatibility, and manufacturing process.

Here's a breakdown of the provided information relevant to your request, with an explanation of why other aspects are not present:

Device Description:
SmileGuard™ is a light-curable resin used with a scanner, design software, validated 3D printer, and curing unit for the additive manufacture of dental appliance splints/mouth guards.

Intended Use:
Fabrication of orthodontic and dental appliances such as mouthguards, nightguards, and splints.

1. Table of Acceptance Criteria and Reported Device Performance

For this device, the "acceptance criteria" are not performance metrics in the sense of diagnostic accuracy (like sensitivity/specificity for AI), but rather material property specifications and biocompatibility requirements for the resin. The acceptance criteria are based on established ISO and ASTM standards for dental polymers and biocompatibility.

Study Proving Device Meets Acceptance Criteria:

The study proving the device meets the acceptance criteria is a laboratory testing program as outlined in Section VII of the 510(k) Summary.

2. Sample size used for the test set and the data provenance:

• Sample Size: The document does not explicitly state the number of samples (e.g., number of test specimens) used for each physical property test (Tensile, Flexural, Impact, Hardness). It provides mean values and standard deviations, implying multiple samples were tested for each property.
• Data Provenance: The testing was conducted in a laboratory setting. No information about country of origin of data is provided beyond the manufacturer and regulatory consultant being based in Germany and the US respectively. The tests performed are prospective bench tests (physical property measurements and biocompatibility testing on newly manufactured resin samples).

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):

• Not applicable. This is not a study involving human interpretation of data for "ground truth" (e.g., medical image reading). The "ground truth" for material properties is established by the results of standardized physical and chemical tests performed in a laboratory, and for biocompatibility by the results of in vitro and in vivo biological tests according to ISO standards. No human expert "adjudication" of these test results in the sense of diagnostic interpretation is mentioned or required.

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

• Not applicable. This type of adjudication is relevant for human expert consensus in diagnostic studies (e.g., radiology reads), not for laboratory material testing or biocompatibility assessments.

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:

• Not applicable. This device is a material for fabricating dental appliances, not an AI-driven diagnostic or assistive tool for human interpretation. Therefore, MRMC studies and assessment of human reader improvement with AI assistance are irrelevant.

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

• Not applicable. There is no standalone AI algorithm in the context of this device. The device is a material.

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

• The "ground truth" for this device's performance is derived from objective, quantitative measurements obtained through standardized laboratory tests (e.g., ISO, ASTM standards for material properties) and biological test results for biocompatibility (ISO 10993 series). It is not based on expert consensus, pathology, or outcomes data in the usual clinical sense.

8. The sample size for the training set:

• Not applicable. This is not an AI model requiring a training set.

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

• Not applicable. No training set for an AI model.

Ask a specific question about this device

SMILE-100 System is intended to review, measure and record skin temperature patterns and variations emitted from the human body. It is intended for use as adjunctive diagnostic imaging for themally significant indications in the breast region. The significance of the value of these thermal patterns is determined by profession. This device is intended for use by qualified healthcare personnel trained in its use. The system is not intended for absolute temperature measurements. The system is not intended to be used as a thermometry device.

The SMILE-100 System is a breast thermography device with a visualization tool that helps a healthcare personnel to review, measure and analyze thermally significant indications in the breast region. It is intended to be used in the hospital, acute care settings, outpatient surgery, healthcare practitioner facilities or an environment where patient care is provided by qualified healthcare personnel.

SMILE-100 System consists of the following:

• An off-the-shelf FDA cleared thermal camera with its associated camera control software (i) provided by the thermal camera vendor for capturing and viewing thermal images
• An off the shelf laptop/desktop computer system with display, keyboard and mouse. (ii)
• SMILE-100 Software for viewing thermal patterns in thermal images (iii)

The SMILE-100 Software takes thermal images captured using off-the-shelf FDA-cleared thermal camera and provides various visualization options in multiple customizable views/palettes and also generates a report with quantitative thermal parameters and annotated images. The Software supports two user roles (i) a thermographer or imaging technician role and (ii) Expert thermologist role. The imaging technician captures thermal images and uploads them to the cloud-hosted SMILE-100 Software which performs image quality checks and submits to Expert. The Expert can select a temperature threshold for the SMILE-100 Software to highlight areas with thermal activity above the threshold in thermal images. The software makes no estimation of the thermal threshold. The software makes no determination regarding what the thermal patterns or relative temperature values mean. Expert thermologist needs to infer the meaning of high thermal activity and other areas of interest based on his/her visual interpretation of those patterns and thermal values.

Here's a breakdown of the acceptance criteria and study information for the SMILE-100 System, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state "acceptance criteria" in a quantitative manner for the SMILE-100 software's diagnostic performance or a clinical study proving its effectiveness in identifying thermally significant indications. The performance testing section primarily focuses on technical verification and comparison with a predicate device's technological characteristics.

However, based on the provided comparison tables, we can infer some technical performance characteristics that are critical for equivalence with the predicate device.

Ask a specific question about this device

Biotech Dental SMILERS® aligners are indicated for the alignment of teeth in patients with permanent dentition (i.e., all second molars) during orthodontic treatment of malocclusion. SMILERS® aligners position teeth by way of continuous gentle force.

The Biotech Dental SMILERS® aligners are a series of prescription-only clear plastic removable aligners intended to incrementally move a patient's teeth from an initial position to a different end position using a software-generated sequence of intermediate states. Biotech Dental SMILERS® sequentially reposition teeth by way of continuous gentle force.

The provided text is an FDA 510(k) summary for the Biotech Dental SMILERS® aligners. It focuses on demonstrating substantial equivalence to a predicate device (Byte Aligner System K180346) rather than detailing acceptance criteria and a study that proves the device meets them in the context of an AI/algorithm-driven device.

However, I can extract the information relevant to non-clinical performance testing and conceptualize how it relates to acceptance criteria and "proving the device meets them," even if it’s not an AI performance study.

Key takeaway from the document: This submission is for orthodontic aligners, which are physical medical devices, not an AI/algorithm. The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context refer to manufacturing validation, material testing, and shelf-life studies, not clinical performance or AI algorithm performance. The FDA determined that no clinical data was needed due to the well-established nature of sequential aligners.

Therefore, the requested information points 1 through 9, which are largely geared towards AI/algorithm performance studies, are not explicitly present in the provided document in the way they would be for an AI-medical device. I will address them based on the information available and note where it's not applicable.

Acceptance Criteria and Device Performance (Based on Non-Clinical Testing for a Physical Device)

1. Table of Acceptance Criteria and Reported Device Performance

Regarding AI/Algorithm-Specific Questions (Not Applicable to this Device Approval, but addressed for completeness):

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

• Not Applicable (N/A): This submission is for a physical medical device (orthodontic aligners), not an AI algorithm. No test set of clinical data (images, etc.) for AI performance was used. The "test set" for this application refers to physical samples used in manufacturing validation and biocompatibility testing. The number of cases for manufacturing validation is not specified, nor is the provenance of those cases.

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):

• N/A: As this is physical device approval, there's no clinical "ground truth" established by experts in the context of an AI algorithm's diagnostic performance. For the fit validation, it states "qualitatively evaluated by a qualified individual," but specific number or detailed qualifications beyond "qualified" are not provided.

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

• N/A: No clinical data or AI performance test set requiring adjudication in this context.

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:

• N/A: This is not an AI-assisted device. No MRMC study was performed. The clinical performance of sequential aligners is stated to be "well established" and "no clinical data is included in this submission."

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

• N/A: This is not an algorithm. The Nemocast software (K193003) is mentioned as a tool for planning cases, but the approval is for the aligners themselves, not the software's performance as a standalone diagnostic or treatment algorithm.

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

• N/A (for AI context): For the physical device, "ground truth" for manufacturing and fit would be based on engineering specifications and qualitative assessment of fit by a "qualified individual." Biocompatibility is assessed against published international standards.

8. The sample size for the training set:

• N/A: There is no AI training set for this device approval.

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

• N/A: There is no AI training set for this device approval.

Ask a specific question about this device