Search Results

The SmartByte device is intended to aid in weight management in overweight to obese individuals. The device is indicated for individuals with a body mass index (BMI) in the range of 27-35 kg/m² in conjunction with behavioral modification instruction.

The Scientific Intake SmartByte device is an oral removable palatal space occupying device that includes a temperature recording sensor to monitor usage. The device includes a Palatal Mold Kit used by a healthcare professional to make the SmartByte device and an optional SmartByte Reader component that connects to a mobile application wirelessly via Bluetooth to allow usage data to be uploaded to assess frequency of device usage, i.e., adherence and patient reported weight management.

The provided document is a 510(k) summary for the SmartByte Device, comparing it to a predicate device (Sensor Monitored Alimentary Restriction Therapy (SMART) Device). The core of the submission is to demonstrate substantial equivalence, primarily for a change in the software platform from a computer-based system to a wireless mobile application.

Based on the document, here's an analysis of the acceptance criteria and the study that proves the device meets them:

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

The document does not present explicit "acceptance criteria" in the typical sense of quantitative performance metrics for a medical device's efficacy (e.g., sensitivity, specificity, accuracy for a diagnostic device). Instead, the acceptance criteria are focused on demonstrating that the modifications to the predicate device (specifically, the mobile app and Bluetooth connectivity) do not raise new questions of safety or effectiveness and that the new components function as intended.

The "reported device performance" is a demonstration of equivalence and functional verification rather than clinical outcomes.

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 "test set" in the context of clinical data for efficacy or a specific dataset for algorithm performance. The testing described is primarily software verification and validation testing and electrical safety testing (IEC 60950-1). These types of tests typically involve controlled environments, specific test cases, and simulation rather than a "sample size" of patient data or data provenance from a real-world setting.

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 applicable and not provided for this 510(k) submission. The device is not an AI/ML diagnostic tool requiring expert-established ground truth for image interpretation or similar tasks. The "ground truth" for the software and hardware components would be established by engineering specifications, functional requirements, and recognized safety standards, which are verified through the V&V activities.

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

This information is not applicable and not provided. Adjudication methods are typically used in clinical studies or studies involving human readers/interpreters to establish a reference standard for ambiguous cases. As this submission focuses on software and hardware functional equivalence and safety, such methods are not relevant.

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:

No, a MRMC comparative effectiveness study was not done. This device is an oral appliance for weight management with a data logging/display component; it is not an AI-assisted diagnostic tool that would typically involve human readers interpreting cases.

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

The device's data upload and display function via the app could be considered an "algorithm only" component in terms of its internal logic. However, the document describes "software verification and validation" (page 5) which confirms its standalone functionality. There is no specific mention of a separate "standalone performance study" in the context of AI algorithm performance metrics (e.g., AUC, sensitivity, specificity). The focus is on the software correctly performing its designed function of data handling and display.

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

The "ground truth" in this context is based on engineering specifications, functional requirements, and recognized industry standards (e.g., ISO 10993 for biocompatibility, IEC 60950-1 for electrical safety). For the software, the ground truth is that the software correctly processes, stores, and displays data according to its design, and that the wireless communication functions reliably and safely. These are verified through various engineering and software testing methods, not through clinical "outcomes data" or "expert consensus" on diagnostic interpretations.

8. The sample size for the training set:

This information is not applicable and not provided. The device is not an AI/ML model that undergoes a "training" phase with a dataset. The software is developed based on programming logic and then verified through testing.

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

This information is not applicable and not provided for the same reason as point 8.

Ask a specific question about this device

The SMART Device is intended to aid in weight management in overweight to obese individuals. The device is indicated for individuals with a body mass index (BMI) in the range 27-35 kg/m2 in conjunction with behavioral modification instruction.

The SMART Device is an oral removable palatal space occupying device that includes an embedded temperature recording sensor. The device is intended to be worn only during meals. to limit bite size and slow the intake of food, thereby reducing the amount of food that is consumed. The SMART Device is available using wire clasps and using a wraparound method (the wraparound technique is an added alternative to accommodate different oral anatomies) where the wires are coated with acrylic and wrapped around teeth in a symmetrical manner to secure the fit of the device (see Figure 1, below). The device is then removed after each meal or snack and the patient or healthcare professional has the option to use the temperature recording sensor embedded in the device to monitor device usage. This component of the SMART Device automatically records adherence, eliminating manual record-keeping by the user. The sensor is operated by a 3 volt lithium coin battery and measures ambient temperature at 5 minute intervals, storing the time and temperature data. The battery and the sensor are both double-encased and hermetically sealed in the acrylic. The SMART Device is provided with the Palatal Mold Kit and SMART Reader components. The Palatal Mold Kit is used to fabricate the SMART Device to match the patient's oral anatomy. The device is made from a mold of the upper oral cavity of the patient taken by a trained healthcare provider using the Palatal Mold Kit. The SMART Reader (See Figure 2, below) is an optional component that connects the sensor to a computer. Usage data are uploaded using infrared data transfer and a record of use can be produced. The user is provided instructions to download software for communicating between a personal computer and the SMART Reader and for displaying the time of day that the SMART Device was used. This software allows information from the embedded sensor to be uploaded to a secure, password protected Patient Portal website. Use of the Patient Portal allows the patient or healthcare provider to assess frequency of device usage.

Here's a breakdown of the acceptance criteria and the study details for the Sensor Monitored Alimentary Restriction Therapy (SMART) Device, based on the provided text:

Acceptance Criteria and Reported Device Performance

*Note on Safety Criteria for Pivotal Study: While the observed rate (4.9%) was less than 10%, the 95% confidence interval [1.6%, 11.1%] extended above 10%, meaning it couldn't be definitively claimed that the true rate was less than 10%. However, the events were non-serious and resolved, supporting a favorable safety profile overall.

Study Details

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

Pivotal Study:

• Test Set Sample Size (ITT Population): 173 subjects (102 device group, 71 control group)
• Test Set Sample Size (PP Population): 108 subjects (41 device group, 67 control group)
• Data Provenance: Prospective, randomized, controlled, open-label study conducted at five US centers.

Confirmatory Study:

• Test Set Sample Size (ITT Population): 76 subjects
• Test Set Sample Size (PP Population): 40 subjects
• Data Provenance: Prospective, single-arm, multicenter study conducted at 4 US investigational centers.

Consumer Preference Study:

• Test Set Sample Size: 24 subjects
• Data Provenance: A separate consumer and provider acceptance study; presumed prospective.

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

• Pivotal & Confirmatory Studies: The ground truth for weight loss was established through direct measurement of body weight by study personnel at study site assessments. No expert consensus on image interpretation or similar cognitive tasks was required for the primary and secondary endpoints related to weight.
• Confirmatory Study (SMART Fit Acceptability Sub Study): "Dental professionals assessed clinical fit of the device in 20 subjects." Their specific qualifications (e.g., years of experience) are not provided, but they are identified as "dental professionals."

4. Adjudication Method for the Test Set

• Pivotal & Confirmatory Studies: Not applicable for the primary endpoints, which involved objective measurements (weight, device usage via sensor data). Adverse events would typically be adjudicated by the study investigators and reported to the sponsor, but a specific multi-expert adjudication method (e.g., 2+1) is not explicitly described.

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

• No MRMC study was done. This device does not involve human readers interpreting images or data to make a diagnosis or assessment where AI assistance would directly improve their performance on a cognitive task. This is a physical medical device for weight management, and clinical outcomes were measured directly.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance)

• Yes, in part. The device's sensor automatically records adherence, providing data independently of human input for that specific function. However, the overall device effectiveness for weight management is and was evaluated in human subjects in conjunction with behavioural modification, making it a human-in-the-loop system for its intended use. The clinical studies measured the device's standalone effect on patients (when used as intended by patients), rather than an algorithm's standalone performance on a dataset.

7. Type of Ground Truth Used

• Pivotal & Confirmatory Studies: Objective Clinical Measurements (e.g., measured body weight at baseline and follow-up for %TBWL, sensor data for device usage/adherence) and Adverse Event Reporting by investigators.
• Confirmatory Study (Fit Sub Study): Expert Assessment by dental professionals for clinical fit.
• Consumer Preference Study: Patient Self-Report for acceptance and satisfaction, and Objective Clinical Measurements (measured body weight) for weight loss.

8. Sample Size for the Training Set

• Not Applicable. The SMART Device is a physical medical device, not an AI/ML algorithm that requires a "training set" in the computational sense. The "training" that occurred was the device's development and iterative testing.

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

• Not Applicable. As above, there is no "training set" in the context of an AI/ML algorithm. The "ground truth" for the device's design and functionality would have been established through engineering specifications, previous research on palatal devices, and pre-clinical bench testing.

Ask a specific question about this device