Search Results

The iLet ACE Pump is an alternate controller enabled (ACE) pump intended to deliver insulin under the skin based on input from an integrated continuous glucose monitor (CGM) and an interoperable automated glycemic controller (iAGC), in people 6 years of age or older with diabetes mellitus. The iLet ACE Pump is intended for single-person use; it is not to be shared.

The iLet ACE Pump described herein includes changes to the graphic user interface (GUI) and alarms to improve the safety of the device. Instructions were added to the User Guide and Quick Reference Guide to advise users regarding CGM sensor calibration.

No significant changes have been made to the technological characteristics of the device.

The iLet ACE Pump is an alternate controller enabled (ACE) pump intended to deliver insulin under the skin based on input from an integrated continuous glucose monitor (CGM) and an interoperable automated glycemic controller (iAGC) in people 6 years of age or older with diabetes mellitus. The iLet ACE Pump provides a graphical user interface and alerts to interact with the iLet delivery system and an iAGC. The iLet Bionic Pancreas System is a collection of wearable medical devices that work together to deliver insulin with minimal user oversight. The iLet System is made up of the iLet bionic pancreas (consisting of the iLet ACE Pump (with accessories) and iAGC which resides on the ACE pump hardware), ACE pump disposables and accessories, CGM and infusion set. The insulin is filled for iLet use by a user, in a ready-to-fill cartridge (from an insulin vial supplied by a drug manufacturer) with the use of the syringe and needle.

The iLet System consists of the iLet ACE Pump (K231485) with iLet Dosing Decision Software (K232224) and disposable consumables.

The iLet System is only for use with a compatible CGM and U-100 rapid acting insulin.

The CGM communicates with the iLet via Bluetooth. The iLet ACE Pump gets glucose readings from the CGM every 5 minutes and the iAGC uses that information as one of the inputs to calculate the person's insulin needs.
The iLet ACE Pump includes a motor–drivetrain pumping mechanism, which independently actuates the delivery of insulin from a cartridge that is separately loaded into the iLet. Insulin is injected under the skin via continuous infusion. The infusion set must be placed at least 3 inches away from the CGM sensor.

The iLet ACE Pump has a wirelessly rechargeable battery and is designed to be used by a single person and have a useful life of at least 4 years. The iLet is charged on a wireless charging pad which comes with the device. The Luer connector and drug cartridge need to be changed every 3 days. The insulin infusion set and CGM sensor need to be changed as indicated in the manufacturers' labeling.

The provided FDA 510(k) Clearance Letter for the iLet ACE Pump (K252770) describes a device modification to an already cleared predicate device (iLet ACE Pump, K231485). As such, the information regarding acceptance criteria and the study that proves the device meets the acceptance criteria is focused on verifying that the changes did not introduce new safety or effectiveness concerns and that the device remains substantially equivalent to its predicate.

Based on the provided document, the focus of the clearance is on non-clinical testing related to software and labeling changes, rather than a new clinical performance study establishing general efficacy and safety from scratch.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) for a device modification, the "acceptance criteria" are predominantly related to the successful verification of the specific changes made and continuous compliance with existing standards. The "reported device performance" refers to the outcome of these verification activities.

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

• Sample Size for Test Set: The document does not specify a numerical sample size for software verification testing (e.g., number of test cases, number of alarm scenarios). It broadly states "Software design verification testing was performed."
• Data Provenance: The data is generated from non-clinical software verification testing performed internally by Beta Bionics, Inc. The document does not specify country of origin for this testing but implies it aligns with internal design controls and regulatory requirements. It is a "prospective" evaluation of the modified software.

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

Not applicable in this context. For software verification testing of GUI and alarms, the "ground truth" is defined by the device's functional specifications and regulatory requirements. The testing is performed against these engineering and regulatory specifications, not against expert clinical consensus or pathology findings.

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

Not applicable. Software verification testing involves comparing observed software behavior against predefined requirements and expected outcomes, not an adjudication process by experts.

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 an Alternate Controller Enabled (ACE) infusion pump, which delivers insulin based on CGM input and an automated glycemic controller (iAGC). It is not an AI-assisted diagnostic imaging device that involves human readers interpreting results. Therefore, an MRMC study with human readers is not relevant to this specific clearance.

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

Yes, in a sense. The "Software Design Verification Testing" implies a standalone evaluation of the modified GUI and alarms. This testing would assess the functionality of these software components in a controlled environment, confirming they operate according to specifications without direct real-time human intervention in the loop of the test itself (though a human designed and executed the tests). The iAGC (automated glycemic controller) within the pump itself operates autonomously based on CGM input, representing an "algorithm only" component that was part of the original device's clearance. This specific 510(k) did not require new clinical performance testing for the iAGC algorithm.

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

For the software modifications addressed in this 510(k), the "ground truth" is primarily based on:

• Functional Specifications: The intended design and behavior of the GUI and alarms as defined by Beta Bionics.
• Regulatory Requirements: Compliance with relevant FDA regulations for medical device software and labeling.

8. The sample size for the training set

Not applicable. This 510(k) is for a device modification involving GUI and alarm changes. The underlying iAGC algorithm (which would have had a "training set" in its development phase) was previously cleared (K231485 & K232224). No new training or re-training of the core control algorithm was indicated by these specific modifications.

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

Not applicable to this specific 510(k). For the original iAGC algorithm, the "ground truth" for its training (if an AI/ML approach was used) would have been established through extensive physiological modeling, clinical trial data, and expert endocrinologist input regarding optimal glycemic control targets and safety parameters. However, this information is not part of the provided document for this modification submission.

Ask a specific question about this device

The iLet Dosing Decision Software is intended for use with compatible integrated continuous glucose monitors (iCGM) and alternate controller enabled (ACE) pumps. A self-monitoring of blood glucose (SMBG) meter may also be used for manual input of blood glucose values to continue insulin dosing for a limited period of time when input from the iCGM is temporarily not available. The iLet Dosing Decision Software autonomously determines and commands an increase, decrease, maintenance, or suspension of all basal doses of insulin and autonomously determines and commands correction doses of insulin based on input from an iCGM, and it autonomously determines and commands meal doses of insulin based on meal announcements. iLet Dosing Decision Software is intended for the management of type 1 diabetes mellitus in people 6 years of age or older. iLet Dosing Decision Software is intended for single patient use and requires a prescription.

The iLet Dosing Decision Software is an iAGC indicated for the management of type 1 diabetes mellitus. It autonomously determines and commands an increase, decrease, maintenance, or suspension of all basal doses of insulin and autonomously determines and commands correction doses of insulin based on input from an iCGM, and it autonomously determines and commands meal doses of insulin based on meal announcements. The iLet Dosing Decision Software is intended for the management of type 1 diabetes in people 6 years of age or older.

The iLet Dosing Decision Software works in conjunction with a compatible alternate controller enabled (ACE) pump. The iLet Dosing Decision Software only requires initialization with the user's body mass (body weight).

The iLet Dosing Decision Software does not require carbohydrate counting by the user or the use of carbohydrate- to-insulin ratios. Although the iLet system does not require a user to enter an exact carb amount to calculate and administer a meal bolus, it does require that the user announce the meal (e.g., breakfast, lunch, dinner) AND provide an estimated carb content as "Usual", "More", or "Less" than is routine for that meal type.

The iLet Dosing Decision Software does not require any information about the user's total daily dose of insulin, basal or long-acting insulin requirements, or insulin correction factors. It is an insulin titration system that requires no insulin-dose determinations by the user or provider. During normal operation, the iLet bionic pancreas (iLet ACE Pump with the iLet Dosing Decision Software installed) autonomously responds every five minutes to a glucose signal, from an iCGM that is worn by the user, by computing a control signal that translates to a dose of insulin, which is delivered to the user through the subcutaneous (SC) route. The iLet dosing decision software has three insulin controllers (algorithms) running in parallel: an adaptive basal insulin controller, which continually adapts to each individual's basal metabolic need for insulin, an adaptive bolus controller which provides doses that are required above and beyond the basal metabolic needs, and an adaptive meal dose controller which provides insulin in response to a meal announcement.

The iLet is intended to dose insulin based on CGM data. In the events where CGM stops providing glucose data to the iLet Dosing Decision Software BG-run mode feature will serve to temporarily continue insulin delivery. BG-run mode will determine and command basal insulin based on past requirements and will allow announcement of meals and entry of fingerstick BG measurements, which will be treated as iCGM data and may result in commanding administration of insulin or temporary suspension of basal insulin. BG-run mode use should always be for the shortest duration possible with the goal to resume CGM.

Here's a breakdown of the acceptance criteria and the study details for the iLet Dosing Decision Software, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state formal "acceptance criteria" in a quantitative manner (e.g., "HbA1c must decrease by X%"). Instead, it presents key outcomes from the clinical study and concludes that the modified device's performance regarding safety and effectiveness is comparable to the predicate device.

2. Sample Size and Data Provenance

• Test Set Sample Size: 46 users (6-17 years of age) from a total of 90 participants in the extension study. The total extension study included participants who were previously in the Standard Care Group of a prior 13-week Randomized Controlled Trial (RCT).
• Data Provenance: The clinical study was a multi-center trial conducted at 16 clinical sites in the United States. The study was prospective for the extension phase where participants used the iLet with Fiasp.

3. Number of Experts and Qualifications for Ground Truth

The document does not provide information on the number of experts used to establish ground truth or their specific qualifications for this particular study. The nature of the device (automated glycemic controller) and the outcomes measured (HbA1c, CGM data) suggest that the "ground truth" is derived directly from objective physiological measurements rather than expert human interpretation of medical images or subjective assessments.

4. Adjudication Method

The document does not describe any adjudication method. This is typical for studies relying on objective physiological measurements (like blood glucose, HbA1c) rather than subjective assessments that might require panel review.

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

• No, an MRMC comparative effectiveness study was not done.
  • An MRMC study typically applies to diagnostic devices where multiple human readers interpret the same cases, with and without AI assistance, to measure the impact of the AI.
  • This device, the iLet Dosing Decision Software, is an automated glycemic controller that directly delivers insulin dosages. It does not involve human readers interpreting data in the same way a diagnostic imaging AI would.
• Effect Size of Human Reader Improvement: Not applicable, as this was not an MRMC study.

6. Standalone (Algorithm Only) Performance Study

• Yes, in essence, a standalone study was performed. The study evaluated the performance of the iLet Dosing Decision Software (the algorithm) in conjunction with an iCGM and an ACE pump, operating autonomously without continuous human intervention for dosing decisions. While a human user initiates and monitors the system, the insulin dosing decisions themselves are made by the software. The study's outcomes directly reflect the algorithm's performance in a real-world setting.

7. Type of Ground Truth Used

The ground truth for this study was primarily based on:

• Objective physiological measurements:
  • HbA1c determination: Obtained from central lab blood samples.
  • Continuous Glucose Monitoring (CGM) data: Collected over the 13-week study period.
  • These are direct, quantitative measures of glycemic control and are considered objective outcomes data.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set used to develop or optimize the iLet Dosing Decision Software. This section focuses solely on the clinical study used to demonstrate the safety and effectiveness of a modified version of an already cleared device (specifically, expanding its indication for Fiasp usage in a younger age group). Information about the original training of the algorithm would typically be found in earlier 510(k) submissions or technical documentation not included here.

9. How Ground Truth for the Training Set Was Established

Since the document does not provide information on the training set, it does not explain how ground truth was established for the training set. However, given the nature of the device and the data types, it is highly probable that the training data would also have relied on objective physiological measurements from individuals with diabetes, similar to how the ground truth for the clinical validation was established (e.g., CGM data, blood glucose levels, clinical outcomes).

Ask a specific question about this device

The iLet ACE Pump is an alternate controller enabled (ACE) pump intended to deliver insulin under the skin based on input from an integrated continuous glucose monitor (iCGM) and an interoperable automated glycemic controller (iACC), in people 6 years of age or older with diabetes mellitus. The iLet ACE Pump is intended for single-person use; it is not to be shared.

The iLet ACE Pump is an alternate controller enabled (ACE) pump intended to deliver insulin under the skin based on input from an integrated continuous glucose monitor (iCGM) and an interoperable automated glycemic controller (iAGC) in people 6 years of age or older with diabetes mellitus. The iLet ACE Pump provides a graphical user interface and alerts to interact with the iLet delivery system and an iAGC. The iLet Bionic Pancreas System is a collection of wearable medical devices that work together to deliver insulin with minimal user oversight. The iLet System is made up of the iLet bionic pancreas (consisting of the iLet ACE Pump (with accessories) and iAGC which resides on the ACE pump hardware), ACE pump disposables and accessories, iCGM and infusion set. The insulin is filled for iLet use by a user, in a ready-to-fill cartridge (from an insulin vial supplied by a drug manufacturer) with the use of the syringe and needle. The iLet ACE Pump includes a motor-drivetrain pumping mechanism, which independently actuates the delivery of insulin from a cartridge that is separately loaded into the iLet. Insulin is injected under the skin via continuous infusion. The iLet ACE Pump has a wirelessly rechargeable battery and is designed to be used by a single person and have a useful life of at least 4 years.

This document describes a Special 510(k) Notification for a device modification, specifically updating the User Guide and Quick Reference Guide to indicate that the iLet bionic pancreas can be used with U-100 Fiasp® PumpCart® (insulin aspart) in a pre-filled 1.6 mL cartridge. The core device (iLet® ACE Pump) itself has not undergone significant technological changes. Because this is a modification to an already cleared device (K223846) to support compatibility with a new insulin formulation, the information provided focuses heavily on non-clinical testing for this specific change and cross-references prior clinical data.

Based on the provided text, a full description of acceptance criteria and the study proving the device meets all acceptance criteria (including for its original clearance) cannot be fully extracted, especially regarding clinical studies for the core device's efficacy. The document explicitly states: "No new clinical testing was required for this Special 510(k) notification. Clinical data to support use of Fiasp® (insulin aspart) with the iLet Dosing Decision Software was reviewed under K220916."

However, I can provide information relevant to this specific modification and what the document implies about the original clearance and its support for a new insulin type.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance (for this modification)

For this specific modification (Fiasp® compatibility), the criteria and performance are focused on non-clinical aspects related to the insulin itself, not the overall pump performance.

Note: The document does not provide the specific numerical data or thresholds for the acceptance criteria for In-Use Stability, Compatibility, or Preservative Efficacy, only that the same methods and Fiasp-specific criteria were met.

Regarding the other requested information, the document does not provide details for the iLet ACE Pump's initial clearance (K223846) or the clinical data for Fiasp (K220916). It only references their existence. Therefore, many of the subsequent points will indicate that the information is "Not provided in this document."

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

• For this K231485 Special 510(k) (Fiasp® compatibility):

  • Test set sample size: Not specified for the non-clinical tests (In-Use Stability, Compatibility, Preservative Efficacy). These would typically involve laboratory testing, not human subjects, so "sample size" refers to the number of test units.
  • Data provenance: Not specified, but generally, such non-clinical testing is done in a lab environment.
  • Retrospective/Prospective: Not applicable for non-clinical lab testing.

• For K220916 (Clinical data for Fiasp® with the iLet Dosing Decision Software):

  • Test set sample size: Not provided in this document.
  • Data provenance: Not provided in this document.
  • Retrospective/Prospective: Not provided in this document.

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

• Not applicable to this Special 510(k) directly. This type of information is typically relevant for studies involving human interpretation or clinical endpoints. The current submission focuses on technical compatibility with a new insulin type.
• For the referenced clinical study (K220916), this information is not provided in this document.

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

• Not applicable to this Special 510(k) directly.
• For the referenced clinical study (K220916), this information is not provided in this 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:

• Not applicable. This device is an insulin pump with an automated glycemic controller, not an AI-assisted diagnostic imaging device that involves human "readers."

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

• The iLet ACE Pump's automated glycemic controller (iAGC) is inherently designed for "algorithm-only" performance in terms of calculating insulin needs based on iCGM input. While human interaction is part of its use (e.g., loading insulin, changing cartridges, responding to alerts), the core insulin delivery decisions are automated.
• The document implies that the iAGC's performance (including with Fiasp) has been evaluated, "Clinical data to support use of Fiasp® (insulin aspart) with the iLet Dosing Decision Software was reviewed under K220916." However, the specifics of that study (e.g., comparison to human-in-the-loop) are not provided in this document.

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

• For the non-clinical Fiasp® compatibility: Ground truth would be based on laboratory measurements and standards for insulin stability, compatibility with materials, and preservative efficacy.
• For the referenced clinical study (K220916) concerning the iLet Dosing Decision Software with Fiasp®: The ground truth would likely involve clinically measured glucose levels, HbA1c, and adverse event rates, and potentially comparison to a standard of care for diabetes management. This information is not provided in this document.

8. The sample size for the training set:

• Not provided in this document. (Relevant for the iAGC algorithm development, but not the current K231485 submission).

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

• Not provided in this document. (Relevant for the iAGC algorithm development, but not the current K231485 submission).

Ask a specific question about this device

The iLet Dosing Decision Software is intended for use with compatible integrated continuous glucose monitors (iCGM) and alternate controller enabled (ACE) pumps. A self-monitoring of blood glucose (SMBG) meter may also be used for manual input of blood glucose values to continue insulin dosing for a limited period of time when input from the iCGM is temporarily not available. The iLet Dosing Decision Software autonomously determines and commands an increase, decrease, maintenance, or suspension of all basal doses of insulin and autonomously determines and commands correction doses of insulin based on input from an iCGM, and it autonomously determines and commands meal doses of insulin based on meal announcements. iLet Dosing Decision Software is intended for the management of type 1 diabetes mellitus in people 6 years of age or older. iLet Dosing Decision Software is intended for single patient use and requires a prescription.

The iLet Dosing Decision Software is an iAGC indicated for the management of type 1 diabetes mellitus. It autonomously determines and commands an increase, decrease, maintenance, or suspension of all basal doses of insulin and autonomously determines and commands correction doses of insulin based on input from an iCGM, and it autonomously determines and commands meal doses of insulin based on meal announcements. The iLet Dosing Decision Software is intended for the management of type 1 diabetes in people 6 years of age or older. The iLet Dosing Decision Software works in conjunction with a compatible alternate controller enabled (ACE) pump. The dosing decision software includes adaptive control algorithms that autonomously and continually adapt to the ever-changing insulin requirements of each individual to enable lifelong adaptive learning. The iLet Dosing Decision Software only requires initialization with the user's body mass (body weight). The iLet Dosing Decision Software does not require carbohydrate counting by the user or the use of carbohydrate- to-insulin ratios. Although the iLet system does not require a user to enter an exact carb amount to calculate and administer a meal bolus, it does require that the user announce the meal (e.g., breakfast, lunch, dinner) AND provide an estimated carb content as "Usual", "More", or "Less" than is routine for that meal type. The iLet Dosing Decision Software does not require any information about the user's total daily dose of insulin, basal or long-acting insulin requirements, or insulin correction factors. It is an insulin titration system that requires no insulin-dose determinations by the user or provider. During normal operation, the iLet bionic pancreas (iLet ACE Pump with the iLet Dosing Decision Software installed) autonomously responds every five minutes to a glucose signal, from an iCGM that is worn by the user, by computing a control signal that translates to a dose of insulin, which is intended to be delivered to the user through the subcutaneous (SC) route. The iLet dosing decision software has three insulin controllers (algorithms) running in parallel: an adaptive basal insulin controller, which continually adapts to each individual's basal metabolic need for insulin, an adaptive bolus controller which provides doses that are required above and beyond the basal metabolic needs, and an adaptive meal dose controller which provides insulin in response to a meal announcement. The iLet is intended to dose insulin based on CGM data. In the events where CGM stops providing glucose data to the iLet Dosing Decision Software BG-run mode feature will serve to temporarily continue insulin delivery. BG-run mode will determine and command basal insulin based on past requirements and will allow announcement of meals and entry of fingerstick BG measurements, which will be treated as iCGM data and may result in commanding administration of insulin or temporary suspension of basal insulin. BG-run mode use should always be for the shortest duration possible with the goal to resume CGM.

The provided text describes the iLet® Dosing Decision Software, an interoperable automated glycemic controller (iAGC), and the study conducted to demonstrate its performance.

Here's an analysis of the acceptance criteria and study as requested:

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

The document doesn't explicitly list "acceptance criteria" in a bulleted or numbered format with corresponding performance metrics like a typical FDA performance table. However, the "Endpoints" section in the Clinical Performance summary serves as the de facto acceptance criteria for the clinical study outcomes. The "Conclusions" section then describes how the device performed against these.

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

• Sample Size for the Clinical Study (RCT): 440 adult and child participants.
• Country of Origin: United States (16 clinical sites).
• Study Design: Prospective, multi-center, randomized controlled trial (RCT).
• Ancillary Study (BG-run feature): Participants in the BP Groups had the option of participating in this ancillary study, but a specific sample size for this ancillary study is not provided, only that it followed the RCT.

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 ground truth for the clinical study was established by the actual physiological responses and clinical outcomes of the participants with Type 1 Diabetes, measured by standard medical metrics (HbA1c, CGM data, adverse events). There is no mention of external experts establishing a "ground truth" for the device's dosing decisions themselves, as the device is designed to operate autonomously. The study evaluated the effectiveness and safety of the device's autonomous decisions.

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

This is not applicable to this type of study. Adjudication methods like 2+1 or 3+1 refer to expert consensus processes for evaluating medical images or diagnoses, typically used when establishing ground truth for AI algorithms in diagnostic imaging. For this device, which makes automated dosing decisions for diabetes management, the "ground truth" is physiological response, not expert interpretation. Adverse events would typically be adjudicated by a Clinical Events Committee (CEC), but the specific method (e.g., how many members reviewed each event) is not detailed.

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 was not done.
• This type of study is primarily relevant for diagnostic imaging AI where human readers interpret medical images. The iLet Dosing Decision Software is an automated glycemic controller, not an imaging interpretation aid.
• The study was a randomized controlled trial comparing the iLet system (which is the AI, managing insulin autonomously) to "standard care" (human-managed insulin delivery, either by pump or injections, though with CGM monitoring). It assesses the device's performance versus standard human-led care, not how human readers improve with AI assistance.

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

• Yes, a standalone study was done in the sense that the iLet Dosing Decision Software operates autonomously, commanding insulin doses without real-time human intervention in its decision-making process. The clinical trial directly evaluated this autonomous "algorithm only" performance within the iLet Bionic Pancreas System.
• The comparison was between the iLet system (operating autonomously) and standard human-managed care.

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

The ground truth for evaluating the iLet Dosing Decision Software's performance in the clinical study was primarily outcomes data and physiological measurements:

• HbA1c (a measure of average blood glucose over time).
• Continuous Glucose Monitoring (CGM) metrics (e.g., time in target range, time spent in hypo/hyperglycemia, mean glucose, standard deviation).
• Safety outcomes (severe hypoglycemia, diabetic ketoacidosis, other serious adverse events).

8. The sample size for the training set

The document does not provide information regarding the sample size used for the training set of the iLet Dosing Decision Software algorithm. It only details the clinical study for validation of the device.

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

The document does not provide information on how the ground truth for the training set was established. The iLet Dosing Decision Software employs "adaptive control algorithms that autonomously and continually adapt to the ever-changing insulin requirements of each individual to enable lifelong adaptive learning." This suggests a machine learning or adaptive control approach, which would have been trained on or developed using a dataset, but the specifics of that training data and ground truth establishment are not disclosed in this summary.

Ask a specific question about this device