(150 days)
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 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 may reside 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. 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 (including tubing and base) needs to be changed every 2-3 days for infusion sets with a teflon cannula (Convatec Inset™ and Inset™ 30) and every 1-2 days for infusion sets with a steel cannula (Convatec Contact™ Detach) as indicated in the infusion set manufacturers' labeling. The iCGM sensor needs to be changed every 10 days.
The provided text does not describe the acceptance criteria and study that proves the device meets those criteria for an AI/ML powered device. The document pertains to the FDA clearance of the iLet ACE Pump, which is an alternate controller enabled infusion pump for insulin delivery. While it mentions the pump receives input from an integrated continuous glucose monitor (iCGM) and an interoperable automated glycemic controller (iAGC), and that the iAGC uses this information to calculate insulin needs, it does not describe an AI/ML algorithm that is being evaluated for its diagnostic or prognostic performance.
Therefore, I cannot extract the specific information requested in your bullet points related to AI/ML acceptance criteria and performance studies, such as:
- A table of acceptance criteria and reported device performance (for an AI/ML algorithm)
- Sample size used for the test set and data provenance (for AI/ML evaluation)
- Number of experts used to establish ground truth and their qualifications (for AI/ML annotation)
- Adjudication method (for AI/ML ground truth)
- Multi-reader multi-case (MRMC) comparative effectiveness study and effect size (for AI/ML assistance)
- Standalone performance (algorithm only without human-in-the-loop performance)
- Type of ground truth used (for AI/ML)
- Sample size for the training set (for AI/ML)
- How ground truth for the training set was established (for AI/ML)
Instead, the document focuses on the regulatory clearance process for a medical device (insulin pump) and typically discusses:
- Non-clinical performance data: This includes bench testing for dose delivery accuracy, occlusion detection, biocompatibility, sterility, electrical safety, EMC, CGM connectivity, packaging, shipping, and mechanical tests. All tests passed.
- Data logging and Interoperability: The device was validated for logging timestamped events and interoperability with connected devices.
- Cybersecurity: Mitigations for cybersecurity risks were incorporated, and an analysis was performed.
- Human Factors: A human factors validation study was conducted in a simulated use condition, including training and documentation, and demonstrated the system's safety and effectiveness for intended users and uses.
- Clinical Performance: A clinical study was not required for the iLet ACE Pump, as insulin delivery could be verified through bench testing and use validated through the human factors study.
The closest thing to "acceptance criteria" presented are the successful completion of these various non-clinical and human factors tests, indicating the device meets its design specifications and regulatory requirements for safety and effectiveness, similar to its predicate device.
§ 880.5730 Alternate controller enabled infusion pump.
(a)
Identification. An alternate controller enabled infusion pump (ACE pump) is a device intended for the infusion of drugs into a patient. The ACE pump may include basal and bolus drug delivery at set or variable rates. ACE pumps are designed to reliably and securely communicate with external devices, such as automated drug dosing systems, to allow drug delivery commands to be received, executed, and confirmed. ACE pumps are intended to be used both alone and in conjunction with digitally connected medical devices for the purpose of drug delivery.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include the following:
(i) Evidence demonstrating that device infusion delivery accuracy conforms to defined user needs and intended uses and is validated to support safe use under actual use conditions.
(A) Design input requirements must include delivery accuracy specifications under reasonably foreseeable use conditions, including ambient temperature changes, pressure changes (
e.g., head-height, backpressure, atmospheric), and, as appropriate, different drug fluidic properties.(B) Test results must demonstrate that the device meets the design input requirements for delivery accuracy under use conditions for the programmable range of delivery rates and volumes. Testing shall be conducted with a statistically valid number of devices to account for variation between devices.
(ii) Validation testing results demonstrating the ability of the pump to detect relevant hazards associated with drug delivery and the route of administration (
e.g., occlusions, air in line, etc.) within a clinically relevant timeframe across the range of programmable drug delivery rates and volumes. Hazard detection must be appropriate for the intended use of the device and testing must validate appropriate performance under the conditions of use for the device.(iii) Validation testing results demonstrating compatibility with drugs that may be used with the pump based on its labeling. Testing must include assessment of drug stability under reasonably foreseeable use conditions that may affect drug stability (
e.g., temperature, light exposure, or other factors as needed).(iv) The device parts that directly or indirectly contact the patient must be demonstrated to be biocompatible. This shall include chemical and particulate characterization on the final, finished, fluid contacting device components demonstrating that risk of harm from device-related residues is reasonably low.
(v) Evidence verifying and validating that the device is reliable over the ACE pump use life, as specified in the design file, in terms of all device functions and in terms of pump performance.
(vi) The device must be designed and tested for electrical safety, electromagnetic compatibility, and radio frequency wireless safety and availability consistent with patient safety requirements in the intended use environment.
(vii) For any device that is capable of delivering more than one drug, the risk of cross-channeling drugs must be adequately mitigated.
(viii) For any devices intended for multiple patient use, testing must demonstrate validation of reprocessing procedures and include verification that the device meets all functional and performance requirements after reprocessing.
(2) Design verification and validation activities must include appropriate design inputs and design outputs that are essential for the proper functioning of the device that have been documented and include the following:
(i) Risk control measures shall be implemented to address device system hazards and the design decisions related to how the risk control measures impact essential performance shall be documented.
(ii) A traceability analysis demonstrating that all hazards are adequately controlled and that all controls have been validated in the final device design.
(3) The device shall include validated interface specifications for digitally connected devices. These interface specifications shall, at a minimum, provide for the following:
(i) Secure authentication (pairing) to external devices.
(ii) Secure, accurate, and reliable means of data transmission between the pump and connected devices.
(iii) Sharing of necessary state information between the pump and any digitally connected alternate controllers (
e.g., battery level, reservoir level, pump status, error conditions).(iv) Ensuring that the pump continues to operate safely when data is received in a manner outside the bounds of the parameters specified.
(v) A detailed process and procedure for sharing the pump interface specification with digitally connected devices and for validating the correct implementation of that protocol.
(4) The device must include appropriate measures to ensure that safe therapy is maintained when communications with digitally connected alternate controller devices is interrupted, lost, or re-established after an interruption (
e.g., reverting to a pre-programmed, safe drug delivery rate). Validation testing results must demonstrate that critical events that occur during a loss of communications (e.g., commands, device malfunctions, occlusions, etc.) are handled appropriately during and after the interruption.(5) The device design must ensure that a record of critical events is stored and accessible for an adequate period to allow for auditing of communications between digitally connected devices and to facilitate the sharing of pertinent information with the responsible parties for those connected devices. Critical events to be stored by the system must, at a minimum, include:
(i) A record of all drug delivery
(ii) Commands issued to the pump and pump confirmations
(iii) Device malfunctions
(iv) Alarms and alerts and associated acknowledgements
(v) Connectivity events (
e.g., establishment or loss of communications)(6) Design verification and validation must include results obtained through a human factors study that demonstrates that an intended user can safely use the device for its intended use.
(7) Device labeling must include the following:
(i) A prominent statement identifying the drugs that are compatible with the device, including the identity and concentration of those drugs as appropriate.
(ii) A description of the minimum and maximum basal rates, minimum and maximum bolus volumes, and the increment size for basal and bolus delivery, or other similarly applicable information about drug delivery parameters.
(iii) A description of the pump accuracy at minimum, intermediate, and maximum bolus delivery volumes and the method(s) used to establish bolus delivery accuracy. For each bolus volume, pump accuracy shall be described in terms of the number of bolus doses measured to be within a given range as compared to the commanded volume. An acceptable accuracy description (depending on the drug delivered and bolus volume) may be provided as follows for each bolus volume tested, as applicable: Number of bolus doses with volume that is 250 percent of the commanded amount.
(iv) A description of the pump accuracy at minimum, intermediate, and maximum basal delivery rates and the method(s) used to establish basal delivery accuracy. For each basal rate, pump accuracy shall be described in terms of the amount of drug delivered after the basal delivery was first commanded, without a warmup period, up to various time points. The information provided must include typical pump performance, as well as worst-case pump performance observed during testing in terms of both over-delivery and under-delivery. An acceptable accuracy description (depending on the drug delivered) may be provided as follows, as applicable: The total volume delivered 1 hour, 6 hours, and 12 hours after starting delivery for a typical pump tested, as well as for the pump that delivered the least and the pump that delivered the most at each time point.
(v) A description of delivery hazard alarm performance, as applicable. For occlusion alarms, performance shall be reported at minimum, intermediate, and maximum delivery rates and volumes. This description must include the specification for the longest time period that may elapse before an occlusion alarm is triggered under each delivery condition, as well as the typical results observed during performance testing of the pumps.
(vi) For wireless connection enabled devices, a description of the wireless quality of service required for proper use of the device.
(vii) For any infusion pumps intended for multiple patient reuse, instructions for safely reprocessing the device between uses.