Search Results

The Sparta Infusion Set for Insulin is indicated for the subcutaneous infusion of insulin, administered by an external pump. The infusion set is indicated for use with adult and pediatric users weighing greater than 10 kg. The infusion set is indicated for single-use.

The Sparta Infusion Set is a sterile, single-use, subcutaneous infusion set that establishes a sealed fluid path from an external portable infusion pump to the patient. Fluid is delivered to the patient through a 6 mm, 90°, soft cannula inserted in the subcutaneous tissue. The cannula is inserted using the preloaded, single-use mechanical Inserter. The infusion set has a 23-inch tubing length that terminates in a Luer connecter.

The provided FDA 510(k) summary for the Sparta Infusion Set for Insulin (K243841) does not contain information about acceptance criteria and a study proving a software-driven device meets those criteria. The device described is an infusion set, which is a physical medical device, not an AI/software device. The document explicitly states:

"No clinical testing is required to support the Subject Device's indications for use or a substantial equivalence determination."

And regarding human factors, it says:

"Human Factors validation testing was performed... Testing demonstrated that use of the Sparta Infusion Set is safe and effective for its intended users, uses, and use environments." This is typical for physical devices, not an AI output study.

Therefore, I cannot provide the specific details about acceptance criteria, study design, sample sizes, expert involvement, or MRMC studies that you requested, as these are typically applicable to AI/software-driven diagnostic or imaging devices.

The document primarily focuses on:

• Biocompatibility Testing: To ensure the materials used are safe for contact with the body.
• Bench Performance Testing: To verify physical performance characteristics like leak resistance, insertion performance, needle safety, occlusion performance, etc.
• Sterilization and Shelf Life: To ensure the device remains sterile and functional over time.
• Human Factors: To ensure the device can be used safely and effectively by its intended users.

These are standard types of studies for a physical medical device like an infusion set, not for a software or AI product.

If you have a document describing an AI/software medical device, I would be happy to analyze it against your criteria.

Ask a specific question about this device

The Remunity® 2.0 Pump for Remodulin® (treprostinil) Injection (the Remunity 2.0 System) is intended for continuous subcutaneous delivery of Remodulin (treprostinil) Injection for use in patients, ages 17 and older.

The Remunity 2.0 System is a wearable infusion pump designed to deliver Remodulin® (treprostinil) subcutaneously for the treatment of pulmonary arterial hypertension (PAH). Remodulin® was FDA-approved under NDA 021272. The system consists of several components: a wearable pump assembly, a remote interface, and accessories (e.g., rechargeable batteries, battery charger, charging cable, power adapter). A commercially available subcutaneous infusion set is connected to the pump assembly via a standard luer connector for the delivery of Remodulin® from the system to the patient. The Remunity 2.0 System is prescription use only.

The pump assembly is composed of a durable pump and a disposable, single-use cassette with a user-filled drug reservoir. The pump infuses Remodulin® subcutaneously into the patient based on an individualized programmed rate. Each disposable cassette may be used for up to 72 hours after attachment to the pump. The subject system utilizes a micro-dosing pump mechanism supplemented with acoustic volume sensor feedback to ensure delivery accuracy.

The provided text describes the Remunity 2.0 Pump for Remodulin® (treprostinil) Injection, an infusion pump, and its substantial equivalence to a predicate device. However, it does not contain information about the acceptance criteria and study that proves a device meets those criteria in the context of an AI/ML medical device.

The document is a 510(k) summary for an infusion pump, which is a hardware device for drug delivery. The "Performance Data" section lists various functional areas evaluated for device performance (e.g., delivery accuracy, occlusion performance, durability) but does not provide specific acceptance criteria values or detailed results for these evaluations. It also mentions software, cybersecurity, human factors, electrical safety, EMC, and alarms as evaluated areas, but again, without specific acceptance criteria or study outcomes.

Therefore, I cannot populate the requested table and answer questions 2 through 9 based on the provided text. The information requested (e.g., sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC study, standalone performance, type of ground truth, training set size and ground truth establishment) is typically associated with studies for AI/ML-driven diagnostic or prognostic devices, which is not the type of device described here.

Ask a specific question about this device

The DEKA Infusion System is indicated for continuous delivery of general maintenance fluids and supported antibiotics to adult patients through a peripheral intravenous (IV) site under the supervision of a qualified clinician.

The DEKA Administration Set is indicated for gravity administration of general maintenance fluids and supported antibiotics approved for peripheral intravenous (IV) infusion to adult patients under the supervision of a qualified clinician. The DEKA Administration Set is indicated for single patient use only. The DEKA Administration Set is not indicated for administration of high-alert medications, blood, and blood products.

The DEKA Administration Set is compatible with the DEKA Infusion Controller or can be used as a stand-alone administration set for performing manual gravity infusions.

The subject device is a modified version of the predicate DEKA Infusion System. Updates have been made to the predicate device software to increase the maximum programmable flow rate (from 300 to 600 mL/h), update the labeling to reflect the increased maximum programmable flow rate and update the performance of tilt angle detection. The administration set is unchanged.

The DEKA Infusion System, comprised of the DEKA Infusion Controller and DEKA Administration Set, is a gravity-based infusion controller. The Infusion Controller uses a camera to view drop formation in an Administration Set Drip Chamber in order to measure flow rate. During an infusion, the Infusion Controller can adjust the Flow Control Valve (FCV) as necessary against the DEKA Administration Set to maintain the desired flow rate without user intervention.

The DEKA Administration Set is a single-use, non-DEHP intravascular administration set provided sterile. It is compatible with the DEKA Infusion Controller or can be used as a standalone administration set for performing manual gravity infusions.

The provided text is a 510(k) summary for the DEKA Infusion System and DEKA Administration Set. It primarily focuses on demonstrating substantial equivalence to a predicate device after a modification, specifically an increased maximum programmable flow rate and an update to tilt angle detection.

However, the document does not contain the detailed information required to answer your specific questions about acceptance criteria, the study proving the device meets the criteria, sample sizes, expert involvement, ground truth, or MRMC studies for an AI/ML-based device.

This document is for a mechanical/electrical infusion system that uses a camera for drop formation detection and flow rate measurement, not an AI/ML diagnostic or prognostic device that would involve a training set, test set, expert adjudication, or MRMC studies in the way your questions imply. The "Vision System Performance" mentioned is likely related to the camera's ability to accurately detect drops, not a complex AI model requiring extensive human-in-the-loop validation or ground truth established by multiple medical experts interpreting images.

Therefore, I cannot extract the requested information from this document. The questions you've asked are typical for the validation of Artificial Intelligence/Machine Learning (AI/ML) medical devices, particularly those involving image interpretation or complex diagnostic algorithms. This 510(k) summary does not describe such a device or its corresponding validation studies.

The closest aspects discussed are:

• Acceptance Criteria for Flow Rate Accuracy: Mentioned as "± 10% nominally" and "± 25% under environmental limits of normal use." The document states "All tests met acceptance criteria."
• Study Proving Device Meets Criteria: "Formal performance testing was conducted on all areas of the subject device that are impacted by its changes with respect to the predicate device."
• Performance Data: "Flow Rate Accuracy," "Vision System Performance," "Stopping Flow," and "Device Handling Alarms" were tested.

But none of these provide the level of detail (sample size, expert ground truth, adjudication, MRMC) specific to AI/ML device validation that your questions are designed to elicit.

Ask a specific question about this device

The HemoCare® Hemodialysis System is indicated for hemodialysis treatment, including short daily and nocturnal hemodialysis, of renal failure patients. The HemoCare Hemodialysis System is indicated for use in chronic dialysis facilities, self-care dialysis facilities, and the home setting. All treatments must be prescribed by a physician and administered by a trained operator. Treatments must be performed with the assistance or observation of an individual who has been trained and is considered competent in the use of the device. The HemoCare Hemodialysis System is not indicated for solo hemodialysis in the home setting.

The HemoCare® Hemodialysis System is a self-contained, software-controlled device that provides hemodialysis treatments, including short daily and nocturnal hemodialysis, for patients with renal failure. The device is intended for use by a single patient in chronic dialysis facilities, self-care dialysis facilities, and the home setting. The HemoCare® Hemodialysis System is composed of the following components:

• The HemoCare® Treatment Device is a hemodialysis delivery system. When provided a source of water for dialysis, it produces infusion grade dialysate using liquid acid and powder bicarbonate concentrates. The Treatment Device provides secure, 2-way communication with the cloud for transmitting patient registration, physician-prescribed dialysis treatments, patient monitoring, and device status information.
• The HemoCare® Water Device is a water purification system that produces water for dialysis through distillation of EPA drinking water. The Water Device interfaces with the Treatment Device.
• The Blood Treatment Set connects to the patient access site and interfaces with the Treatment Device to provide extracorporeal blood flow through a dialyzer for dialysis treatment. The Blood Treatment Set is terminally sterilized and includes displacement blood pumps, a heparin delivery system, and an access disconnect sensor. The Blood Treatment set can be used for up to 16 treatments.

The provided text describes the HemoCare® Hemodialysis System, a medical device. However, it does not contain the specific information required to complete the detailed table about acceptance criteria and device performance results as requested, nor does it detail a study proving the device meets acceptance criteria in the context of an AI/ML algorithm.

The document is a 510(k) summary for a hemodialysis system, focusing on its substantial equivalence to predicate devices. It outlines performance data categories like Biocompatibility, Electrical Safety, Software Verification and Validation, Bench Performance Testing, Sterilization and Shelf Life, Human Factors, and Clinical Testing.

Importantly, the document does not describe an AI/ML algorithm that would have "acceptance criteria," "test sets," "ground truth," "expert readers," or "MRMC studies" in the context typically associated with an AI/ML medical device submission. The "Software Verification and Validation Testing" section states that "Testing results demonstrate that the device meets all software performance requirements," but it does not specify what those requirements are, nor does it indicate these requirements relate to an AI/ML diagnostic or predictive function.

Therefore, I cannot fulfill the request as the type of information sought (related to AI/ML algorithm performance) is not present in the provided text. The document is about a physical medical device (hemodialysis system) and its regulatory clearance as substantially equivalent to existing devices, not about a software-as-medical-device (SaMD) or AI-enabled medical device performance study with the detailed metrics requested.

Ask a specific question about this device

The HemoCare Bicarbonate Concentrate Set (BCS) is indicated for use in the preparation of dialysate in a 3-stream proportioning hemodialysis machine with a compatible mechanical interface, such as the HemoCare Hemodialysis System. The BCS is intended for extracorporeal bicarbonate hemodialysis for chronic renal failure, according to a physician's prescription.

The HemoCare Bicarbonate Concentrate Set (BCS) is the Subject Device of this submission. It consists of powdered sodium bicarbonate in a single use cartridge with an integrated tubing assembly for interfacing with hemodialysis systems with compatible three-stream proportioning connector ports such as the HemoCare Hemodialysis System. The HemoCare System uses the bicarbonate concentrate in 3-stream, 45x proportioning to generate dialysate for bicarbonate hemodialysis therapy.

This document is a 510(k) summary for the HemoCare Bicarbonate Concentrate Set (BCS). It outlines the device, its intended use, comparison to a predicate device, and performance data. However, it does not describe a study involving an AI/Machine Learning (ML) device.

Therefore, I cannot provide information on acceptance criteria, reported device performance, sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, or ground truth details as they pertain to an AI/ML device.

The document focuses on the HemoCare Bicarbonate Concentrate Set, which is a medical accessory for hemodialysis, and its performance data relates to biocompatibility and bench testing to verify specified performance, not the performance of an AI/ML algorithm.

Ask a specific question about this device

The Remunity® Pump for Remodulin® (treprosimil) Injection (the Remunity System) is intended for continuous subcutaneous delivery of Remodulin (treprostinil) Injection for use in adults (greater than 22 years old).

The Remunity Subcutaneous Delivery System for Remodulin® (Remunity System) is a wearable infusion pump designed to deliver Remodulin® for the treatment of pulmonary arterial hypertension (PAH). It is intended for continuous subcutaneous delivery of FDA-approved Remodulin® (treprostinil) (hereinafter referred to as 'Remodulin®' or 'Remodulin® (treprostinil)'), NDA 021272. The Remunity System consists of several components: a wearable pump assembly, a remote interface, a filling and priming aid, and accessories (e.g., rechargeable batteries, battery charger, charging cable, power adapter). A commercially available subcutaneous infusion set is connected to the pump assembly via a standard luer connector for the delivery of Remodulin® from the Remunity System to the patient.

The pump assembly is composed of a reusable pump and a disposable single-use cassette with a pharmacy-filled or user-filled drug reservoir, which infuses Remodulin® subcutaneously into the patient based on an individualized programmed rate. Each disposable cassette may be used for up to 72 hours after attachment to the pump. The Remunity System utilizes a micro-dosing pump mechanism supplemented with acoustic volume sensor feedback to ensure delivery accuracy.

The device is prescription use only.

The modified device utilizes a touchscreen remote controller.

The provided text describes the Remunity System, an infusion pump. However, the document is a 510(k) summary for a substantial equivalence determination, not a study report proving a device meets specific acceptance criteria.

The 510(k) process primarily demonstrates that a new device is "substantially equivalent" to a legally marketed predicate device, meaning it has the same intended use and similar technological characteristics, or that any differences do not raise new questions of safety or effectiveness. It does not typically involve the presentation of detailed clinical study results or performance data in the format of acceptance criteria and proven performance as might be found in a clinical trial report or a comprehensive validation study.

Specifically, the document states:

• "No animal study or clinical trial data was obtained in support of this premarket submission."
• "Performance testing was conducted in order to verify and validate the subject device remote interface for its intended use, and to establish substantial equivalence to the respective predicate device remote interface in terms of safety and effectiveness." This indicates that performance testing was done, but the details of acceptance criteria and reported numerical performance values are not provided within this summary.
• The only "performance data" mentioned are the types of tests conducted (e.g., Touchscreen Remote Reliability, Functionality, Wireless Communication, Software and Cybersecurity, Human Factors, Electrical Safety, EMC, Alarms), not the quantitative results of those tests.

Therefore, Based solely on the provided FDA 510(k) summary (K240256), I cannot extract the specific information requested regarding acceptance criteria and a study proving the device meets those criteria, as detailed as your prompt requires. The document attests that appropriate testing was performed and that the modified device (with a touchscreen remote controller) is substantially equivalent to its predicate, but it does not present the raw or summarized performance data against explicit acceptance criteria.

The information you are asking for, such as sample size for test sets, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, standalone performance, and training set details, are typically found in more detailed study reports (e.g., clinical study reports, validation reports) that might be referenced in a 510(k) submission but are not fully elaborated in the summary itself.

In summary, the provided text does not contain the detailed information required to fill out the table and answer the specific questions about acceptance criteria and performance study methods.

Ask a specific question about this device

The DEKA ACE Pump System is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, ages six and above. The pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, and confirm commands from these devices. The pump is intended for single patient, home use and requires a prescription.

The bolus calculator is indicated for use for aiding the user in determining the bolus insulin dosage for management of diabetes mellitus based on consumed carbohydrates, operator entered blood glucose, insulin sensitivity, insulin to carbohydrate ratio, target glucose values, and current insulin on board.

The DEKA ACE Pump System described herein contains a modification of the labeling of the previously cleared DEKA ACE Pump System (K233952) to add Novolog U-100 (insulin aspart) as a compatible insulin. The device is a wearable alternate controller enabled (ACE) insulin infusion pump intended to subcutaneously deliver insulin. at set and variable rates, for the management of diabetes mellitus in persons requiring insulin. The pump is able to reliably and securely communicate with compatible, digitally connected devices to receive, confirm, and execute commands. The pump is intended for single patient, ambulatory use and requires a prescription. The DEKA ACE Pump System is intended for the management of diabetes mellitus in persons six years of age and greater.

The pump was previously cleared and is indicated for use with Humalog U-100 insulin. This Special 510(k) utilizes the same methodology and acceptance criteria used to obtain the clearance and indication for Humalog U-100 to add the indication for Novolog U-100.

The DEKA ACE Pump System, consistent with the predicate K233952, consists of the following durable and disposable components:

1. Pump: A durable pump that incorporates fluid delivery algorithms and interfaces to a cassette, external wireless user interface, and iCGM. The pump is powered by a rechargeable lithium ion battery.
2. Cassette: A single-use pumping cassette that combines microfluidic valves, a pump chamber, insulin reservoir, and Acoustic Volume Sensing (AVS) measurement chamber. The cassette interfaces to a pump and off-the-shelf infusion sets.
3. DEKA Loop App: An iOS mobile application that serves as the primary user interface for the system. The DEKA Loop app can be downloaded onto the user's personal iPhone.

Also consistent with the predicate, the DEKA ACE Pump system includes the following electronic interfaces:

• Dexcom G6 iCGM: The DEKA ACE Pump System is compatible with Dexcom G6 iCGMs. Communication between the Dexcom G6 and DEKA ACE Pump is unchanged from the predicate device. The BLE central role on the ACE Pump radio processor connects directly to the Dexcom iCGM transmitter using the sensor's medical slot. The ACE Pump communicates with the iCGM transmitter at a regular interval to provide iCGM sensor data to the iAGC.
• Halo Cloud: Halo Cloud is a digital platform that connects the DEKA ACE Pump System to a variety of cloud-related services. These services include:
• Patient onboarding and device pairing via secure key transfer
• Prescription setting downloads to the ACE Pump
• Event log uploads from the ACE pump to the cloud
• Remote (OTA) software updates

No changes to the hardware or software of the system from that of the predicate are necessary to add the Novolog U-100 compatibility claim.

The provided text describes a 510(k) submission for the DEKA ACE Pump System, specifically seeking to add Novolog U-100 (insulin aspart) as a compatible insulin. The core of this submission is to demonstrate substantial equivalence to a previously cleared version of the same pump (K233952), which was cleared for use with Humalog U-100 insulin.

Based on the provided text, the device in question is an insulin pump, not an AI/Software as a Medical Device (SaMD) for image analysis or diagnosis. Therefore, many of the typical acceptance criteria and study aspects related to AI/SaMD (like MRMC studies, expert ground truth establishment for diagnostic images, sample sizes for training/test sets for AI models, etc.) are not applicable to this type of medical device submission.

The "acceptance criteria" in this context refer to the demonstration that the modified device (with Novolog U-100 compatibility) is substantially equivalent to the predicate device (with Humalog U-100 compatibility) in terms of safety and effectiveness, and that it meets all applicable Special Controls for Alternate Controller Enabled Infusion Pumps (21 CFR 880.5730, Product Code QFG).

Here's an attempt to answer the questions based on the provided document, highlighting what is and isn't applicable:

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

   The document doesn't present a table of quantitative acceptance criteria and reported numerical performance for a new study, but rather asserts that the same methodology and acceptance criteria used for Humalog U-100 were applied to Novolog U-100, implying the new performance matches the previously accepted thresholds. The comparison focuses on demonstrating equivalence across various characteristics.

   Implicit Acceptance Criteria (based on equivalence to predicate and Special Controls):

   • Indications for Use: No change.
   • Prescription Use: Yes.
   • Intended Population: Persons with Diabetes Mellitus ages 6 and above.
   • Environment of Use: Professional healthcare facilities and home healthcare environments.
   • Patient Environment: On-body wearable ambulatory pump.
   • Delivery Method: Microprocessor controlled Micro-dosing pump mechanism supplemented with acoustic volume sensor (AVS) feedback for monitoring delivery accuracy.
   • Insulin Basal Rate Delivery Range: 0 units/hour - 30 units/hour.
   • Insulin Bolus Delivery Range: Programmable from 0.05 - 25.00 Units in 0.01 Unit increments.
   • Basal Accuracy: Unchanged from K213536 (predicate's reference).
   • Bolus Accuracy: Unchanged from K213536 (predicate's reference).
   • Bolus Volume after Occlusion Release: No more than 0.74 units.
   • Time to occlusion alarm: 10 min (Bolus); 3 hours (Basal, 1 U/h); 6 hours (Basal, 0.1 U/hr).
   • Material Biocompatibility: Compliant with ISO-10993.
   • Cartridge/Cassette Shelf Life: 1 year.
   • Ingress Protection: IP28.
   • Applicable Safety Standards: Compliance with listed IEC and ISO standards (e.g., IEC 60601-1, ISO 14971).
   • Power Source: Rechargeable Lithium Ion Battery.
   • Pump Storage Conditions: Temperatures of -25 °C to 70 °C, Non-condensing humidity 15% to 90%.
   • Operating Conditions: Temperatures of 5 °C to 40 °C, Non-condensing humidity of 15% to 90%.
   • System User Feedback: Visual, audible, and vibratory.
   • Battery Operating Time: 72 hours.
   • New "Acceptance": The addition of Novolog U-100 compatibility does not impact the safety and effectiveness, and testing with Novolog U-100 is equivalent to that performed with Humalog U-100.

   Reported Device Performance (based on assertion of equivalence):
   For all the criteria listed above, the "Subject Device" (DEKA ACE Pump with Novolog U-100 compatibility) is stated to have the exact same characteristics and performance as the "Predicate Device" (DEKA ACE Pump with Humalog U-100 compatibility), or that its performance is equivalent to the predicate's established performance for the relevant aspects (e.g., Novolog U-100 testing being equivalent to Humalog U-100 testing). The key is that "No new or modified risks" are introduced.

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

   The document states: "No clinical data was obtained in support of this premarket submission."
   It also states that "Performance testing was performed in order to establish substantial equivalence for the compatibility claim of Novolog U-100 in comparison to the previously cleared compatibility claim for Humalog U-100 in terms of both safety and effectiveness..."

   This heavily implies in vitro or bench testing rather than human subject testing. The "test set" in this context would likely refer to the number of tests/replicates performed with Novolog U-100 to demonstrate equivalent performance to Humalog U-100, not a dataset for an AI model. This information (specific sample sizes for bench testing, e.g., number of pump cycles, number of insulin lots tested) is not provided in this summary document. Data provenance for such non-clinical testing is typically internal lab data, not human patient data with country of origin.

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 an AI/SaMD for diagnostic image analysis. Ground truth would be established through engineering specifications, validated test methods, and measurement standards for pump performance, not expert consensus on medical images.

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

   Not applicable. This is not an AI/SaMD for diagnostic image analysis.

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/SaMD for diagnostic image analysis. The device is an insulin pump.

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

   Not applicable. The device has algorithms (fluid delivery, bolus calculator) but it's a physical pump with user interaction, not a standalone diagnostic algorithm being evaluated. Its performance is inherent to the pump's mechanical and electronic design working with insulin.

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

   The ground truth for the performance of the insulin pump (e.g., basal/bolus accuracy, occlusion detection, battery life) would be established through engineering specifications, standardized test methods, and quantifiable measurements (e.g., precision volumetric measurements, pressure sensor readings, time-to-event logging). For this submission, the "ground truth" for Novolog U-100 compatibility is that its chemical and physical properties allow the pump to perform identically or equivalently to how it performs with Humalog U-100, which has already been established as safe and effective.

8. The sample size for the training set

   Not applicable. This device does not use machine learning that requires a "training set" in the conventional AI sense for diagnostic tasks. The "training" of the pump would be its design, development, and validation testing based on engineering principles and regulatory standards.

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

   Not applicable. As above, there isn't a "training set" in the AI sense. The "ground truth" for the pump's design and function comes from established medical device standards, diabetes management requirements, and rigorous engineering testing.

Ask a specific question about this device

DEKA Loop is intended for use with compatible integrated continuous glucose monitors (iCGM) and the DEKA alternate controller enabled (ACE) insulin infusion pump to automatically increase, and suspend delivery of basal insulin based on iCGM readings and predicted glucose values. It can also recommend, and with the user's confirmation, control the delivery of correction boluses when glucose values are predicted to exceed user configurable thresholds.

DEKA Loop is intended for the management of Type 1 diabetes mellitus in persons six years of age and greater.

DEKA Loop is intended for single patient use and requires a prescription.

DEKA Loop is an interoperable Alternate Glycemic Controller (iAGC) and works to control an ACE (Alternate Controller Enabled) insulin pump to automatically increase, decrease, and suspend delivery of basal insulin based on readings from an iCGM (integrated continuous glucose monitor) and glucose values predicted by DEKA Loop. DEKA Loop can also recommend, and with the user's confirmation, control the delivery of correction boluses when glucose values are predicted to exceed user configurable thresholds. It is controlled by an iOS app that is downloaded to a user's iPhone.

The provided document, an FDA 510(k) K234055 clearance letter for the DEKA Loop device, focuses on demonstrating substantial equivalence to a predicate device (Tidepool Loop K203689). It details the device's technological characteristics and mentions performance data primarily through in silico testing for clinical equivalence. However, the document does not directly provide specific acceptance criteria or detailed results of a study designed to prove the device meets those criteria in the format requested (e.g., a table with numerical acceptance values and reported performance). Nor does it describe patient-level ground truth establishment, expert adjudication, or MRMC studies.

The information below is extracted and inferred from the provided text, highlighting what is available and what is explicitly not mentioned or detailed in relation to your specific questions.

Here's a breakdown based on the provided text:

Device Performance Acceptance Criteria and Study Details (Based on available information)

The document primarily relies on demonstration of substantial equivalence to a predicate device (Tidepool Loop) based on technological, functional, and performance characteristics, rather than establishing de novo performance criteria. The "Performance Data" section specifically states: "Additionally, in-silico software challenge testing demonstrated clinical equivalence to the predicate device."

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not provide a table with specific numerical acceptance criteria and corresponding reported device performance values. Instead, it states that "in-silico testing proves that the DEKA Loop algorithm is clinically equivalent to the Tidepool Loop Algorithm." This implies that the 'acceptance' for clinical performance was demonstrating equivalence through in silico methods.

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

• Sample Size (Test Set): Not explicitly stated. The document mentions "in-silico software challenge testing." This implies a simulated patient cohort, but the size of this cohort is not provided in terms of "samples."
• Data Provenance: The nature of in silico testing means it's not based on ex vivo or in vivo patient data in the traditional sense for the test set. It's a computational simulation.
  • For the predicate device's clinical performance (which the subject device aims to be equivalent to), the document states: "Tidepool Loop clinical performance is supported by representative 1,250 participants in a 15 months duration real-world, observational, single arm study of DIY Loop including both pediatric and adult participants." This refers to the predicate's data, not the subject device's in silico test set.

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

• Not applicable / Not stated. Ground truth, in the context of an in silico study for a glycemic controller, would likely refer to the accuracy of the simulated physiological model against known physiological principles or real-world data characteristics, rather than expert annotation of medical images or diagnoses. No human experts are mentioned for establishing ground truth for the in silico test set.

4. Adjudication Method for the Test Set:

• Not applicable / Not stated. Given the in silico nature and lack of human expert involvement in "ground truth" establishment as typically understood in AI imaging, no adjudication method is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. An MRMC study is relevant for human-in-the-loop performance studies, particularly in medical imaging where radiologists or clinicians interpret cases. The DEKA Loop is an automated glycemic controller. The document does not describe any study where human readers (e.g., clinicians) used the DEKA Loop (or a simulated version) to assess its comparative effectiveness against a standard of care or the predicate with outcomes like improved blood glucose control. The stated clinical performance evaluation was in silico device-to-predicate algorithm equivalence.

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

• Yes, implicitly. The "in-silico software challenge testing" is an algorithm-only (standalone) performance evaluation. It assessed the DEKA Loop algorithm's performance against the predicate's algorithm in a simulated environment, without direct human intervention in the loop of glucose regulation within the test.

7. The Type of Ground Truth Used:

• For the in-silico testing, the ground truth would be based on the simulated physiological model's behavior, which is designed to accurately represent human glucose metabolism and insulin action under various conditions. This is a form of simulated data / model-based ground truth rather than expert consensus, pathology, or direct patient outcomes data from a clinical trial for the subject device itself. The goal was to prove "clinical equivalence to the predicate device," meaning the in silico performance mirrored what the predicate device achieved in its real-world clinical study.

8. The Sample Size for the Training Set:

• Not stated. As this is a 510(k) submission for an existing algorithm (the "Loop" algorithm, which DEKA Loop is shown to be equivalent to), and not a novel AI/ML algorithm requiring de novo training, details about its original training set (if any, as an "algorithm" might be more deterministic control logic than a learned AI model in some cases) are not provided in this regulatory document. The focus is on the validation that the DEKA Loop implementation of the algorithm is equivalent to the predicate's.

9. How the Ground Truth for the Training Set was Established:

• Not stated. Refer to point 8. If the algorithm involved machine learning, its original training (if any) would have required a separate dataset and ground truth establishment method, which is not detailed in this 510(k) summary. Given the description ("predicts glucose levels... based on prior iCGM readings, insulin delivery history, and user input... uses that prediction to adjust insulin delivery"), it sounds more like a model-based predictive control algorithm rather than a deep learning model trained on a large dataset with ground truth labels.

Ask a specific question about this device

The DEKA ACE Pump System is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, ages six and above. The pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, execute, and confirm commands from these devices. The pump is intended for single patient, home use and requires a prescription.

The bolus calculator is indicated for use for aiding the bolus insulin dosage for management of diabetes mellitus based on consumed carbohydrates, operator entered blood glucose, insulin to carbohydrate ratio, target glucose values, and current insulin on board.

The DEKA ACE Pump system is a modification of the previously cleared DEKA ACE Pump System (K213536). The modified device is a wearable alternate controller enabled (ACE) insulin infusion pump (DEKA ACE Pump System) with the addition of an embedded iAGC (DEKA Loop). The user interface is an iOS app that can be downloaded to a user's iPhone.

The updated system is still intended to subcutaneously deliver insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin. The pump is able to reliably and securely communicate with compatible, digitally connected devices to receive, confirm, and execute commands. The Pump is intended for single patient, ambulatory use and requires a prescription. The Pump is indicated for use with Humalog U-100 insulin.

The DEKA ACE Pump System is indicated for the management of mellitus in persons six years of age and greater.

The system as described in this submission is able to be integrated with an integrated Continuous Glucose Monitor (iCGM). This submission also details the integration process that was used to incorporate the DEKA Loop iAGC Algorithm onto the DEKA ACE Pump.

The DEKA ACE Pump System consists of the following durable and disposable components:

• Pump: A durable pump that incorporates fluid delivery algorithms and interfaces to a cassette, external wireless user interface, and iCGM. The pump is powered by a rechargeable lithium ion battery.
• Cassette: A single-use pumping cassette that combines microfluidic valves, a pump chamber, insulin reservoir, and Acoustic Volume Sensing (AVS) measurement chamber. The cassette interfaces to a pump and off-the-shelf infusion sets.
• DEKA Loop App: An iOS mobile application that serves as the primary user face for the system. The DEKA Loop app can be downloaded onto the user's personal iPhone.

The provided text is a 510(k) summary for the DEKA ACE Pump System, focusing on demonstrating substantial equivalence to a previously cleared predicate device. It addresses modifications, primarily the addition of an embedded iAGC (DEKA Loop) and a change in the user interface to an iOS app, as well as a broadened age indication (from 13+ to 6+).

However, the document does not contain the specific information required to answer your request about acceptance criteria and study proving the device meets those criteria for aspects like deep learning model performance (e.g., accuracy, sensitivity, specificity, or AUC). The request is structured as if the document describes an AI/ML-based diagnostic device where performance metrics against a ground truth dataset would be evaluated.

Instead, this document describes a medical device (insulin pump) where the "performance testing" refers to engineering and quality assurance testing against technical standards and safety requirements (e.g., electrical safety, electromagnetic compatibility, biocompatibility, delivery accuracy of insulin). The "Acceptance Criteria" implicitly refer to meeting these established engineering and regulatory standards rather than statistical performance metrics of a diagnostic algorithm against a labeled test set.

Specifically:

• There is no mention of a deep learning model's performance metrics (accuracy, sensitivity, specificity, AUC) or related test set details (sample size, data provenance, ground truth establishment, expert adjudication, MRMC studies).
• The "DEKA Loop iAGC Algorithm" is mentioned as being integrated, but there are no details on how its performance was evaluated, other than "Human Factors testing demonstrates equivalent safety and effectiveness for the indicated population" (page 7). This suggests focus on usability and safety in human interaction, not algorithmic diagnostic performance.
• The document explicitly states "No clinical data was obtained in support of this premarket submission" (page 13), reinforcing that the evaluation was primarily non-clinical and focused on substantial equivalence based on existing data and engineering tests.

Given the content of the provided document, I cannot fulfill your request for the specific details outlined for an AI/ML-based diagnostic device. The available information relates to the regulatory submission for an insulin pump, which is evaluated against different types of performance criteria.

Ask a specific question about this device

The DEKA Infusion System is indicated for continuous delivery of general maintenance fluids and supported antibiotics to adult patients through a peripheral intravenous (IV) site under the supervision of a qualified clinician.

The DEKA Administration Set is indicated for gravity administration of general maintenance fluids and supported antibiotics approved for peripheral intravenous (IV) infusion to adult patients under the supervision of a qualified clinician. The DEKA Administration Set is indicated for single patient use only. The DEKA Administration Set is not indicated for administration of high-alert medications, blood, and blood products.

The DEKA Administration Set is compatible with the DEKA Infusion Controller or can be used as a stand-alone administration set for performing manual gravity infusions.

The DEKA Infusion System, comprised of the DEKA Infusion Controller and DEKA Administration Set, is a gravity-based infusion controller. The Infusion Controller uses a Camera to view drop formation in an Administration Set Drip Chamber in order to measure flow rate. During an infusion, the Infusion Controller can adjust the Flow Control Valve (FCV) as necessary against the DEKA Administration Set to maintain the desired flow rate without user intervention.

The DEKA Administration Set is a single-use, non-DEHP intravascular administration set provided sterile. It is compatible with the DEKA Infusion Controller or can be used as a standalone administration set for performing manual gravity infusions.

This document describes the regulatory submission for the DEKA Infusion System and DEKA Administration Set, emphasizing their substantial equivalence to previously cleared devices. It outlines performance data related to device testing but does not contain information on studies proving the device meets acceptance criteria related to AI/human reader performance or ground truth established by experts for such studies.

Therefore, I will extract relevant information that is present and note the absence of information specifically requested for AI/human reader performance studies.

Here's the analysis based on the provided text:

Acceptance Criteria and Device Performance (as far as described for the hardware components):

Ask a specific question about this device