Search Results

Ask a specific question about this device

Ask a specific question about this device

SmartGuard technology is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible Medtronic continuous glucose monitors (CGMs), and alternate controller enabled (ACE) pumps to automatically adjust the delivery of basal insulin and to automatically deliver correction boluses based on sensor glucose values.
SmartGuard technology is intended for the management of Type 1 diabetes mellitus in persons 7 years of age and older requiring insulin.
SmartGuard technology is intended for single patient use and requires a prescription.

Predictive Low Glucose technology is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible Medtronic continuous glucose monitors (CGMs), and alternate controller enabled (ACE) pumps to automatically suspend delivery of insulin when the sensor glucose value falls below or is predicted to fall below predefined threshold values.
Predictive Low Glucose technology is intended for the management of Type 1 diabetes mellitus in persons 7 years of age and older requiring insulin.
Predictive Low Glucose technology is intended for single patient use and requires a prescription.

SmartGuard Technology, also referred to as Advanced Hybrid Closed Loop (AHCL) algorithm, is a software-only device intended for use by people with Type 1 diabetes for ages 7 years or older. It is an interoperable automated glycemic controller (iAGC) that is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible interoperable Medtronic continuous glucose monitors (CGM) and compatible alternate controller enabled (ACE) pumps to automatically adjust the delivery of basal insulin and to automatically deliver correction boluses based on sensor glucose (SG) values.
The AHCL algorithm resides on the compatible ACE pump, which serves as the host device. It is meant to be integrated in a compatible ACE pump and is an embedded part of the ACE pump firmware.
Inputs to the AHCL algorithm (e.g., SG values, user inputs) are received from the ACE pump (host device), and outputs from the AHCL algorithm (e.g., insulin delivery commands) are sent by the algorithm to the ACE pump. As an embedded part of the firmware, the AHCL algorithm does not connect to or receive data from compatible CGMs; instead, sensor glucose (SG) values or other inputs received by the ACE pump from compatible CGMs via Bluetooth Low Energy (BLE) technology are transmitted to the embedded AHCL algorithm.
The AHCL algorithm works in conjunction with the ACE pump and is responsible for controlling insulin delivery when the ACE pump is in Auto Mode. It includes adaptive control algorithms that autonomously and continually adapt to the ever-changing insulin requirements of each individual.
The AHCL algorithm requires specific therapy settings (target setpoint, insulin-to-carb ratios and active insulin time) that need to be established with the help of a health care provider (HCP) before activation. It also requires five (5) consecutive hours of insulin delivery history, a minimum of two (2) days of total daily dose (TDD) of insulin, a valid sensor glucose (SG) and blood glucose (BG) values to start automated insulin delivery.
When activated, the AHCL algorithm adjusts the insulin dose at five-minute intervals based on CGM data. A basal insulin dose (auto basal) is commanded by the AHCL algorithm to manage glucose levels to the user's target setpoint of 100 mg/dL, 110 mg/dL or 120 mg/dL. The user can also set a temporary target of 150 mg/dL for up to 24 hours. In addition, under certain conditions the algorithm can also automatically command correction boluses (auto correction bolus) without user input.
Meal boluses are the responsibility of the user. The AHCL algorithm includes an integrated bolus calculation feature for user-initiated boluses for meals. When the user inputs their carbohydrate intake, the AHCL algorithm automatically calculates a bolus amount based off available glucose information, entered carbohydrate amount and other patient parameters.
The AHCL algorithm contains several layers of "safeguards" (mitigations) to provide protection against over-delivery or under-delivery of insulin to reduce risk of hypoglycemia and hyperglycemia, respectively.
The AHCL algorithm is a software-only device and does not have a user interface (UI). The compatible ACE pump provides a UI to the user to configure the therapy settings and interact with the algorithm. The AHCL-related alerts/alarms are displayed and managed by the pump.

Predictive Low Glucose Technology, also referred to as the Predictive Low Glucose Management (PLGM) algorithm is a software-only device intended for use by people with Type 1 diabetes for ages 7 years or older. It is an interoperable automated glycemic controller (iAGC) that is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible interoperable Medtronic continuous glucose monitors (CGM) and compatible alternate controller enabled (ACE) pumps to automatically suspend delivery of insulin when the sensor glucose value falls below or is predicted to fall below predefined threshold values.
The PLGM algorithm resides on the compatible ACE Pump, which serves as the host device. It is meant to be integrated in a compatible ACE pump and is an embedded part of the ACE pump firmware.
Inputs to PLGM algorithm (e.g., sensor glucose values, user inputs) are received from the ACE pump (host device), and outputs from PLGM algorithm (e.g., suspend/resume commands) are sent by the algorithm to the ACE pump. As an embedded part of the ACE pump firmware, the PLGM algorithm does not connect to or receive data from compatible CGMs; instead, sensor glucose (SG) values or other inputs are received by the ACE pump from compatible CGMs via Bluetooth Low Energy (BLE) technology are transmitted to the embedded PLGM algorithm.
The PLGM algorithm works in conjunction with the ACE pump. When enabled, the PLGM algorithm is able to suspend insulin delivery for a minimum of 30 minutes and for a maximum of 2 hours based on current or predicted sensor glucose values. It will automatically resume insulin delivery when maximum suspend time of 2 hours has elapsed or when underlying conditions resolve. The user is also able to manually resume insulin at any time.
The PLGM algorithm is a software-only device and does not have a user interface (UI). The compatible ACE pump provides the UI to configure therapy settings and interact with the algorithm. The PLGM-related alerts/alarms are displayed and managed by the pump.

The provided FDA 510(k) clearance letter and supporting documentation detail the acceptance criteria and the studies conducted to prove that Medtronic's SmartGuard Technology and Predictive Low Glucose Technology meet these criteria.

It's important to note that the provided text focuses on demonstrating substantial equivalence to a predicate device, as is typical for 510(k) submissions, rather than establishing de novo acceptance criteria for an entirely novel device. The "acceptance criteria" here refer to the performance benchmarks that demonstrate safety and effectiveness comparable to the predicate and compliance with regulatory special controls.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The acceptance criteria are generally implied by the comparative data presented against the predicate device (Control-IQ Technology) and the compliance with "iAGC Special Controls requirements defined in 21 CFR 862.1356." The clinical study primarily aims to demonstrate non-inferiority or beneficial outcomes in key glycemic metrics compared to baseline (run-in period).

Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) submission showing substantial equivalence, the "acceptance criteria" are largely derived from the performance of the predicate device and clinical guidelines (e.g., ADA guidelines for Time Below Range). While specific numerical thresholds for acceptance are not explicitly listed as "acceptance criteria" in a table format within the provided text, the results presented serve as the evidence that these implicit criteria are met.

For the purpose of this response, I will synthesize the implied performance targets from the "Pivotal Study Observed Results" and "Supplemental Clinical Data" sections and present the device's reported performance against them.

Table 1: Implied Acceptance Criteria (via Predicate Performance/Clinical Guidelines) and Reported Device Performance for SmartGuard Technology (AHCL Algorithm)

Table 2: Implied Acceptance Criteria and Reported Device Performance for Predictive Low Glucose Technology (PLGM Algorithm)

Study Details

1. Sample Sizes and Data Provenance

Test Set (Clinical Studies):

• SmartGuard Technology (AHCL Algorithm) - Pivotal Study:

  • Adults (18-80 years): 110 subjects enrolled (105 completed).
  • Pediatrics (7-17 years): 112 subjects enrolled (107 completed).
  • Total: 222 subjects enrolled (212 completed).
  • Provenance: Multi-center, single-arm study conducted across 25 sites in the U.S. This implies prospective data collection, specifically designed for this regulatory submission. Home-setting study.

• Predictive Low Glucose Technology (PLGM Algorithm) - Clinical Testing:

  • Adults (14-75 years): 71 subjects. In-clinic study.
  • Pediatrics (7-13 years): 105 subjects. In-clinic evaluation.
  • Total: 176 subjects.
  • Provenance: Multi-center, single-arm, in-clinic studies. Location not explicitly stated but part of a US FDA submission, implying US or international sites adhering to FDA standards. Prospective data.

Training Set:

• SmartGuard Technology & Predictive Low Glucose Technology (Virtual Patient Model):
  • Sample Size: Not explicitly stated as a number of "patients" but referred to as "extensive validation of the simulation environment" and "virtual patient (VP) model."
  • Data Provenance: In-silico simulation studies using Medtronic Diabetes' simulation environment. This is synthetic data generated by computational models, validated against real patient data.

2. Number of Experts and Qualifications for Ground Truth (Test Set)

The clinical studies for both SmartGuard and PLGM technologies involved direct measurement of glucose values via CGM and blood samples (YSI for PLGM study, and HbA1c for SmartGuard study). These are objective physiological measures, not subjective interpretations requiring external expert consensus for "ground truth."

• For SmartGuard Technology: Glucose values were measured by the Simplera Sync CGM and HbA1c by laboratory tests. These are considered objective measures of glycemic control.
• For Predictive Low Glucose Technology: Hypoglycemia induction was monitored with frequent sample testing (FST) and frequent blood sampling for glucose measurements (likely laboratory-grade methods like YSI [Yellow Springs Instrument]).
• Expert involvement: While healthcare professionals (investigators, study coordinators, endocrinologists, nurses) were undoubtedly involved in conducting the clinical studies, managing patient care, and interpreting results, their role was not to establish "ground truth" through consensus or adjudication in the sense of image review. The ground truth was physiological measurements.

3. Adjudication Method for the Test Set

Not applicable in the typical sense of subjective clinical assessments (e.g., radiology image interpretation). Ground truth was established by direct physiological measurements (CGM data, HbA1c, YSI/FST blood glucose). The clinical studies were single-arm studies where subject outcomes were measured, not comparative assessments where multiple readers adjudicate on decisions.

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

No, an MRMC comparative effectiveness study was not described. The clinical studies were single-arm (evaluating the device's performance in a standalone setting against a baseline or predefined safety/efficacy metrics) and did not involve human readers interpreting data from the device to make clinical decisions and then comparing human performance with and without AI assistance. Instead, the AI (algorithm) directly controlled insulin delivery and was evaluated based on patient physiological outcomes.

5. Standalone (Algorithm Only) Performance

Yes, the core of the evaluation is the standalone performance of the algorithms (SmartGuard AHCL and PLGM) in managing glucose, as they are "software-only devices" that reside on the ACE pump firmware. The clinical studies directly measured the physiological impact of the algorithm's actions on glucose levels, HbA1c, and safety parameters in a human population.

6. Type of Ground Truth Used

• Clinical Studies (SmartGuard & PLGM): Objective Physiological Measurements

  • Sensor Glucose (SG) values: From compatible CGMs (Simplera Sync CGM, Guardian 4 CGM)
  • HbA1c: Laboratory measurements of glycosylated hemoglobin.
  • Frequent Sample Testing (FST) / Blood Glucose (BG) values: Clinical laboratory measurements (e.g., YSI) to confirm hypoglycemia during PLGM induction.
  • Adverse Events (AEs): Clinically reported and documented events.
  • These are considered the definitive "ground truth" for evaluating glycemic control and safety.

• In-Silico Simulation Studies: Virtual Patient Model Outputs

  • The "ground truth" for these simulations is the metabolic response of the validated virtual patient models. This computational modeling is used to extend the clinical evidence to various parameter settings and demonstrate equivalence to real-world scenarios.

7. Sample Size for the Training Set

The document does not explicitly state a numerical "sample size" for a distinct "training set" of patients in the traditional machine learning sense for the algorithms themselves. The algorithms are likely developed and refined using a combination of:

• Physiological modeling: Based on established understanding of glucose-insulin dynamics.
• Historical clinical data: From previous similar devices or general diabetes patient populations (though not specified in this document for algorithm training).
• Clinical expertise: Incorporated into the algorithm design.
• The "Virtual Patient Model" itself is a form of simulated data that aids in development and testing. The validation of this model is mentioned as "extensive validation" and establishment of "credibility," implying a robust dataset used to verify its accuracy against real patient responses.

It's typical for complex control algorithms like these to be developed iteratively with physiological models and potentially large historical datasets, but a specific "training set" size for a machine learning model isn't detailed.

8. How the Ground Truth for the Training Set was Established

As noted above, a distinct "training set" with ground truth in the conventional sense of labeling data for a machine learning model isn't described. The development of control algorithms often involves:

• Physiological Simulation: The ground truth for this is the accurate metabolic response as modeled mathematically.
• Clinical Expertise & Design Principles: The ground truth is embedded in the scientific and medical principles guiding the algorithm's control logic.
• Validation of Virtual Patient Model: The "equivalency was demonstrated between Real Patients (RPs) and Virtual Patients (VPs) in terms of predetermined characteristics and clinical outcomes." This suggests that real patient data was used to validate and establish the "ground truth" for the virtual patient model itself, ensuring it accurately mirrors human physiology. This validated virtual patient model then serves as a crucial tool for in-silico testing.

Ask a specific question about this device

The Origin™ system is comprised of the Origin™ inline device and Origin™ App. The Origin™ system is indicated for use in conjunction with a compatible drainage system by a trained healthcare professional during postoperative recovery in a hospital setting. The Origin™ inline device is placed between the surgical drainage catheter and reservoir system to continuously measure the pH of drainage fluid to provide additional information on effluent characteristics. The device is not intended to diagnose or treat any clinical condition.

Origin™ is an inline biosensor system that is integrated between an off-the-shelf drainage catheter and reservoir system and is designed to monitor real-time changes in drained effluent characteristics. Origin™ system continuously monitors the pH of wound drainage. Origin™ App is a mobile application for displaying and analyzing data from the Origin™ inline device. Origin™ App is pre-installed on an Android mobile device supplied by FluidAI. The Origin™ inline device connects to Origin™ App via Bluetooth.

The provided FDA 510(k) clearance letter and summary document for the Origin™ system primarily focus on the non-clinical performance of the device, particularly its analytical performance in measuring pH. It does not describe a study involving human readers or multi-reader multi-case (MRMC) comparative effectiveness. Therefore, some of the requested information, particularly related to clinical studies, human expert involvement in ground truth establishment for a test set, and MRMC studies, is not present in the provided text.

However, based on the analytical performance studies described, we can extract the following information:

1. Acceptance Criteria and Reported Device Performance

The document implicitly defines acceptance criteria through the results presented. The "Overall" pH range for linearity, for example, is 0.1446 pH units from 5 to 9, and 0.1 pH units from 4-10 using buffer solutions. For precision, the "Within-Laboratory" precision (total) is 0.0922 SD (1.46% CV) for sample A (pH ~6.3) and 0.1650 SD (2.10% CV) for sample B (pH ~7.85).

Since the document presents the results of studies conducted to demonstrate that the device meets some internal performance goals, we can infer that the reported values met their pre-specified acceptance criteria for analytical performance. However, the specific numerical acceptance thresholds (e.g., "Max Deviation from Linearity must be

Ask a specific question about this device

The T1D1 mobile application is indicated for the management of diabetes by people with Type 1 diabetes age 2 and older by calculating insulin doses based on user-entered data.

Prior to use, a healthcare professional must provide the patient target blood glucose values, insulin-to-carbohydrate ratios, and the correction factor (also known as the insulin sensitivity factor) to be programmed into the App software.

The T1D1 application is a user-friendly mobile application designed for Android and Apple devices, specifically catering to individuals aged 2 and above who have Type 1 Diabetes Mellitus (T1DM) and undergo multiple daily injection (MDI) therapy. Its primary objective is to simplify insulin dosing management by providing essential features such as a bolus calculator, a convenient logbook, and various configurable user-specific settings. The T1D1 application is intended to be distributed free of charge and without advertisements while operating independently of any other diabetes care devices. The overarching aim of the app is to streamline the daily calculations required by individuals with T1DM, alleviating the time-consuming and error-prone task of manually calculating and keeping track of insulin dosing.

The key feature of the T1D1 application is the bolus calculator. This calculator implements the standard insulin bolus calculation, taking into account factors such as the user's current blood glucose levels, carbohydrate intake, and target blood glucose levels. By considering these variables, the app provides users with an insulin dose recommendation, which assists in maintaining stable blood sugar levels.

The logbook feature allows users to record, track, and share their diabetes-related information. This information includes blood glucose levels, insulin doses, carbohydrate intake, and other relevant information. The ability to log and share this information with healthcare professionals or family members allows for improved communication and collaboration between individuals with T1DM and their support network.

The T1D1 application offers several presets to simplify the insulin dosing process. These presets can be customized based on individual preferences and needs. By providing preset options, the app eliminates the need for manual input of commonly used settings, saving time and reducing the likelihood of errors. In summary, the T1D1 application is a user-friendly mobile application that assists individuals with T1DM in managing their everyday insulin dosing from day one of their diagnosis.

The provided FDA 510(k) clearance letter for the T1D1 device, while detailing the general process and regulatory compliance, does not contain the specific performance data for the device that would allow for the construction of the requested table of acceptance criteria and reported device performance. The "Performance Data" section on page 10 only lists the standards and guidances followed for risk analysis, software V&V, cybersecurity, and human factors, but does not present any quantitative results from these studies.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance
• Sample size used for the test set and data provenance
• Number of experts and their qualifications
• Adjudication method
• MRMC comparative effectiveness study details
• Standalone (algorithm-only) performance details
• Type of ground truth used
• Sample size for the training set
• How ground truth for training set was established

To answer these questions, you would need access to the full 510(k) submission, which includes the detailed performance data, verification and validation reports, and clinical study summaries. The clearance letter only confirms that such data was reviewed and deemed acceptable by the FDA for the purpose of granting clearance.

Ask a specific question about this device

The SteadiSet infusion set is indicated for the subcutaneous infusion of insulin administered by an external pump. The infusion set is indicated for single use.

The subject device, SteadiSet infusion set, is a sterile, non-pyrogenic, intravascular administration set device used to administer insulin from a reservoir cartridge to a patient subcutaneously through a cannula. The infusion set administers insulin by means of a compatible external pump.

The infusion set consists of an inserter, tube set, and disconnect cover. The inserter consists of a housing, insertion buttons, an infusion set hub (with cannula) and adhesive patch with protective liner. The inserter facilitates insertion of the cannula subcutaneously. The cannula is a soft medical-grade polymer extruded over a stainless-steel coil.

The tube set provides the insulin pathway between the hub's indwelling cannula and an external insulin pump cartridge. The tube set consists of infusion set tubing with a reservoir connector (proximal end) and hub connector (distal end).

The disconnect cover can be connected to the hub to provide cover when the infusion set tubing is disconnected from the hub.

The device is sterilized by Ethylene Oxide (ETO) and is a single-patient, single-use device.

This FDA 510(k) clearance letter pertains to a medical device, the SteadiSet infusion set, not an AI or software as a medical device (SaMD). Therefore, many of the requested elements for AI/SaMD studies (such as sample sizes for test/training sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and ground truth types) are not applicable or not found within this type of documentation for a physical infusion set.

However, I can extract the relevant information regarding the clinical trial conducted for the device.

Acceptance Criteria and Study for SteadiSet Infusion Set

Based on the provided FDA 510(k) clearance letter for the SteadiSet infusion set, the "acceptance criteria" are not explicitly defined as specific numerical thresholds for performance metrics (such as sensitivity or specificity) in the way they would be for an AI model. Instead, the "acceptance criteria" are implied by the overall demonstration of safety and effectiveness as required for substantial equivalence to a predicate device.

The study that proves the device meets (these implied) acceptance criteria is a clinical study.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set (Clinical Study)

• Sample Size: A total of 260 subjects were enrolled.
• Data Provenance: The clinical study was conducted in the US at 15 investigational centers. This indicates prospective, real-world data collection in a clinical setting.

3. Number of Experts and Qualifications for Ground Truth

• Not Applicable. For a physical medical device like an infusion set, "ground truth" is typically established through direct clinical observation of patient outcomes (safety and effectiveness) rather than expert consensus on diagnostic images or data. The assessment of safety and effectiveness would have been based on clinical endpoints and observed adverse events, which are measured directly.

4. Adjudication Method for Test Set

• Not Applicable. Clinical trial outcomes (adverse events, device function) are typically evaluated by the investigational site staff and potentially reviewed by a clinical events committee, but the concept of "adjudication method" as applied to expert consensus for AI ground truth does not directly apply here.

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

• No. This type of study is relevant for diagnostic imaging AI, comparing human reader performance with and without AI assistance. It is not applicable to a physical infusion set.

6. Standalone Performance Study

• No, not in the context of an algorithm. The clinical study did evaluate the standalone performance of the device (the infusion set itself) in 260 subjects. However, this definition of standalone performance does not refer to an algorithm without human-in-the-loop, as the device is a physical product directly interacting with the patient.

7. Type of Ground Truth Used

• Clinical Outcomes Data: The ground truth was established by direct observation of clinical outcomes, specifically the absence of device-related serious adverse events and the demonstration of effective insulin infusion over the study period (maximum of 7 days).

8. Sample Size for Training Set

• Not Applicable. This device is a physical product, not an AI model requiring a training set.

9. How Ground Truth for Training Set Was Established

• Not Applicable. As there is no AI model or training set, this question is not relevant.

Ask a specific question about this device

Diazyme Colorimetric Lithium Assay kit is for quantitative in vitro determination of lithium in human serum or EDTA plasma. Measurements of lithium are carried out to ensure that proper drug dosage is administered in the treatment of patient suffering from bipolar disorder and to avoid toxicity.

Not Found

This document is an FDA 510(k) clearance letter for the Diazyme Colorimetric Lithium Assay. It formally grants permission to market the device based on a determination of substantial equivalence to predicate devices. However, this document does not contain the detailed study information regarding acceptance criteria and performance data.

The letter primarily covers:

• Confirmation of 510(k) review and clearance.
• The trade/device name, regulation number/name, regulatory class, and product code.
• General controls and additional regulations applicable to the device (e.g., Quality System regulation, UDI rule, MDR).
• Contact information for FDA resources.
• The "Indications for Use" statement for the device.

To answer your specific questions, one would typically need access to the 510(k) submission document itself, specifically the performance data sections. The provided FDA letter is the clearance notice, not the supporting technical file.

Therefore, I cannot provide the information requested in your prompt based solely on the provided FDA clearance letter. The letter confirms that a review was done and clearance granted, implying that the device did meet acceptance criteria demonstrated in the submission, but it does not detail those criteria or the study results.

To answer your questions, I would need a different document, such as the actual 510(k) application's test report or a summary of safety and effectiveness data (SSE) that outlines the performance studies.

Ask a specific question about this device

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

Access hsTnI is a paramagnetic particle, chemiluminescent immunoassay for the quantitative determination of cardiac troponin I (cTnI) levels in human serum and plasma using the Unicel DxI Immunoassay Systems to aid in the diagnosis of myocardial infarction (MI).

The Access hsTnI is a two–site immunoenzymatic ("sandwich") assay. Monoclonal anti–cTnI antibody conjugated to alkaline phosphatase is added to a reaction vessel along with a surfactant–containing buffer and sample. After a short incubation, paramagnetic particles coated with monoclonal anti–cTnI antibody are added. The human cTnI binds to the anti–cTnI antibody on the solid phase, while the anti–cTnI antibody–alkaline phosphatase conjugate reacts with different antigenic sites on the cTnI molecules. After incubation, materials bound to the solid phase are held in a magnetic field while unbound materials are washed away. Then, the chemiluminescent substrate is added to the vessel and light generated by the reaction is measured with a luminometer. The light production is directly proportional to the concentration of analyte in the sample. Analyte concentration is automatically determined from a stored calibration.

Here's a breakdown of the acceptance criteria and study information for the Access hsTnI device, based on the provided FDA 510(k) clearance letter:

Acceptance Criteria and Reported Device Performance

Study Details

The provided document describes a study primarily focused on demonstrating the substantial equivalence of the Access hsTnI assay when run on the UniCel DxI 800 Immunoassay System compared to its predicate device (Access hsTnI on the Access 2 Immunoassay System). This is achieved through performance testing of various analytical aspects.

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

   • Method Comparison: 239 samples (119 Lithium Heparin Plasma and 120 Serum).
   • Data Provenance: Not specified (e.g., country of origin). The document indicates it's a retrospective comparison between the "IVD Access hsTnI (Current Assay Protocol File (APF))" and the "proposed Access hsTnI (Proposed APF)" on the UniCel DxI 800 instruments, implying existing samples or previously collected data.

2. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:

   • Not Applicable. This device is an in-vitro diagnostic (IVD) immunoassay for quantitative determination of cTnI levels. The "ground truth" for the test set in this context refers to the measured cTnI values, which are inherently quantitative and determined by the predicate device's method and the proposed device's method, not by expert consensus or interpretation of images/clinical findings.

3. Adjudication Method for the Test Set:

   • Not Applicable. As noted above, this is a quantitative analytical method comparison, not a diagnostic interpretation or clinical outcome study that would require adjudication.

4. 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 an in-vitro diagnostic device, not an AI-based image interpretation or diagnostic aid system involving human readers.

5. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:

   • Yes, implicitly. The studies described (Method Comparison, Imprecision, Linearity, LoB/LoD, LoQ, Carryover) evaluate the performance of the analytical instrument and assay without human intervention in the measurement process. The device itself is an automated immunoassay system that produces quantitative results.

6. The Type of Ground Truth Used:

   • The "ground truth" in this context refers to the quantitative measurements of cTnI levels themselves. For the method comparison, the predicate device (Access hsTnI on the Access 2 Immunoassay System, or the "Current Assay Protocol File (APF)" on the DxI 800) essentially serves as the reference for comparison against the "Proposed APF" on the UniCel DxI 800. Therefore, it's a comparison against an established, legally marketed reference measurement method.

7. The Sample Size for the Training Set:

   • Not specified. This documentation primarily focuses on the validation of the device's analytical performance. While there would have been internal development and optimization (which could be considered "training"), the document does not distinguish a formal "training set" (as might be seen with AI/ML models) from "internal validation" data. The tested datasets described are for analytical validation.

8. How the Ground Truth for the Training Set Was Established:

   • Not specified / Not applicable in the traditional sense. As an IVD assay, the "ground truth" for developing such a test is the accurate quantitative measurement of the analyte (cTnI) in biological samples, requiring highly controlled reference methods and materials. The document indicates the device's principle is a "two-site immunoenzymatic ('sandwich') assay," which is a well-established biochemical technique. The development process would involve extensive characterization against reference standards and known concentrations, rather than establishing ground truth through, for example, expert labeling of clinical data.

Ask a specific question about this device

Immunoassay for the in vitro quantitative determination of cortisol in human urine. The determination of cortisol is used for the recognition and treatment of functional disorders of the adrenal gland.

The electrochemiluminescence immunoassay "ECLIA" is intended for use on cobas e immunoassay analyzers.

The Elecsys Cortisol III immunoassay employs a competitive test principle using a cortisol-specific biotinylated monoclonal antibody and a cortisol-derivative labeled with a ruthenium complex. The Elecsys Cortisol III immunoassay is intended for the in vitro quantitative determination of cortisol in human urine. The determination of cortisol is used for the recognition and treatment of functional disorders of the adrenal gland on the cobas e immunoassay analyzers.

Results are determined via a calibration curve which is instrument-specifically generated by a two-point calibration and a master curve provided via the cobas link.

The Elecsys Cortisol III immunoassay reagent Rack Pack comprises the following:

M Streptavidin-coated microparticles (transparent cap), 1 bottle, 12.4 mL:
Streptavidin-coated microparticles 0.72 mg/mL; preservative.

R1 Anti-cortisol-Ab~biotin (gray cap), 1 bottle, 21.0 mL:
Biotinylated monoclonal anti-cortisol antibody (mouse) 18 ng/mL; danazol 20 μg/mL; MES buffer 100 mmol/L, pH 6.0; preservative.

R2 Cortisol-peptide~Ru(bpy) (black cap), 1 bottle, 21.0 mL:
Cortisol derivative (synthetic), labeled with ruthenium complex, 5 ng/mL; danazol 20 μg/mL; MES buffer 100 mmol/L, pH 6.0; preservative.

MES = 2-morpholino-ethane sulfonic acid

The provided 510(k) summary for the Elecsys Cortisol III device focuses primarily on non-clinical performance evaluations to demonstrate substantial equivalence to a predicate device. It does not describe a study to prove performance against specific acceptance criteria for diagnostic accuracy (e.g., sensitivity, specificity, or agreement with ground truth in a clinical context) with a test set of patient samples.

Here's an analysis of the available information:

1. Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in the traditional sense for diagnostic performance metrics like sensitivity, specificity, or agreement against a clinical ground truth. Instead, it details performance specifications for various analytical aspects and states that these "met the predefined acceptance criteria." These are primarily related to the analytical performance of the assay itself.

2. Sample Size and Data Provenance for Test Set

• Precision (Repeatability & Intermediate Precision): Human urine samples (24-hour urine) and controls. Two replicates per run, two runs per day for 21 days for each of 4 human urine samples and 2 controls. (Total of $4 \text{ samples} \times 2 \text{ replicates/run} \times 2 \text{ runs/day} \times 21 \text{ days} = 336$ measurements for human urine, plus $2 \text{ controls} \times 2 \text{ replicates/run} \times 2 \text{ runs/day} \times 21 \text{ days} = 168$ measurements for controls. Or potentially 42 total runs for each sample/control).
• Analytical Sensitivity (LoB, LoD, LoQ): Not specified beyond "reagents and calibrators" likely being used.
• Linearity/Assay Reportable Range: Dilution series contained a minimum of 9 concentrations. Number of samples not explicitly stated but implies a set of samples specifically created to span the measuring range.
• HAMA: Not specified.
• Endogenous Interferences: Human urine samples (24-hour urine) were used. The number of samples is not explicitly stated.
• Analytical Specificity/Cross-Reactivity: Human urine (24-hour urine) samples. Specific numbers not provided beyond "samples were measured in the presence and absence of the potential cross-reactants."
• Exogenous Interferences – Drugs: In vitro tests performed on 12 commonly used pharmaceuticals and additional special drugs. This implies spiked samples rather than a "test set" of patient samples.
• Method Comparison: "Native 24 h urine samples" for comparison with the predicate device. The number of samples is not specified.
• Reference Range Study: Samples collected from an "apparently healthy population in the United States" across three study sites. The exact number of samples is not provided, but it's sufficient for establishing 2.5th and 97.5th percentiles (typically requires 120+ samples according to CLSI EP28-A3c).

Data Provenance: The document explicitly states "human urine samples (24-hour urine)" for most studies and for the reference range, "collected across three study sites... in the United States." This indicates prospective collection for the reference range study specifically for generating normal values applicable to the US population. For other analytical performance claims, the sample type (human urine) is generally mentioned, suggesting a similar provenance, likely for prospective testing within the manufacturer's lab or clinical sites.

3. Number of Experts and Qualifications for Ground Truth

Not applicable for the Elecsys Cortisol III. This is an in vitro diagnostic device (IVD) that quantitatively measures a biomarker (cortisol). The "ground truth" for such devices is typically established through recognized analytical standards, reference methods, and comparison to a legally marketed predicate device, rather than expert consensus on diagnostic images or clinical assessments. The closest to "ground truth" in this context would be the accuracy against a gold standard analytical method or purified cortisol standards. These details are not provided but are implicit in the validation that relies on CLSI guidelines.

4. Adjudication Method for the Test Set

Not applicable. As this is a quantitative IVD for a biomarker, diagnostic classification and adjudication by experts are not relevant to the described analytical studies. The performance is assessed by comparison to expected analytical results or a predicate device.

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

Not applicable. MRMC studies are typically for imaging devices or software that assist human readers in making a diagnosis. The Elecsys Cortisol III is an automated in vitro diagnostic immunoassay for quantitative measurement of cortisol in urine. It does not involve human readers interpreting cases with or without AI assistance.

6. Standalone Performance Study

Yes, the entire submission describes standalone performance. The Elecsys Cortisol III is an immunoassay designed to operate on cobas e immunoassay analyzers. All the performance data (precision, sensitivity, linearity, interference, cross-reactivity, method comparison) are generated directly from the device's measurement of cortisol in urine samples. The device itself performs the quantitative determination without human-in-the-loop interpretation impacting the measurement results. The method comparison study directly compares its quantitative output to the predicate device's quantitative output.

7. Type of Ground Truth Used

For an IVD like Elecsys Cortisol III, the "ground truth" for the test set is established by:

• Reference standards/Calibrators: For analytical sensitivity (LoB, LoD, LoQ) and linearity studies, known concentrations of cortisol (or materials traceable to them) are used.
• Predicate device comparison: For method comparison, the results from the Elecsys Cortisol III are compared to those obtained from the legally marketed ARCHITECT Cortisol (K062204), which serves as the established "truth" or benchmark for demonstrating substantial equivalence.
• Spiked samples/characterized samples: For interference and cross-reactivity studies, samples with known concentrations of interferents or cross-reactants are used to determine the device's accuracy in their presence.
• Clinically characterized healthy population samples: For the reference range study, samples from healthy individuals are used to establish normal ranges, though this isn't a "ground truth" for diagnostic accuracy.

8. Sample Size for the Training Set

The document does not mention "training set" in the context of an AI/ML algorithm. This device is an immunoassay, which relies on chemical reactions and optical detection, not an AI/ML model that requires a training set. The term "training set" is therefore not applicable here.

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

Not applicable. As noted above, there is no AI/ML training set for this immunoassay device.

Ask a specific question about this device