Search Results

The ReliOn Premier BLU Blood Glucose Monitoring System is comprised of the ReliOn Premier BLU Blood Glucose Meter and the ReliOn Premier Blood Glucose Test Strips.

The ReliOn Premier BLU Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips.

The ReliOn Premier BLU Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control.

The system is intended to be used by a single person and should not be shared.

The system is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The ReliOn Premier BLU Blood Glucose Monitoring System is a blood glucose meter with Bluetooth Low Energy technology that the meter communicates to smartphones wirelessly. The ReliOn Premier BLU BGMS has a target range indicator that upon consulting with a healthcare professional, users have the option to activate the function that displays blood glucose measurement results on a colored backlight display. By default, this indicator function is set to OFF. However, it is recommended that users consult with a healthcare professional to determine the target range for their individual needs.

This document describes the FDA's 510(k) clearance for the ReliOn Premier BLU Blood Glucose Monitoring System, comparing it to a predicate device. The information required for a comprehensive study description, such as that for an AI-based medical device, is not provided in this document. This submission focuses on engineering modifications of an existing device and its equivalence to a predicate, not on a new algorithm's performance or a comparative effectiveness study involving human readers and AI.

Therefore, many of the requested details, particularly regarding AI-specific studies (e.g., MRMC studies, standalone algorithm performance, training data details, expert consensus for ground truth on AI models), are not applicable to this submission.

However, I can extract the information relevant to the device's technical specifications and the non-clinical testing performed.

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

The document does not provide a table of precise quantitative acceptance criteria (e.g., specific thresholds for accuracy, precision) or detailed reported device performance data as would be seen for a new algorithm study. Instead, it describes equivalence to a predicate device and mentions that the non-clinical tests indicated the device "performed as intended and fulfilled the specifications."

The key performance characteristics are compared to the predicate device:

Acceptance Criteria (Implied from the document):
The acceptance criteria are implicitly that the ReliOn Premier BLU Blood Glucose Monitoring System demonstrates "substantial equivalence" to the predicate device, CareSens N Premier BT Blood Glucose Monitoring System (K170614), and that the modifications (target range function, LCD, PCB, labeling) perform as intended and fulfill specifications. Specific quantitative criteria for accuracy, precision, or other performance metrics (e.g., ISO standards for blood glucose meters) are not detailed in this summary.

Reported Device Performance:
"The results of these tests indicated that the ReliOn Premier BLU Blood Glucose Monitoring System, with the proposed changes outlined in this document, performed as intended and fulfilled the specifications."

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

The document does not specify the sample size for any test set (e.g., number of subjects or samples used in the non-clinical tests like software function, power consumption, etc.).
The data provenance (e.g., country of origin, retrospective or prospective) is also not specified for the non-clinical tests mentioned. Given the manufacturer's location, testing likely occurred in South Korea, but this is not confirmed.

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

This is not applicable. The ground truth for a blood glucose monitoring system is typically established against a laboratory reference method (e.g., YSI analyzer) for glucose concentration, not by human experts interpreting results. The document does not mention any expert involvement in establishing ground truth for the non-clinical tests.

4. Adjudication method for the test set

This is not applicable. Adjudication methods are typically used in studies involving human interpretation or subjective assessments, often in imaging or clinical trial contexts. This document describes non-clinical engineering and performance tests for a blood glucose meter.

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

This is not applicable. This document describes a continuous glucose monitoring system, not an AI imaging or diagnostic tool that assists human readers. No MRMC study was conducted or mentioned.

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

This is not applicable in the context of an AI algorithm. This device is a measurement system; its "standalone performance" refers to its accuracy in measuring blood glucose, which is evaluated through specific performance studies (e.g., accuracy against a reference method, precision studies). While these types of studies were undoubtedly performed as part of the overall testing (likely consistent with ISO 15197 for blood glucose monitoring systems, though not explicitly stated in this summary), the details of such quantitative performance studies are not provided in this 510(k) summary. The summary only broadly states that the device "performed as intended and fulfilled the specifications."

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

For a blood glucose monitoring system, the ground truth for glucose measurements is typically established using a laboratory reference method (e.g., YSI glucose analyzer) on venous plasma or serum samples. This is a highly accurate chemical measurement. The document does not explicitly state the ground truth method but this is standard practice for blood glucose meter validation.

8. The sample size for the training set

This is not applicable. This document describes a medical device (blood glucose meter), not an AI model that requires a training set.

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

This is not applicable. As above, this is an engineering device, not an AI model with a training set.

Ask a specific question about this device

LDE4 Lancing device is used with a disposable blood lancet to obtain a capillary blood sample from the fingertip for testing utilizing small amounts of blood.

LDE4 Lancing device is used with a disposable blood lancet to obtain a capillary blood sample from the fingertip for testing utilizing small amounts of blood. It has nine levels of penetration depths. LDE4 lancing device is compatible with CareSens lancets, Soft series disposable blood lancet from SteriLance and most other blood lancets.

The provided text is a 510(k) summary for the LDE4 Lancing Device. It details the device's technical characteristics and the performance data submitted to support its substantial equivalence to a predicate device. However, it does not contain a typical acceptance criteria table with reported device performance in distinct metrics like sensitivity, specificity, accuracy, or F1 score, which are common for AI/ML-based diagnostic devices. This document focuses on demonstrating that the lancing device performs its intended mechanical function, is biocompatible, and can be properly cleaned and disinfected.

Based on the information provided, here's a breakdown of the requested elements:

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

The document doesn't provide specific numerical acceptance criteria in the format of a typical diagnostic device performance table (e.g., sensitivity, specificity). Instead, the performance evaluations verify that the device functions as intended and meets safety standards. The "acceptance criteria" are implied by the successful completion and positive results of the various tests.

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

The document does not explicitly state sample sizes for each particular test type. For instance, the number of devices or material samples used for biocompatibility or cleaning/disinfection validation is not specified. The studies appear to be prospective bench tests and laboratory evaluations, not clinical trials with human subjects as a "test set" in the context of diagnostic AI. The provenance is implied to be laboratory testing conducted by the manufacturer or its contract labs.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not applicable to the provided document. The LDE4 Lancing Device is a mechanical device, and its performance evaluation does not involve establishing ground truth through expert consensus as would be typical for image-based diagnostic AI. The "ground truth" here is objective physical measurements and established biological/chemical testing standards.

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

This information is not applicable. Adjudication methods are typically used in clinical studies or expert reviews to resolve disagreements in interpretation, which is not relevant for the type of bench testing described for a lancing device.

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

This information is not applicable. The LDE4 Lancing Device is a standalone mechanical device, not an AI-assisted diagnostic tool. Therefore, MRMC studies or human reader improvement with AI assistance are not relevant.

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

This information is not applicable. The LDE4 Lancing Device is a mechanical lancing device, not an algorithm, and therefore does not have "standalone" AI performance.

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

The "ground truth" for the performance described in this document is based on:

• Established physical and chemical standards: For puncture depth measurements, material properties, and mechanical functionality.
• Standardized biological testing methods: For biocompatibility (ISO 10993-1) and virus inactivation efficacy.

8. The sample size for the training set

This information is not applicable. The LDE4 Lancing Device is a mechanical device and does not utilize a "training set" in the context of machine learning or AI.

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

This information is not applicable, as there is no training set for a mechanical lancing device.

Ask a specific question about this device

The CareSens N Feliz BT Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips. The CareSens N Feliz BT Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The CareSens N Feliz BT Blood Glucose Monitoring System is comprised of the CareSens N Blood Glucose Test Strips and the CareSens N Feliz BT Blood Glucose Meter.

This FDA 510(k) clearance letter for the CareSens N Feliz BT Blood Glucose Monitoring System does not contain the detailed information required to answer all the questions about specific acceptance criteria and the study that proves the device meets those criteria.

The letter primarily confirms that the device is substantially equivalent to a predicate device and outlines regulatory obligations. It does not include performance data, study design details, or specific acceptance criteria for analytical or clinical performance characteristics of the glucose monitoring system.

Therefore, I cannot provide a complete answer with the requested information based only on the provided text.

However, based on common practices for glucose monitoring systems, I can infer some general aspects and state what information is missing.

Here's an assessment based on the available text and what would typically be found in a 510(k) submission for such a device:

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

Information Not Provided in the Text. The FDA 510(k) letter does not include a table of acceptance criteria or performance data. For a blood glucose monitoring system, this table would typically refer to the ISO 15197 standard (or equivalent FDA guidance) for accuracy of blood glucose measurements.

Typical Acceptance Criteria (Inferred, not from provided text):

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

Information Not Provided in the Text. The letter does not specify sample sizes for test sets or the provenance of the data. For a glucose meter, the test set would typically involve a prospective clinical study with a sufficient number of subjects (e.g., 100-200 patients) to ensure statistically robust results across the measuring range and for different glycemic conditions. The country of origin and whether the study was retrospective or prospective would be detailed in the full 510(k) submission.

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)

Information Not Provided in the Text. This question is typically more relevant for diagnostic imaging AI devices where human readers establish ground truth. For a blood glucose monitoring system, the "ground truth" is established by a highly accurate laboratory reference method, such as a hexokinase or glucose oxidase method calibrated to an NIST traceable standard. There aren't "experts" in the sense of human readers for this type of device's primary performance evaluation.

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

Information Not Provided in the Text. Adjudication methods like 2+1 or 3+1 are used for expert consensus in imaging studies. For a blood glucose meter, the "ground truth" is determined by the reference laboratory instrument, not by expert adjudication. Comparisons are made directly between the device's reading and the reference method's reading.

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. An MRMC comparative effectiveness study is specific to medical imaging devices where human readers interpret images, often with and without AI assistance. The CareSens N Feliz BT Blood Glucose Monitoring System is a standalone device that provides a quantitative measurement of glucose; it does not involve human interpretation of images or AI assistance to human readers in its primary function.

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

Yes, inherently. The performance of a blood glucose monitor is by its nature "standalone" or "algorithm only" in terms of how it processes the blood sample and produces a reading. The device measures glucose electromagnetically or electrochemically and outputs a numerical value. There is no human-in-the-loop performance in the measurement itself (though a human performs the test). The device's accuracy is evaluated directly against a reference method. The letter confirms substantial equivalence without detailing this study, but such a standalone analytical performance study would definitely have been conducted.

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

The ground truth for a blood glucose monitoring system is established by a reference laboratory method (e.g., YSI 2300 STAT Plus Glucose & Lactate Analyzer, or equivalent methods based on hexokinase or glucose oxidase reactions) that is highly accurate and traceable to international standards (e.g., NIST). This is considered the "gold standard" for glucose concentration measurement.

8. The sample size for the training set

Information Not Provided in the Text. Blood glucose meters typically do not have a "training set" in the sense of machine learning algorithms that learn from data. The measurements are based on chemical reactions and electrical signals, with firmware programmed to convert these signals into glucose concentrations. Any "training" or calibration would happen during the manufacturing process and be validated analytically, not through a data-driven training set in the AI sense. If there are advanced algorithms, the training set size would not be disclosed in this FDA letter.

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

Not Applicable/Information Not Provided in the Text. As explained above, blood glucose meters do not typically use "training sets" and "ground truth" in the same way AI algorithms do. Their fundamental principle relies on well-established chemical/electrochemical reactions. Calibration and quality control are done against reference materials and methods, but this is different from establishing ground truth for a machine learning model's training data.

In summary: The provided FDA 510(k) clearance letter serves as regulatory approval but does not contain the detailed technical and scientific study information (like performance metrics, study design, sample sizes, and ground truth establishment methods) necessary to fully answer the specific questions about the device's acceptance criteria and the studies proving it meets them. This information would be found in the full 510(k) submission document, which is not publicly available in this format.

Ask a specific question about this device

The KetoSens BT Blood ß-Ketone Monitoring System is intended for the quantitative measurement of 0-Ketone (betahydroxybutyrate) level in capillary whole blood drawn from the fingertip. The KetoSens BT Blood β-Ketone Monitoring System is intended for self-testing outside the body (in vitro) by people with diabetes at home as an aid to monitor the effectiveness of ketoacidosis control. The system is not intended for use in the diagnosis of or screening for ketoacidosis and is not intended for use on neonates. This system is intended to be used by a single person and should not be shared.

The KetoSens Blood 0-Ketone Test Strips work with the KetoSens BT Blood 0-Ketone Meter to quantitatively measure Blood ß-Ketone in capillary whole blood samples drawn from the finger.

Not Found

I am sorry, but the provided text does not contain any information about acceptance criteria, device performance, validation studies, sample sizes, ground truth establishment, or expert involvement. The document primarily consists of an FDA 510(k) clearance letter for the KetoSens BT Blood $\beta$ -Ketone Monitoring System, outlining its indications for use and regulatory compliance. Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based on the given information.

Ask a specific question about this device

The CareSens S Clear BT Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips. The CareSens S Clear BT Blood Glucose Monitoring System is intended for self testing outside the body (in vitro) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The CareSens S Blood Glucose Test Strips are for use with the CareSens S Clear BT Blood Glucose Meters to quantitatively measure glucose in fresh capillary whole blood samples drawn from the fingertip.

Not Found

This is an FDA 510(k) clearance letter for a medical device (CareSens S Clear BT Blood Glucose Monitoring System), not a study report. Therefore, it does not contain the detailed information required to describe acceptance criteria, device performance, or study specifics like sample sizes, ground truth establishment, or expert qualifications.

The letter confirms that the device is "substantially equivalent" to legally marketed predicate devices. The "Indications for Use" section (page 2) describes what the device is intended for, but it does not present acceptance criteria or performance data for meeting those criteria.

To answer your questions, one would need to access the full 510(k) submission, which is typically not publicly available in its entirety in this format. The 510(k) submission would contain the detailed studies and data to demonstrate substantial equivalence, including performance data against specific acceptance criteria.

Ask a specific question about this device

The CareSens S Fit BT Blood Glucose Monitoring System consists of the CareSens S Fit BT Blood Glucose Meter and the CareSens S Blood Glucose Test Strips. The CareSens S Fit BT Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips. The CareSens S Fit BT Blood Glucose Monitoring System is intended for self testing outside the body (in vitro) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The CareSens S Fit BT Blood Glucose Monitoring System consists of the CareSens S Fit BT Blood Glucose Meter and the CareSens S Blood Glucose Test Strips.

This FDA 510(k) clearance letter does not contain the specific acceptance criteria, study details, and performance data requested. It primarily grants market clearance for the CareSens S Fit BT Blood Glucose Monitoring System based on substantial equivalence to predicate devices.

To answer your questions, I would need access to the actual 510(k) submission summary or a separate performance study report for the device. The provided document only includes:

• Trade/Device Name: CareSens S Fit BT Blood Glucose Monitoring System
• Regulation Number: 21 CFR 862.1345
• Regulation Name: Glucose test system
• Regulatory Class: Class II
• Product Code: NBW
• Indications for Use: The system is intended for quantitative measurement of glucose in fresh capillary whole blood samples from fingertips, for self-testing by people with diabetes at home to monitor diabetes control. It is for single-person use, not for neonates, and not for diagnosis or screening of diabetes.
• Type of Use: Over-The-Counter Use

Without the actual study data, I cannot provide the detailed information requested in your prompt regarding acceptance criteria, reported performance, sample sizes, ground truth establishment, or any comparative effectiveness studies.

Ask a specific question about this device

The ReliOn™ Premier Classic Blood Glucose Monitoring System consists of the The ReliOn™ Premier Classic Blood Glucose Meter and the ReliOn™ Premier Blood Glucose Test Strips. The ReliOn™ Premier Classic Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips and alternate sites such as the forearm, palm, thigh, and calf. Alternate site testing should be used only during steady-state blood glucose conditions. The ReliOn™ Premier Classic Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The ReliOn™ Premier Classic Blood Glucose Monitoring System consists of the The ReliOn™ Premier Classic Blood Glucose Meter and the ReliOn™ Premier Blood Glucose Test Strips.

Here's a breakdown of the acceptance criteria and study information for the ReliOn™ Premier Classic Blood Glucose Monitoring System, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text only touches upon the regulatory approval and indications for use. It does not include a table explicitly stating acceptance criteria or detailed performance results against those criteria. Clinical performance data, often presented in tables conforming to ISO standards (e.g., ISO 15197 for blood glucose monitoring systems), would typically be found in the full 510(k) submission but are not present in this summary.

To illustrate what such a table would look like for a blood glucose monitoring system, I'll describe typical acceptance criteria based on ISO 15197 (a common standard for such devices), and then indicate that the provided document does not contain the performance data.

Hypothetical Table (Based on typical ISO 15197 standards; performance data not in document):

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

The provided document does not contain any information regarding the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective nature). This information would typically be detailed in the study report itself.

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

The provided document does not contain any information regarding the number or qualifications of experts used to establish the ground truth. For blood glucose monitors, the "ground truth" (reference method) is typically established using a high-precision laboratory analyzer, not usually by human experts in the same way as, for example, diagnostic imaging.

4. Adjudication Method for the Test Set

As the "ground truth" for blood glucose monitors is typically an objective measurement from a laboratory reference method, an adjudication method (like 2+1, 3+1 consensus) for the test set is generally not applicable or mentioned in the context of device accuracy for this type of product.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and Effect Size

MRMC comparative effectiveness studies are typically performed for diagnostic imaging devices where human interpretation is a key component and the AI's role is to assist human readers. For a blood glucose monitoring system like the ReliOn™ Premier Classic, which is a standalone measurement device, an MRMC study is not relevant or applicable, and therefore, no information is provided.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done

The ReliOn™ Premier Classic Blood Glucose Monitoring System is a standalone device. Its performance, as designed and intended, is the "algorithm only" or system-only performance without a human-in-the-loop directly interpreting the result for diagnostic purposes (the human reads the result and takes action, but doesn't "interpret" it in the way a radiologist interprets an image). Therefore, the accuracy and precision studies performed for such a device would inherently be standalone performance studies.

7. The Type of Ground Truth Used

For a blood glucose monitoring system, the ground truth is typically established by measurements from a laboratory reference method (e.g., YSI 2300 STAT Plus Glucose & Lactate Analyzer or similar) which is considered highly accurate and precise. The provided document does not explicitly state the type of ground truth used, but this is the standard practice for such devices.

8. The Sample Size for the Training Set

The provided document does not contain any information regarding the sample size for a training set. Blood glucose meters do not typically involve "training" a machine learning algorithm in the same way modern AI algorithms do. Their calibration and algorithms are developed based on extensive characterization using chemical and electrical engineering principles, and clinical/analytical validation. If there were "training data" for a calibration curve, it would be part of the device's inherent design and manufacturing process, rather than a separate "training set" in the AI sense.

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

As noted above, the concept of a "training set" and establishing ground truth for it, in the context of machine learning, is not explicitly applicable to a traditional blood glucose monitoring system. The device's calibration and measurement principles are based on established electrochemical reactions and sensor design, validated against laboratory reference methods.

Ask a specific question about this device

The GLUCOCARD Shine Express Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips. The GLUCOCARD Shine Express Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The GLUCOCARD Shine Blood Glucose Test Strips are for use with the GLUCOCARD Shine Express Blood Glucose Meters to quantitatively measure glucose in fresh capillary whole blood samples drawn from the fingertip.

The GLUCOCARD Shine Connex Blood Glucose Monitoring System is intended for the quantitative measurement of glucose in fresh capillary whole blood samples drawn from the fingertips. The GLUCOCARD Shine Connex Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The GLUCOCARD Shine Blood Glucose Test Strips are for use with the GLUCOCARD Shine Connex Blood Glucose Meters to quantitatively measure glucose in fresh capillary whole blood samples drawn from the fingertip.

The GLUCOCARD Shine Connex Blood Glucose Monitoring System consist of a hand held GLUCOCARD Shine Connex Blood Glucose Meter, GLUCOCARD Shine Blood Glucose Test Strip, and GLUCOCARD Shine Glucose Control Solution. The GLUCOCARD Shine Express Blood Glucose Monitoring System consist of a hand held GLUCOCARD Shine Express Blood Glucose Meter, GLUCOCARD Shine Blood Glucose Test Strip, and GLUCOCARD Shine Glucose Control Solution. The two candidate test systems are derived from the same design platform as their predicate device, CareSens N Premier Blood Glucose Monitoring System/CareSens N Premier BT Blood Glucose Monitoring System (K170614). The candidate devices are modified versions of the predicate device to suit the market needs for test systems with Bluetooth and talking features. The GLUCOCARD Shine Connex Blood Glucose Meter is a Bluetooth meter, similar to the CareSens N Premier BT Blood Glucose Meter, whereas the GLUCOCARD Shine Express Blood Glucose Meter is enabled with a talking feature (English and Spanish).

Both candidate devices are used with the GLUCOCARD Shine Blood Glucose Test Strip and GLUCOCARD Shine Glucose Control Solution, which are the same in chemical composition, fundamental scientific technology, intended use and operating principle as with the components of the predicate device, cleared in K170614. The only difference between the test strip & control solution of the candidate device and the ones of the predicate device is the brand name.

This is a medical device application for two blood glucose monitoring systems, GLUCOCARD Shine Connex and GLUCOCARD Shine Express. As such, the acceptance criteria are based on established performance standards for blood glucose meters, primarily ISO 15197:2013 or equivalent.

Here's an analysis of the provided text to fulfill your request:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a table format for accuracy or precision, nor does it provide specific numerical performance results for the new devices. However, it does refer to "pre-determined Pass/Fail criteria" and concludes that the device passed "all of the tests."

For blood glucose monitoring systems, a common standard for accuracy is ISO 15197:2013, which typically requires:

• For glucose concentrations < 100 mg/dL: 95% of results must be within ±15 mg/dL of the reference method.
• For glucose concentrations ≥ 100 mg/dL: 95% of results must be within ±15% of the reference method.

Given that this is a 510(k) submission and the device is deemed substantially equivalent, it implies that the device met similar, if not identical, criteria to its predicate device (CareSens N Premier BGMS/CareSens N Premier BT BGMS, K170614), which would have needed to meet such standards.

Inferred Table:

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

The document does not explicitly state the sample size for the clinical or analytical test set used for performance evaluation of the GLUCOCARD Shine Connex or GLUCOCARD Shine Express. It only mentions:

• "Verification, validation and testing activities were conducted to establish the performance, functionality and liabilities of the modified devices."
• "The device passed all of the tests based on pre-determined Pass/Fail criteria."

Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective.

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

This information is typically not applicable for blood glucose monitoring systems. The "ground truth" for blood glucose measurements is established by a highly accurate laboratory reference method (e.g., YSI analyzer), not by expert consensus. Therefore, no "experts" in the human reviewer sense are used for establishing the ground truth.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

Not applicable for blood glucose monitoring systems. The ground truth is determined by an objective, quantitative laboratory reference method, not by human adjudication of images or clinical cases.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, If So, What War the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

Not applicable. Blood glucose monitoring systems are standalone diagnostic devices and do not involve human "readers" interpreting results in a way that would necessitate an MRMC study or AI assistance. The device directly provides a numerical glucose value.

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

Yes, the performance evaluation performed for this device is a standalone performance assessment. Blood glucose meters are designed to provide a direct, quantitative glucose measurement without human interpretation or intervention in the measurement process itself. The "device performance" mentioned refers to the accuracy and precision of the meter and test strip system in autonomously measuring glucose.

7. The Type of Ground Truth Used

The ground truth for blood glucose monitoring systems is typically established using a laboratory reference method known for its high accuracy and precision, such as a YSI glucose analyzer, measuring glucose in plasma or whole blood. The document doesn't explicitly name the reference method used but this is the standard practice.

8. The Sample Size for the Training Set

The document does not mention a "training set" in the context of device performance studies. Blood glucose monitoring systems are not typically developed using machine learning models that require distinct training sets for their primary measurement function. Their performance is validated through analytical and clinical studies.

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

As explained in point 8, a "training set" in the machine learning sense is not applicable here. The ground truth for the validation of the device's accuracy would be established by the laboratory reference method, as described in point 7.

Ask a specific question about this device

The CareSens S Fit Blood Glucose Monitoring System is intended for the surement of glucose in fresh capillary whole blood samples drawn from the fingertips. The CareSens S Fit Blood Glucose Monitoring System is intended for self-testing outside the body (in vitro) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The system is intended to be used by a single person and should not be shared. It is not intended for use on neonates and is not for the diagnosis or screening of diabetes.

The CareSens S Blood Glucose Test Strips are with the CareSens S Fit Blood Glucose Meters to quantitatively measure glucose in fresh capillary whole blood samples drawn from the fingertip.

The CareSens S Fit BGMS is a derivation from the same design file as it predicate device, CareSens N Premier and CareSens N Premier BT Blood Glucose Monitoring System, utilizing a new test strip. This Premarket Notification (510(k) is intended to demonstrate that the candidate devices to be marketed is safe and effective as the predicate device.

The CareSens S Fit BGMS consists of a blood glucose meter, single use test strips, and control solutions with two different glucose concentrations ("Level 1" and "Level 2" ranges). The CareSens S Fit BGMS is based on an electrochemical biosensor technology (electrochemical). The System measures the glucose level in whole blood samples using a small electrical current generated in the test strips. The following items are included in the CareSens S Fit BGMS Blood Glucose Monitoring system:

• 1 CareSens S Fit Blood Glucose Meter
• 10 CareSens S Blood Glucose Test Strips
• 1 Lancing device
• 10 Lancets
• 1 Owner's Booklet
• 1 Quick Reference Guide
• 1 Battery (3.0V lithium battery)

The following items are compatible with the CareSens S Fit BGMS and are available separately.

• CareSens S Blood Glucose Test Strips
• CareSens S Glucose Control Solution

The provided text describes the performance testing and acceptance criteria for the CareSens S Fit Blood Glucose Monitoring System, particularly in the context of its 510(k) submission (K180866) to the FDA.

Here's an organized breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document frequently refers to "acceptance criteria" and "satisfying" or "meeting" them, particularly referencing the FDA SMBG Guidance (2016). While specific numerical acceptance criteria for each test (e.g., CV% for precision above a certain threshold) are often implied rather than explicitly stated in a single table, the key accuracy criteria from the Method Comparison/User Performance study are provided.

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

• Method Comparison/User Performance Study:
  • Sample Size: At least 350 different subjects. The specific study conducted for CareSens S Fit had 376 subjects.
  • Data Provenance: Not explicitly stated, but the submission is from Seoul, Korea (i-SENS, Inc.), suggesting the data is likely from Korea. The study is prospective as it involves subjects participating in a user evaluation of the device.
• Within-Run Precision Evaluation: 10 meters and 500 test strips (from 10 vials of 3 manufacturing lots) for each sample concentration.
• Intermediate Precision Evaluation: 10 meters and 500 test strips (from 10 vials of 3 manufacturing lots) for each sample concentration.
• Linearity Evaluation: 11 evenly spaced concentrations of blood samples.
• Hematocrit Effect Test: Five concentration levels of blood samples at nine hematocrit levels for three lots of test strips.
• Test Strip Stability (Before Opening): Three strip lots tested with 24 distinct samples at each testing point for 462 days. Total of 360 data points.

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

The document does not mention the use of human experts to establish ground truth for the test set. Instead, it relies on a laboratory comparator method.

4. Adjudication Method for the Test Set

Not applicable, as expert adjudication was not described for establishing ground truth. The ground truth was established by a laboratory reference instrument.

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

No, an MRMC comparative effectiveness study, in the sense of comparing human readers with and without AI assistance, was not explicitly done. This device is a Blood Glucose Monitoring System where the "reading" is performed by the device itself, not a human interpreter of images or complex data. The "user performance" study assesses the device's accuracy in the hands of intended users, and their ability to follow instructions, not their diagnostic performance with or without computational aid.

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

Yes, numerous "standalone" tests were conducted where the device's performance was evaluated against a laboratory reference. These include:

• Within-Run Precision
• Intermediate Precision
• Linearity
• Additional Accuracy at Extreme Glucose Values
• Interfering Substance Evaluation
• Hematocrit Effect Test
• Various Stability Tests (Accelerated, Before Opening, After Opening, Extended Open Vial)
• Altitude Test
• Operating Condition Test
• Flex Study
• Cleaning and Disinfection Study

The Method Comparison/User Performance study combines both standalone device accuracy (in the hands of users) with usability aspects, but the core accuracy measurement is a standalone performance metric against a reference.

7. The Type of Ground Truth Used

The primary ground truth used for performance evaluation, particularly for accuracy, was:

• Laboratory Reference Instrument: The YSI 2300 STAT Plus glucose analyzer was consistently used as the reference equipment (comparator method) for measuring glucose levels in blood samples.

8. The Sample Size for the Training Set

The document does not specify a separate training set for an algorithm in the way that would typically be described for AI/machine learning models. The CareSens S Fit BGMS is an electrochemical biosensor system, implying its performance is largely governed by its hardware and electrochemical design, rather than a machine learning algorithm trained on a large dataset. The development and calibration of such a system would involve extensive testing and refinement, but this is not typically referred to as a "training set" in the context of this type of medical device's regulatory submission.

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

As no specific "training set" in the AI/ML sense is mentioned, this question is not directly applicable. The device's calibration and design would be based on established glucose measurement principles and validated against reference methods during its development phase.

Ask a specific question about this device

KetoSens Blood ß-Ketone Monitoring System is intended to be used for the quantitative measurement of f-Ketone (beta-hydroxybutyrate) level in capillary whole blood samples drawn from the fingertip. The KetoSens Blood B-Ketone Monitoring Systems are for self-testing outside the body (for in vitro diagnostic use) in the home as an aid to monitor the effectiveness of diabetes control program. The system is not in the diagnosis of or screening for diabetes mellitus and is not intended for use on neonates. This system is intended to be used by a single person and should not be shared.

The KetoSens Blood ß-Ketone Test Strips work with the KetoSens Blood ß-Ketone Meter to quantitatively measure Blood ß-Ketone in capillary whole blood samples drawn from the fingertip.

KetoSens Multi Blood p-Ketone Monitoring System is intended to be used for the quantitative measurement of f-Ketone (beta-hydroxybutyrate) level in capillary whole blood from the fingertip and venous EDTA whole blood. KetoSens Multi Blood ß-Ketone Monitoring System is intended for in vitro diagnostic use and is intended for multiple-patient use in professional healthcare settings as an aid to monitor the effectiveness of diabetes control program. The system is not intended for use in the diagnosis of or screening for diabetes mellitus and is not intended for use on neonates. This system should only be used with single-use, auto-disabling lancing devices.

The KetoSens Multi Blood p-Ketone Test Strips work with Blood ß-Ketone Meter to quantitatively measure Blood B-Ketone in capillary whole blood samples drawn from the fingertip and venous whole blood drawn in professional healthcare settings.

The KetoSens Blood ß-Ketone Monitoring System/KetoSens Multi Blood ß-Ketone Monitoring System consists of a meter, single use test strips, and control solutions with two different B-Ketone concentrations ("Control A" and "Control B" ranges).

The KetoSens Blood ß-Ketone Monitoring System/KetoSens Multi Blood ß-Ketone Monitoring System is based on an electrochemical biosensor technology (electrochemical). The System measures the Blood ß-Ketone level in whole blood samples using a small electrical current generated in the test strips.

This document focuses on the KetoSens Blood β-Ketone Monitoring System and its validation studies. It describes various performance tests conducted to ensure the device meets specified criteria, primarily focusing on accuracy, precision, and usability.

Here's an organized breakdown of the acceptance criteria and study details based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a single table labeled "Acceptance Criteria." However, acceptance criteria are implicitly stated within the "System Accuracy Test" and "Consumer Study" results, and "Repeatability Test" and "Intermediate Precision Test" conclusions.

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

• System Accuracy Test (Capillary Blood): 204 samples.
• System Accuracy Test (Venous Blood): 204 samples.
• Repeatability Test: 300 measurements (N=300 for each of 5 concentration levels). This suggests a large number of readings rather than 300 unique samples.
• Intermediate Precision Test: 600 measurements (N=600 for each of 3 control levels).
• Consumer Study: 185 general users.
• Point-of-Care Test: 124 patients for capillary samples, 123 patients for venous samples.
• Hematocrit Effect Test: 5 different hematocrit levels, 5 different ketone intervals, measured using 30 meters and 3 lots of strips.
• Interference Test: 2 ketone concentrations, across 29 interferents, with 3 strip lots.
• Altitude Test: Not specified in terms of distinct sample numbers, but tested.
• Operating Condition Test: Not specified in terms of distinct sample numbers, but tested.

Data Provenance: The document does not explicitly state the country of origin of the data or whether the studies were retrospective or prospective. However, based on the nature of clinical evaluation, consumer studies, and POC tests involving patient samples and human participants, these are typically prospective studies. The company, i-SENS, Inc., is based in Seoul, Korea, suggesting the studies likely took place there or in a similar regulatory environment.

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

• The document mentions "trained staff" and "Health Care Professionals" (HCPs) in the context of comparative measurements.
• In the Consumer Study, results of general users are compared against "Rx Imola reference values" and "BKMS results obtained by trained staff."
• In the Point-of-Care Test, "Health care professionals" (six members) performed tests, and "The study staff operates the reference equipment and modify the KetoSens Multi BKMS results are compared against the reference values."
• The qualifications of these "trained staff" or "Health Care Professionals" are not explicitly defined (e.g., "radiologist with 10 years of experience"). Their role is to operate the reference equipment and/or the candidate device for comparison.

4. Adjudication Method (e.g. 2+1, 3+1, none) for the Test Set

The document does not describe an adjudication method for the test set in the context of expert review or consensus, as would be typical for image-based diagnostic AI. For a quantitative measurement device, the "ground truth" is typically established by comparative measurement to a highly accurate reference method. Discrepancies are usually managed through statistical analysis rather than an adjudication process among human readers.

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

This is not applicable as the device is a quantitative blood β-ketone monitoring system, not an AI-based diagnostic imaging tool that assists human readers. Therefore, an MRMC study and analysis of human reader improvement with AI assistance are not relevant to this device.

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

The device is a standalone quantitative measurement system. Its performance (accuracy, precision) is evaluated independently against a reference standard (Rx Imola equipment). The human user's role is to operate the device correctly, consistent with its "intended to be used for the quantitative measurement" function. The consumer study and POC test assess the usability for target users (self-testing or HCPs), but the core performance data in the system accuracy tests represent the device's measurement capabilities.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The ground truth for the quantitative measurement of β-ketone levels was established using a reference measurement procedure/equipment. Specifically:

• "The accuracy of KetoSens is evaluated with clinical evaluation using capillary and venous blood samples... and with the standard measurement."
• "KetoSens BKMS did not show significant difference with respect to the Rx Imola equipment, nor with different altitudes at all ketone concentrations."
• In the Consumer Study and POC test, results were compared against "Rx Imola reference values."

Therefore, the ground truth is comparative measurement to a recognized laboratory reference method/instrument (Rx Imola).

8. The Sample Size for the Training Set

The document describes performance evaluation (test set) studies but does not mention a 'training set' in the context of machine learning model development. This is because the KetoSens Blood β-Ketone Monitoring System is based on electrochemical biosensor technology, which relies on a chemical reaction to produce an electrical current proportional to the analyte, rather than an AI/ML algorithm that requires training data.

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

As the device does not employ an AI/ML algorithm requiring a 'training set,' this question is not applicable. The underlying principle is electrochemical, not data-driven machine learning.

Ask a specific question about this device