Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K093789
    Device Name
    INTOUCH DIABETES
    Date Cleared
    2010-02-19

    (72 days)

    Product Code
    Regulation Number
    862.1345
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    SYMCARE PERSONALIZED HEALTH SOLUTIONS, INC

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    InTouch™•diabetes is intended for use in home settings to aid people with diabetes and healthcare professionals in the review, analysis and evaluation of historical blood glucose test results to support effective diabetes management. It is intended for use as an accessory to blood glucose meters with data management capabilities. This system is intended for use by people 18 years of age and older. InTouch™•diabetes is not intended to provide treatment decisions or to be used as a substitute for professional healthcare judgment. All patient medical diagnoses and treatment are to be performed under the supervision and oversight of an appropriate healthcare professional.

    Device Description

    InTouch™ediabetes is an online tool that helps patients to manage their diabetes and communicate their blood glucose readings to their invited healthcare professionals, who they partner with in managing their diabetes. InTouch™diabetes enables a blood glucose meter to connect via a Bluetooth accessory, the Polymap Wireless Polytel® GMA Glucose Meter Accessory (GMA), to a cellular phone in order to transmit meter readings to online system, which is accessible by the the InTouch™.diabetes healthcare provider as well as the patient. The Polymap Wireless Polytel® GMA(s) that are utilized by InTouch™.diabetes are currently marketed accessories cleared for OTC use via 510(k) K091296. Patients are offered insights into their condition and in partnership with their HCPs can engage in new self-management activities, including monitoring regimens. Education content and interactive communications with their caregivers, disease managers, or educators, are available. The InTouchTModiabetes application software that resides on the mobile phone transmits the patient's blood glucose measurement data from a glucose meter to the InTouch™, diabetes central repository database. The data is analyzed to recognize health patterns, show trends, and this information is displayed visually along with personalized health information and education. InTouch™odiabetes does not provide alerts/alarms, specific treatment or insulin does recommendations; or any advertisements and it meets the applicable HIPAA privacy requirements.

    AI/ML Overview

    The provided text describes the "InTouch™•diabetes Version 2.1" device, an accessory to a glucose test system intended for aiding people with diabetes and healthcare professionals in reviewing, analyzing, and evaluating historical blood glucose test results.

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

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided documentation does not explicitly state specific numerical acceptance criteria for the device's performance in terms of accuracy or efficacy (e.g., specific thresholds for blood glucose deviation, or target user comprehension percentages). Instead, the studies focused on software functionality and usability.

    However, based on the general statements and the nature of the device (an accessory for data management, not a diagnostic tool), the implicit acceptance criteria are:

    Acceptance Criteria CategoryReported Device Performance
    Functional EquivalenceThe device performs as well as, or better than, the legally marketed predicate device (SymCare Diabetes Management Program(DMP) V2.03, K083263; MCT Diabetes Version 2.0; K073699; Think Positive (t+) Diabetes Management System, K061328).
    Software Functionality and Design ComplianceThe software must meet all specified requirements and design specifications.
    UsabilityThe device and its labeling (user manual, website) must be comprehensible and usable by the intended user (people 18 years of age and older) for safe and effective use.
    Safety and EffectivenessThe device must be safe and effective for its intended use (review, analysis, and evaluation of historical blood glucose).
    No Treatment Decisions/AlarmsThe device must not provide alerts/alarms, specific treatment or insulin recommendations, or advertisements. Additionally, it must adhere to HIPAA privacy requirements.

    2. Sample Size for Test Set and Data Provenance

    The document mentions "a human factors/usability study was performed" but does not specify the sample size for this study (the number of participants).

    The document does not provide information on the data provenance (e.g., country of origin, retrospective or prospective data) for the usability study. It does discuss transmitting meter readings via a Bluetooth accessory and cellular phone, implying prospective data collection during use, but no details are given about the study's data collection methodology.

    3. Number of Experts and Qualifications for Ground Truth

    For the human factors/usability study, it's not explicitly stated that "experts" were used to establish ground truth in the traditional sense of clinical interpretations. Instead, the study measured the "usability of the InTouch™diabetes" and identified "critical areas that require modification to improve comprehensibility." The "ground truth" here would be user experience and comprehension, evaluated directly from the study participants' interactions and feedback.

    The readability assessment used the Fry Scale, which is an objective measure of text complexity, so no human experts were needed to establish "ground truth" for readability; it's a calculated score.

    4. Adjudication Method for the Test Set

    No adjudication method (e.g., 2+1, 3+1) is mentioned. Given the nature of the "human factors/usability study," the evaluation likely involved direct observation, questionnaires, and interviews with users, rather than expert judgment on discrete diagnostic outcomes requiring adjudication.

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

    No MRMC comparative effectiveness study was done or reported. The device is a data management accessory, not a diagnostic imaging device that typically uses MRMC studies. The focus was on software functionality, usability, and demonstrating substantial equivalence to predicate devices.

    6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

    A standalone performance study of the "algorithm only" (without human-in-the-loop) was effectively performed as part of the "Non-clinical Testing." This included:

    • Software verification and validation testing: This covers unit, integration, and system-level testing, which evaluates the software's internal logic and data processing capabilities independently of human interaction.
    • Load testing: This assesses the system's performance under various loads, demonstrating its robustness and functional capacity.

    These tests confirm the software's ability to process and display data correctly as intended without human intervention in the data processing itself, though the interpretation of that processed data is always intended for human users (patients and HCPs).

    7. Type of Ground Truth Used

    • For Software Verification and Validation: The ground truth was the defined requirements and design specifications for the software. The tests ensured the software's output matched the expected output based on these specifications.
    • For Human Factors/Usability Study: The ground truth was the observed user behavior and direct feedback regarding comprehensibility and ease of use. There was also an objective readability score (Fry Scale) for the manuals and website content.

    8. Sample Size for the Training Set

    The document does not mention a training set in the context of an AI/ML model, as this device appears to be a rule-based software system for data management and display, rather than an adaptive AI system that learns from a training set. The "analysis to recognize health patterns, show trends" likely refers to pre-programmed algorithms rather than machine learning trained on data.

    9. How Ground Truth for the Training Set Was Established

    As no training set is mentioned or implied for an AI/ML model, this question is not applicable based on the provided information.

    Ask a Question

    Ask a specific question about this device

    K Number
    K083263
    Date Cleared
    2009-03-13

    (128 days)

    Product Code
    Regulation Number
    862.1345
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    SYMCARE PERSONALIZED HEALTH SOLUTIONS, INC

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The SymCare Diabetes Management Program is intended for use in home settings to aid people with diabetes and healthcare professionals in the review, analysis and evaluation of historical blood glucose test results to support effective diabetes management. It is intended for use as an accessory to blood glucose meters with data management capabilities. This system is intended for use by people 18 years of age and older. The SymCare Diabetes Management Program is not intended to provide treatment decisions or to be used as a substitute for professional healthcare judgment. All patient medical diagnoses and treatment are to be performed under the supervision and oversight of an appropriate healthcare professional.

    Device Description

    The SymCare Diabetes Management Program (DMP) is an online tool that helps patients to manage their diabetes and communicate their blood glucose readings to their healthcare providers, healthcare providers manage their diabetes patient population, and insurance companies manage their diabetes patient and health care provider populations. The DMP enables a blood glucose meter to connect via a Bluetooth accessory, the Polymap Wireless Polytel® GMA Glucose Meter Accessory (GMA), to a cellular phone. Once the mobile phone has gathered the data from the meter, it transmits the data to a centralized repository database. The data is analyzed to recognize health patterns, show trends, and offer personalized health information.

    AI/ML Overview

    The SymCare Diabetes Management Program is an online tool that helps patients manage their diabetes and communicate blood glucose readings to healthcare providers. It also assists healthcare providers and insurance companies in managing diabetes patient populations. The device connects a blood glucose meter via a Bluetooth accessory (Polytel® GMA Glucose Meter Accessory) to a cellular phone, which then transmits data to a centralized database for analysis, trend identification, and personalized health information.

    1. Acceptance Criteria and Reported Device Performance

    The provided 510(k) summary does not specify quantitative acceptance criteria in terms of accuracy, sensitivity, or specificity for the SymCare Diabetes Management Program. Instead, the "Nonclinical Tests" and "Clinical Tests" sections describe the device's performance in terms of software verification, validation, and usability.

    Acceptance Criteria (Implied)Reported Device Performance
    Compliance with software requirements and design specificationsExtensive software verification and validation testing conducted, demonstrating compliance.
    Comprehension by study doctors, medical team members, and participantsDemonstrated comprehension of the DMP.
    Appropriate human factorsDemonstrated appropriate human factors related to the DMP.
    Ease of useDemonstrated ease of use of the DMP.

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

    • Sample Size for the Test Set: The document does not explicitly state the sample size for the usability study (referred to as "Clinical Tests"). It mentions "study doctors, medical team members, and participants," but gives no numbers.
    • Data Provenance: The document does not specify the country of origin for the data or whether the study was retrospective or prospective.

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

    The concept of "ground truth" as typically applied to diagnostic algorithms (e.g., pathology, expert consensus on imaging) is not directly applicable here. The "Clinical Tests" section focuses on usability and comprehension.

    • Number of Experts: Not specified. The study involved "study doctors" and "medical team members."
    • Qualifications of Experts: Not specified.

    4. Adjudication Method for the Test Set

    Since the study described is a usability study and not an evaluation of diagnostic accuracy, an adjudication method for establishing a "ground truth" (e.g., 2+1, 3+1) is not relevant or described. The study assessed comprehension, human factors, and ease of use.

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

    No Multi-Reader Multi-Case (MRMC) comparative effectiveness study is mentioned in the provided information. The study described focuses on the usability of the device for a single user (patient or healthcare professional).

    6. Standalone Performance Study

    A standalone performance study, in the sense of an algorithm-only performance without human-in-the-loop, is not explicitly described in terms of diagnostic accuracy. The "Nonclinical Tests" section refers to "extensive software verification and validation testing" demonstrating compliance to requirements and design specifications, which would cover software functionality and integrity. However, this is distinct from quantifying the clinical performance of an AI algorithm in isolation. The SymCare DMP is described as an "online tool that helps patients to manage their diabetes and communicate their blood glucose readings to their healthcare providers," implying a human-in-the-loop design where the data analysis is presented to and used by individuals.

    7. Type of Ground Truth Used

    The type of ground truth used is related to usability and comprehension assessments. The "Clinical Tests" evaluated:

    • Comprehension by users (doctors, medical team members, and participants) regarding the DMP.
    • Appropriateness of human factors.
    • Ease of use.

    This is a qualitative form of "ground truth" based on user feedback and observation rather than a definitive medical outcome or diagnosis.

    8. Sample Size for the Training Set

    The document does not provide any information about a "training set" or sample size for it. This typically applies to machine learning models that are trained on data. While the device does "analyze data to recognize health patterns, show trends, and offer personalized health information," there is no description of an AI/ML model training process. The submission focuses on software validation and system usability.

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

    Since no training set is described or implies a machine learning model, information on how its ground truth was established is not applicable or provided.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1