Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    DEN110019
    Device Name
    NEBA SYSTEM
    Date Cleared
    2013-07-15

    (585 days)

    Product Code
    Regulation Number
    882.1440
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K885306, K883149, K112319

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

    The Neuropsychiatric EEG-Based ADHD Assessment Aid (NEBA®) uses the theta/beta ratio of the EEG measured at electrode CZ on a patient 6-17 years of age combined with a clinician's evaluation to aid in the diagnosis of ADHD.

    NEBA should only be used by a clinician as confirmatory support for a completed clinical evaluation or as support for the clinician's decision to pursue further testing following a clinical evaluation. The device is NOT to be used as a stand-alone in the evaluation or diagnosis of ADHD.

    Device Description

    The NEBA System consists of the following high-level sub-systems:

    1. Compact EEG (CEEG) recording system
    2. EEG data archive and communications system (EDACS)
    3. NEBA Analysis System (NAS).

    The CEEG Recording System is used to acquire EEG data from the patient and consists of a dedicated portable computer and monitor (CEED Computer), EEG amplifier hardware (CEEG Amplifier), and EEG recording software (CEEG Software). EEG data is collected by the CEEG Recording System using FDA cleared electrodes and electroconductive gel. The International 10-20 System is used as a basis for electrode placement. A single recording electrode is placed on the scalp at location CZ, while the ground electrode is placed a location FZ (midline frontal) and linked ears reference. Electrooculography (EOG) is used to monitor eve blinks and gross eve movement.

    The EDACS is used to provide secure transmission and storage for training and patient data collected at remote sites and consists of server hardware and software and data storage. Data collected from the CEEG System is securely transmitted via EDACS to secure storage.

    The NAS is stand-alone software which takes in EEG data recorded by the CEEG system, processes it, and produces the final NEBA Report. The NAS consists of EEG artifact reduction and review software. EEG Frequency Analysis and theta-beta ratio calculation software, and the NEBA Report Generator software. Trained technicians first use the NAS to perform manual and algorithm-based artifact reduction of the EEG signal. The artifact-reduced EEG data is then processed using frequency spectrum analysis software, which converts the time-domain EEG data into the frequency domain. Calculations are then performed to determine the ratio of the power of the theta band ( (000) Hz). Finally, the results of the theta-beta ratio Hz) to the beta band ( calculations are processed by the NEBA Report Generator to generate the report provided to the clinician.

    The high-level NEBA sub-systems form an EEG recording and analysis system that is used to compare an individual's quantified EEG with clinical reference values. NEBA provides clinicians with a specific EEG marker of activity in the form of a power ratio. (b)(4) This ratio is computed by adjusted TBR cutoffs are provided that are specific to the NEBA processing and analysis of EEG.

    The NEBA interpretive report is transmitted back to the clinician's office and offers two general possibilities that depend on the combination of the NEBA result with the clinician's initial evaluation:

    • Confirmatory support
    • Further clinical testing may be needed (possible/probable presence of . complicating conditions)

    Specifically, the interpretative reports may consist of the following:

    1. Along with a clinical diagnostic evaluation. NAS will separate the patients with ADHD as the primary clinical diagnosis into two groups:
      a. A group receiving confirmatory support for presence of ADHD as primary diagnosis.
      b. A group receiving support for the clinician's decision to pursue further testing with focus on other conditions before proceeding with ADHD as primary diagnosis.
    2. Along with a clinical diagnostic evaluation. NAS will separate patients with an uncertain clinical diagnosis regarding ADHD into two groups:
      a. A group receiving support for the clinician's decision to pursue further testing with focus on ADHD.
      b. A group receiving support for the clinician's decision to pursue further testing with focus on other conditions.
    3. Negative for ADHD as the primary clinical diagnosis is always solely determined by the clinician; no ADHD primary diagnosis is possible without the clinician's determination of ADHD.
    AI/ML Overview

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

    Acceptance Criteria and Device Performance

    Note: The document does not explicitly present a table of acceptance criteria as a set of specific numerical targets that the device must meet to be approved. Instead, it describes general requirements for performance testing and then presents the device's measured performance in clinical studies. The table below synthesizes the performance requirements and the reported results.

    Acceptance Criteria (Inferred/Stated Requirement)Reported Device Performance (Adolescents, 12-17.99 years)Reported Device Performance (Children, 6-11.99 years)
    Accuracy (Overall Concordance)88% (65/74)88% (177/201)
    Specificity87% (40/46)97% (96/99)
    Sensitivity89% (25/28)79% (81/102)
    Positive Predictive Value (PPV)81% (25/31)96% (81/84)
    Negative Predictive Value (NPV)93% (40/43)82% (96/117)
    Repeatability (Intraclass Correlation Coeff)0.83 (for theta/beta ratio)0.83 (for theta/beta ratio)
    SafetyNo serious adverse events or device events reportedNo serious adverse events or device events reported
    Non-stand-alone diagnostic natureRequires clinician's initial diagnostic evaluationRequires clinician's initial diagnostic evaluation

    Study Details

    1. Sample Sizes and Data Provenance

    • Test Set Sample Size: 275 subjects in total for diagnostic clinical performance analysis (74 adolescents, 201 children).
    • Data Provenance:
      • Country of Origin: United States (13 geographically distinct clinics).
      • Retrospective/Prospective: The study involved a prospective, double-blinded, multi-site, clinical cohort study (Study 1) for data collection, followed by a prospectively planned retrospective review of de-identified patient files (Study 2) to establish ground truth.

    2. Number of Experts and Qualifications for Ground Truth

    • Number of Experts: 3 experts formed the multidisciplinary clinical team.
    • Qualifications: A clinical psychologist, a neurodevelopmental pediatrician, and a child/adolescent psychiatrist.

    3. Adjudication Method for the Test Set

    • Adjudication Method: Consensus best estimate diagnosis from the multidisciplinary team.

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

    • Was an MRMC study done? Yes, a comparison of "NEBA Interpretation (clinician using NEBA) versus clinician alone" against the clinical reference standard was performed.
    • Effect size of human reader improvement with AI vs. without AI assistance: The document states, "the results indicate that NEBA provides additional information beyond the clinician's initial diagnosis, substantiating the use of NEBA." While specific effect sizes (e.g., changes in AUC or sensitivity/specificity for human readers) for "human readers improve with AI vs without AI assistance" are not numerically quantified in the provided text as, for example, a percentage increase in accuracy, the provided tables (Tables 5 and 6) illustrate the classification shifts when NEBA interpretation is integrated with the clinician's initial diagnosis compared to the clinician's diagnosis alone. These tables show how the final NEBA Interpretation (positive/negative) aligns with the BED, whereas the clinician alone might have categorized cases as ADHD, Uncertain, or Other Condition. For example, for adolescents, out of 28 BED=ADHD cases, the clinician alone correctly identified 24 as ADHD, with 3 uncertain and 1 other condition. With NEBA Interpretation, 25 were identified as positive for ADHD, correctly capturing 22 of the 24 identified as ADHD by the clinician and 3 of the uncertain cases. This represents an improvement in certainty and alignment with the BED.

    5. Standalone Performance Study

    • Was a standalone study done? No, the NEBA system is explicitly stated as "NOT to be used as a stand-alone in the evaluation or diagnosis of ADHD." The performance results presented are for "NEBA Interpretation (NEBA+Clinician's initial diagnosis)."

    6. Type of Ground Truth Used

    • Type of Ground Truth: Expert consensus (Best Estimate Diagnosis - BED) from a multidisciplinary team, based on a comprehensive review of all clinical evaluation data (excluding NEBA results, parent rating scales, and clinician diagnostic conclusions to maintain blinding).

    7. Training Set Sample Size

    • Training Set Sample Size: The document does not explicitly state the sample size of a specific training set. It mentions that "NEBA cutoffs for analysis were pre-established in a separate study." This implies that data was used to train or determine these cutoffs, but the sample size for this is not provided in detail.

    8. How Ground Truth for Training Set was Established

    • How Ground Truth for Training Set was Established: The document states "NEBA cutoffs for analysis were pre-established in a separate study." The specific methodology for establishing ground truth within that separate study is not detailed in the provided text.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1