BrainScope Ahead 100

DEN140025

BRAINSCOPE COMPANY, INC · granted 2014-11-17 · product code PIW · Neurology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.3)
“The Ahead 100 is a portable EEG system consisting of two models: the Ahead M-100 and the Ahead CV-100. As stated in the Indications for Use above, the only functional difference between the M-100 model and the CV-100 model is that the M-100 stores and displays an electronic version of the Military Acute Concussion Evaluation (MACE) cognitive assessment and user-entered responses to the MACE questions in addition to all other device functionality as discussed below. The Handheld Unit employs a color, touch-screen user interface and utilizes proprietary software to perform real-time analyses of the collected EEG data. Using the Handheld Unit, the user is able to review the raw EEG data, view spectral plots, and view a number of calculated quantitative EEG (qEEG) measures including Absolute and Relative Power, Asymmetry, Coherence and Fractal Dimension. The software utilized by the Handheld Unit also processes the collected raw EEG to produce the final Ahead 100 classification.”
AlgorithmThe software utilized by the Handheld Unit also processes the collected raw EEG to produce the final Ahead 100 classification. This data analysis includes filtering the raw EEG, performing artifact reduction, computation of a variety of qEEG features across specific frequency bands, normalization of these computed features, a quality check to identify potential outliers, integration of these features to determine the appropriate classification, and finally a graphical display of this classification to the user.
source quote (p.5)
“The software utilized by the Handheld Unit also processes the collected raw EEG to produce the final Ahead 100 classification. This data analysis includes filtering the raw EEG, performing artifact reduction, computation of a variety of qEEG features across specific frequency bands, normalization of these computed features, a quality check to identify potential outliers, integration of these features to determine the appropriate classification, and finally a graphical display of this classification to the user.”
Adaptive (vs locked)No
source quote (p.5)
“The algorithm used to integrate the computed features and determine a classification was pre-established in a separate study, prior to validation in the B-AHEAD II study.”
PCCPFDA source did not state this
Cybersecurity addressedNo

Validation studies (2)

Bench

sample size not stated

endpoints: Battery charge and discharge according to specification; Impedance measurement and display; EEG signal measurement and display; Noise performance; Common mode rejection ratio (CMRR); Frequency and phase response within EEG frequency bands; Repeatability and reliability testing demonstrating consistency of the device outputs when testing is administered by a variety of physicians as well as when testing is administered on the same subject at multiple different times; Artifact reduction; qEEG feature calculation; Discriminant score calculation and final classification that demonstrates the algorithm performs predictable and repeatable calculations given a fixed or known set of input data; Human factors engineering/usability that obtains either data or feedback from users of the device in order to verify adequate use and operability of the device; Software verification and validation testing as mentioned above that includes a complete device hazard analysis

standards: IEC60601-1:1988+A1: 1991+A2: 1995, IEC60601-2-26: 2002, IEC60601-1-2: 2007, IEC60601-1-4, IEC/UL 60950-1

Prospective clinical

n=552 patients · 11 site(s)

endpoints: sensitivity; specificity; negative predictive value (NPV); positive predictive value (PPV)

Reported performance (4 observations)

sensitivity78.5CI (69.9%, 85.5%)
source quote (p.10)
“78.5% (91/116) (69.9%, 85.5%)”
specificity48.6CI (43.8%, 53.4%)
source quote (p.10)
“48.6% (212/436) (43.8%, 53.4%)”
npvas written: “NPV”89.5CI (84.8%, 93.1%)
source quote (p.10)
“89.5% (212/237) (84.8%, 93.1%)”
ppvas written: “PPV”28.9CI (23.9%, 34.2%)
source quote (p.10)
“28.9% (91/315) (23.9%, 34.2%)”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: De Novo decision summary PDF.

Predicate network

Postmarket — what happened after clearance

Not yet tracked — the weekly postmarket refresh hasn't snapshotted this device.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to De Novo AI/ML devices in the Neurology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/DEN140025