Neuro Scan AI Solutions
DEMO READY · CHB-MIT VALIDATED · PRE-PILOT
ETHICS REVIEW IN PROGRESS · 2 TR · 1 FI · 1 US · 2026
REC PT · 08 22 CH · 256 Hz BIPOLAR · 10-20
SESSION · 03:42:18 NSAS · MONITOR
01FP1-F7
02F7-T7
03T7-P7
04P7-O1
05FP2-F8
06F8-T8
CLASSIFIER · ONLINE
Monitoring
Cross-subject model · v2.4
SEIZURE DETECTED
CH · P7-O1 · focal
Onset 02:14:03 · latency 2.4s · confidence 0.93
SENSITIVITY
75.34%
FAR · 24H
0.1
LATENCY
3s
EVENTS · 24H
3
00:00 · 03:42:18 · 24:00

We detect epileptic seizures from raw EEG — in real time.

Neuro Scan AI Solutions is a Finnish AI & robotics company building clinical-grade epilepsy diagnosticspediatric-first, where the diagnostic gap is widest. The wearable EEG headset and mobile app are built; the detection engine is validated on the CHB-MIT pediatric dataset. Live hospital deployment is the next gate — ethics-committee reviews are in progress at four sites (two in Turkey, one in Helsinki, one in the United States).

0
Window classification accuracy
CHB-MIT · LOO cross-subject
24
Scalp EEG channels
supported (hardware)
92
Engineered features per
5-second window
0
Hours of continuous
dataset EEG tested
50M people live with epilepsy worldwide · WHO 12M misdiagnosed — even by specialists · Oto 2017 higher mortality · untreated epilepsy CHB-MIT Pediatric EEG Dataset · 24 patients · 916h 173 test seizures across 24 patients (Shoeb 2010) 72.63% 5-fold subject-wise sensitivity 126K EEG procedures / year · Europe 3s median onset latency · patient-specific mode 0.1 false alarms / 24h · CHB-MIT Up to 24 channels · 256Hz · bipolar montage 5s non-overlapping windows · event-driven 32 selected features per channel 50M people live with epilepsy worldwide · WHO 12M misdiagnosed — even by specialists · Oto 2017 higher mortality · untreated epilepsy CHB-MIT Pediatric EEG Dataset · 24 patients · 916h 173 test seizures across 24 patients (Shoeb 2010) 72.63% 5-fold subject-wise sensitivity 126K EEG procedures / year · Europe 3s median onset latency · patient-specific mode 0.1 false alarms / 24h · CHB-MIT Up to 24 channels · 256Hz · bipolar montage 5s non-overlapping windows · event-driven 32 selected features per channel
— THE HARDWARE

Clinical scalp EEG, live-streamed.

Up to twenty-four electrodes positioned by the international 10–20 system. Bipolar montage at 256 Hz. Designed for ambulatory home use as well as in-clinic monitoring, with on-device buffering for connectivity loss and encrypted upload.

Brain neural activity visualization
CH · FP1-F7
CH · T8-P8
SAMPLING · 256 Hz

Up to 24-channel scalp EEG, 256 Hz

The NSAS reference device is a wireless, wearable headset designed for comfortable long-term wear at home and clinical-grade fidelity in the ward. Silver/silver-chloride electrodes, 10–20 international placement, paired bipolar montage. Compatible with existing clinical EEG hardware via standard data export. CHB-MIT validation uses the 22-channel bipolar standard.

ChannelsUp to 2410–20 system · bipolar
Sampling rate256Hz
Window5seconds · non-overlapping
Features92 → top 32per channel
Buffering24hoffline · auto-sync
OutputEDF · CSV · HL7 FHIRinterop
— THE AI ENGINE

Five steps, from raw signal to clinical event.

Every NSAS prediction is auditable. No black-box deep nets where we can't show the responsible features. Random Forest + post-processing, with full provenance from electrode to alert.

STEP · 01

Acquire

22-channel scalp EEG streams from clinical hardware at 256Hz. Bipolar montage, real-time.

STEP · 02

Window

The continuous signal is sliced into non-overlapping 5-second windows for downstream feature work.

STEP · 03

Extract

92 features computed per window — time, frequency, entropy, statistical. Top 32 selected per channel.

STEP · 04

Classify

Random Forest segment classifier. Auditable, feature-explainable — clinicians can trace any decision back to features.

STEP · 05

Event

Post-processing groups consecutive segments into seizure events. Smart escalation to clinician via NSAS Mobile.

— PERFORMANCE

Honest benchmarks, not optimistic ones.

Reported with all continuous EEG data (not curated subsets). Cross-subject splits — no patient leakage between train and test.

98.7%
Window classification accuracy
CHB-MIT · leave-one-out · cross-subject

Seizure event sensitivity — CHB-MIT

Sensitivity is the harder metric: did the system catch the actual seizure? We report it openly alongside accuracy, on continuous data, with no patient leakage.

NSAS · LOO cross-subjectleave-one-patient-out75.34%
NSAS · 5-fold subject-wisecross-subject splits72.63%
Shoeb & Guttag 2010patient-specific · 173 seizures96%
Typical curated-subset baselinebalanced data · optimistic92%
3sec
MEDIAN ONSET LATENCY · CHB-MIT
Patient-specific mode reaches sub-3-second detection from seizure onset on dataset evaluation.
0.1/24h
FALSE ALARM RATE · CHB-MIT
One false alert every ten days on dataset — within clinically deployable range, pending live validation.
916h
CONTINUOUS EEG TESTED
No hand-selected segments, no balanced-data tricks. Full continuous recordings from the public dataset.
— NSAS MOBILE

The neurologist's extra eyes, in the patient's pocket.

NSAS Mobile is built to stream the patient's home EEG, surface detected events in real time, and route alerts to the care team — without the bureaucratic dance of legacy patient portals. The app is ready; live patient streaming opens with the first clinical pilot.

Live monitoring

Continuous 22-channel feed with on-device buffering when the network drops.

Instant seizure alerts

Push notification within seconds of detection — patient, family, and clinician.

Auditable history

Replay any event with the surrounding EEG context. Export for the neurologist.

Clinician handoff

One-tap share with the care team via GDPR-compliant secure channels.

See the app in action
GOOD MORNING
Dr. Serkan
ALL CLEAR · LAST 24H
0 events
Monitoring continuously since 03:42
LIVE EEG · CH T8-P8● ONLINE
7-DAY EVENTS
2 ↓ 60%
SLEEP HOURS
7.4
Recent activity
Brief focal event
Tue · 02:14 · 11s
Sleep stage transition
Mon · 23:52
Medication reminder
Mon · 21:00
HOME
EEG
LOG
ME
— THE DATA

Validated on the most studied pediatric EEG dataset in the world.

CHB-MIT is a publicly available continuous scalp EEG dataset from Boston Children's Hospital, collected in collaboration with MIT. NSAS reports performance across the full continuous recordings — not curated subsets.

CHB-MIT Scalp EEG Database

Continuous multi-channel scalp EEG from 24 pediatric patients with intractable seizures. Recorded after withdrawal of anti-epileptic medication to characterize seizures and assess candidacy for surgical intervention. The de-facto benchmark for any serious seizure detection system.

24
Pediatric patients
916h
Continuous recording
173
Annotated seizures
METHODOLOGY · 01

Continuous data, not curated subsets

Many published baselines test on hand-picked records that contain seizures. NSAS reports on all data, including long stretches of non-seizure activity.

METHODOLOGY · 02

Cross-subject splits

No patient appears in both train and test. Leave-one-out and 5-fold subject-wise — preventing the data-leakage that inflates benchmark numbers.

METHODOLOGY · 03

Event detection, not random segments

Output is seizure events, post-processed from segment classifications — the unit clinicians actually act on.

— THE SCIENCE

Built on peer-reviewed foundations.

R. SOC. OPEN SCI · 2024

Epileptic seizure detection using CHB-MIT: the overlooked perspectives

Cross-subject generalization, continuous-data evaluation, and event detection — the three things most prior CHB-MIT studies skip. NSAS' methodology builds directly on this framing: 92 features, top-32 selection, RF classification, event post-processing.

Read the paper →
ICML · 2010

Application of machine learning to epileptic seizure detection

The Shoeb & Guttag paper that defined the patient-specific seizure-detection benchmark. 96% sensitivity on 173 seizures, 3-second median delay, 2 false detections / 24h. The reference point for any new approach on CHB-MIT.

Read the paper →
PHYSIONET · CHB-MIT

CHB-MIT Scalp EEG Database

The dataset itself — Boston Children's Hospital + MIT collaboration. 24 pediatric patients, 916 hours, 173 annotated seizures. Open access for academic research.

View the dataset →
NSAS · TECHNICAL NOTE

92 features, 32 selected — feature engineering for ambulatory EEG

How we balance feature richness with deployment cost: time-domain, frequency-domain, entropy, and statistical features computed in 5-second windows, then ranked per-channel by mutual information.

Request the note →
SEIZURE · 2017

The misdiagnosis of epilepsy: appraising risks and managing uncertainty

Oto (Meritxell). The source for the misdiagnosis figures we cite on this site: even at tertiary epilepsy centres under specialist care, misdiagnosis rates over 20% have been reported. The clinical motivation for everything NSAS does.

Read the paper →
SEIZURE · 2023

Estimates of epilepsy prevalence, psychiatric co-morbidity and cost

Christensen et al. The source for the per-patient cost figures on this site (~€15,240/year in Finland, ~€10,650/year in high-income countries). What the system spends today on a problem we believe is partially addressable.

Read the paper →
— WHERE WE ARE

Built. Validated. Awaiting clinical opening.

Honest status, in one section. We have shipped the parts we control — model, app, hardware — and we are in the ethics-review queue at the four hospitals that will host our first live pilots.

PHASE · 01
✓ Done

Research & algorithm

CHB-MIT validation. 92 features, top 32 selected. Random Forest. Cross-subject splits.

PHASE · 02
✓ Done

Mobile app

Expo + React Native. Patient and clinician flows. Push alerts, event replay, GDPR exports.

PHASE · 03
✓ Done

Hardware reference

22-channel scalp EEG, 256 Hz, bipolar montage. Compatible with standard clinical EEG interfaces.

PHASE · 04
⊙ In review

Ethics review · 4 sites

Submissions open at 2 hospitals in Turkey, 1 in Helsinki, and 1 in the United States. Partners published on consent.

For investors

Open to mission-aligned investor conversations.

NSAS sits at the bridge between a dataset-validated algorithm and a CE-marked clinical product. Capital deployed at this stage funds the clinical-pilot operations at the four hospitals under ethics review, the regulatory submission package, and the small team that will deliver both.

We are deliberate about who we work with. If a healthcare-adjacent fund or strategic with neurology-domain depth resonates, we want to hear from you.

View the investor brief
— PARTNER WITH US

Schedule a pre-clinical demo for your team.

A 30-minute walkthrough with a neurologist, an engineer, and a regulatory lead. We bring the platform; you bring the questions. No patient EEG required to evaluate the workflow.