pith. sign in

arxiv: 2605.08157 · v2 · pith:SC5KCVJ4new · submitted 2026-05-04 · 📡 eess.SP · cs.CY

Clinical Utility and Feasibility of Smartphone-based EEG in Kenya: A Multicenter Observational Study

Nomin Enkhtsetseg , William Lehn-Schi{\o}ler , Anton Mosquera Storgaard , Magnus Guldberg Pedersen , Dylan Rice , George Wambugu , Nshimiyimana Jules Fidele , Melita Cacic Hribljan
show 4 more authors
Anca Alina Arbune Sidsel Armand Larsen Sandor Beniczky Farrah J. Mateen
This is my paper

Pith reviewed 2026-05-21 00:46 UTC · model grok-4.3

classification 📡 eess.SP cs.CY
keywords smartphone EEGfeasibility studyKenyaresource-limited settingsepilepsy diagnosispoint-of-care EEGnon-specialist operatorsLMICs
0
0 comments X

The pith

Non-specialist operators in Kenya can acquire large-scale, interpretable EEG data using a smartphone-based system.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This multicenter study tested a smartphone EEG device across 29 sites in Kenya to see if it could work in everyday clinical practice. Trained healthcare workers performed 3,036 recordings, and remote experts could interpret 96 percent of them. The system proved practical for common issues like seizures, with quick turnaround times for results. If this holds, it offers a way to bring brain wave testing to places without traditional EEG machines or specialists.

Core claim

The authors report that large-scale, point-of-care EEG acquisition by non-specialist operators in a resource-limited setting is feasible, as shown by 96% of 3,036 smartphone-based recordings being interpretable with a mean interpretation turnaround of 107 minutes.

What carries the argument

Smartphone-based 27-lead EEG system that allows trained healthcare workers to acquire standardized recordings for remote expert interpretation.

If this is right

  • High interpretability rates support use for diagnosing epilepsy and other neurological conditions.
  • Shorter recording times were linked to uninterpretable results, suggesting minimum duration guidelines.
  • Abnormal findings were common, especially epileptiform activity in children.
  • Mean turnaround time of 107 minutes enables timely clinical decisions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This approach could help close the diagnostic gap for epilepsy in sub-Saharan Africa by enabling more tests without building new hospitals.
  • Further studies comparing smartphone EEG directly to standard systems would strengthen confidence in the findings.
  • Scaling this could support broader neurological care in other low-resource countries.

Load-bearing premise

The smartphone-based recordings produce data of sufficient quality for reliable clinical interpretation by remote experts.

What would settle it

A head-to-head study where standard hospital EEG and smartphone EEG are performed on the same patients and the smartphone version misses clinically relevant abnormalities would challenge the claim.

read the original abstract

Purpose: Access to electroencephalography (EEG) remains limited across low- and middle-income countries (LMICs) due to cost, infrastructure requirements, and a shortage of trained staff. This study evaluated the feasibility and clinical utility of a smartphone-based EEG system in a real-world setting. Methods: We conducted a multicenter observational study (November 2023 to April 2026) across 29 clinical sites in Kenya. A smartphone-based 27-lead EEG system enabled trained healthcare workers to acquire standardized recordings with remote expert interpretation. Results: 3,036 EEG sessions were performed. Male patients constituted 57.8% of the cohort, with representation across pediatric and adult populations. The most common referral indication was seizures or convulsions (68.5%). Overall, 2,915 (96%) recordings were interpretable, while 121 (4%) were uninterpretable, primarily due to high electrode impedance and insufficient recording duration. Uninterpretable recordings were significantly shorter than interpretable recordings (mean 18.5 vs. 33.8 minutes; median 15.1 vs. 31.6 minutes; p < 0.0001). Mean turnaround time for interpretation was 107 minutes. Among interpretable recordings, 917 (30.2%) were abnormal, including 701 (76.4%) with epileptiform abnormalities, 215 (23.4%) with non-epileptiform findings, and 1 (0.1%) indeterminate finding. Epileptiform abnormalities were highest in children aged 4-9 years (33.1%) and less frequent in adults (14-21%). Non-epileptiform abnormalities were more common in patients aged 60+ years (19.2%) compared to younger age groups (3-9%). Conclusion: Large-scale, point-of-care EEG acquisition by non-specialist operators in a resource-limited setting is feasible. Expansion of smartphone-based EEG systems may improve equitable access to neurological diagnosis and care in LMICs.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript reports results from a multicenter observational study across 29 sites in Kenya (November 2023–April 2026) that deployed a smartphone-based 27-lead EEG system operated by trained non-specialist healthcare workers, with remote expert interpretation. Key findings from 3,036 recordings include a 96% interpretability rate, significantly shorter durations for the 4% uninterpretable cases (mean 18.5 vs. 33.8 min, p<0.0001), a mean interpretation turnaround of 107 minutes, and 30.2% abnormal recordings (76.4% of which showed epileptiform activity, highest in children aged 4–9 years).

Significance. If the results hold, the work provides large-scale empirical evidence that point-of-care EEG acquisition is feasible in resource-limited LMIC settings without specialist operators on site. Notable strengths include the multicenter design, high recording volume, and direct statistical support for technical factors affecting success; these elements strengthen the feasibility demonstration and its potential relevance for expanding neurological diagnostics.

minor comments (3)
  1. [Results] Results section: sample sizes underlying the age-stratified abnormality percentages (e.g., 33.1% epileptiform in 4–9 years) are not reported, which limits assessment of precision and statistical power for those subgroup claims.
  2. [Methods] Methods: the operational criteria used by remote experts to classify a recording as 'interpretable' versus 'uninterpretable' are described only at the level of failure reasons (impedance, duration); an explicit checklist or threshold would improve reproducibility.
  3. [Discussion] The manuscript would benefit from a brief statement in the Discussion on how the observed abnormality rates compare with published conventional EEG cohorts in similar populations, even if only as context.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive and accurate summary of our multicenter observational study on smartphone-based EEG in Kenya, as well as the recommendation for minor revision. The significance assessment correctly highlights the value of the large-scale data, multicenter design, and statistical support for technical factors. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity; purely empirical observational study

full rationale

The paper reports a multicenter observational study collecting 3,036 smartphone-based EEG recordings across Kenyan sites, with direct empirical metrics (96% interpretability rate, statistical comparisons of duration and impedance, turnaround times, and abnormality rates by age). No equations, derivations, predictive models, fitted parameters, or self-referential claims exist. All conclusions rest on observed data and remote expert interpretation as the quality proxy, without any reduction of results to inputs by construction or load-bearing self-citations. This is a standard non-circular empirical feasibility report.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests primarily on empirical deployment data rather than new theoretical constructs; the main supporting elements are standard clinical assumptions about EEG interpretation.

axioms (1)
  • domain assumption Standard clinical EEG interpretation criteria remain valid when applied to recordings from the smartphone-based system.
    Invoked when reporting abnormality rates and interpretability based on remote expert review without additional validation steps described.

pith-pipeline@v0.9.0 · 5982 in / 1271 out tokens · 65717 ms · 2026-05-21T00:46:53.837349+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

    cs.LG 2026-05 unverdicted novelty 6.0

    Sparse autoencoders on EEG transformers identify three regimes of clinical concept encoding and reveal entanglements such as age-pathology confounding via a new steering selectivity metric.

  2. Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

    cs.LG 2026-05 unverdicted novelty 6.0

    TopK SAEs applied to EEG transformers extract clinical features, enable concept steering, and identify selectively steerable, entangled, and non-encoded regimes with a spectral decoder for physiological interpretation.

  3. Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

    cs.LG 2026-05 unverdicted novelty 6.0

    Sparse autoencoders on EEG transformers extract clinical features, identify three steering regimes, expose age-pathology entanglements and wrecking-ball failures, and map interventions to frequency spectra.

Reference graph

Works this paper leans on

22 extracted references · 22 canonical work pages · cited by 1 Pith paper

  1. [1]

    Intersectoral Global Action Plan on Epilepsy and Other Neurological Disorders 2022–2031

    World Health Organization. Intersectoral Global Action Plan on Epilepsy and Other Neurological Disorders 2022–2031. Geneva: WHO; 2022

    work page 2022

  2. [2]

    The Epidemiology of Global Epilepsy

    Singh A, Trevick S. The Epidemiology of Global Epilepsy. Neurol Clin . 2016;34(4):837-847. doi:10.1016/j.ncl.2016.06.015

    work page doi:10.1016/j.ncl.2016.06.015 2016

  3. [3]

    EEG coverage in Africa: How can the gap be covered? Epilepsy Research

    Naji Y, Kissani N, Saylor D, et al. EEG coverage in Africa: How can the gap be covered? Epilepsy Research. 2026;223:107784. doi:10.1016/j.eplepsyres.2026.107784

    work page doi:10.1016/j.eplepsyres.2026.107784 2026

  4. [4]

    Premature mortality of epilepsy in low- and middle-income countries: A systematic review from the Mortality Task Force of the International League Against Epilepsy

    Levira F, Thurman DJ, Sander JW, et al. Premature mortality of epilepsy in low- and middle-income countries: A systematic review from the Mortality Task Force of the International League Against Epilepsy. Epilepsia . 2017;58(1):6-16. doi:10.1111/epi.13603

    work page doi:10.1111/epi.13603 2017

  5. [5]

    Global disparities in the epilepsy treatment gap: a systematic review

    Meyer AC, Dua T, Ma J, Saxena S, Birbeck G. Global disparities in the epilepsy treatment gap: a systematic review. Bull World Health Organ . 2010;88(4):260-266. doi:10.2471/BLT.09.064147

    work page doi:10.2471/blt.09.064147 2010

  6. [6]

    Nicholas A. (2023). Unlocking the hidden burden of epilepsy in Africa: Understanding the challenges and harnessing opportunities for improved care. Health science reports , 6(4), e1220. https://doi.org/10.1002/hsr2.1220

    work page doi:10.1002/hsr2.1220 2023

  7. [7]

    FY26 Updated Country Income Classification for Analytical Purposes (English)

    World Bank. FY26 Updated Country Income Classification for Analytical Purposes (English). Washington (DC): World Bank Group; 2026 http://documents.worldbank.org/curated/en/099062525111074500 [accessed 29 April 2026]. [10] Ibinda F, Wagner RG, Bertram MY, et al. Burden of epilepsy in rural Kenya measured in disability-adjusted life years. Epilepsia . 2014;...

    work page doi:10.1111/epi.12741 2026

  8. [8]

    Estimation of the burden of active and life-time epilepsy: a meta-analytic approach

    Ngugi AK, Bottomley C, Kleinschmidt I, Sander JW, Newton CR. Estimation of the burden of active and life-time epilepsy: a meta-analytic approach. Epilepsia . 2010;51(5):883-890. doi:10.1111/j.1528-1167.2009.02481.x

    work page doi:10.1111/j.1528-1167.2009.02481.x 2010

  9. [9]

    Prevalence of all epilepsies in urban informal settlements in Nairobi, Kenya: a two-stage population-based study

    Mwanga DM, et al. Prevalence of all epilepsies in urban informal settlements in Nairobi, Kenya: a two-stage population-based study. Lancet Glob Health . 2024;12(8):e1323-e1330. doi:10.1016/S2214-109X(24)00217-1

    work page doi:10.1016/s2214-109x(24)00217-1 2024

  10. [10]

    Epilepsy diagnosis and management of children in Kenya: review of current literature

    Samia P, Hassell J, Hudson JA, et al. Epilepsy diagnosis and management of children in Kenya: review of current literature. Res Rep Trop Med . 2019;10:91-102. Published 2019 Jun 28. doi:10.2147/RRTM.S201159

    work page doi:10.2147/rrtm.s201159 2019

  11. [11]

    Does Hyperventilation Elicit Epileptic Seizures?

    Carter JA, Neville BG, White S, et al. Increased prevalence of epilepsy associated with severe falciparum malaria in children. Epilepsia . 2004;45(8):978-981. doi:10.1111/j.0013-9580.2004.65103.x

    work page doi:10.1111/j.0013-9580.2004.65103.x 2004

  12. [12]

    Diagnostic and treatment gaps

    Birmeh C, Urio OH, Wilmshurst JM. Diagnostic and treatment gaps. Semin Pediatr Neurol . 2025;55:101200. doi:10.1016/j.spen.2025.101200

    work page doi:10.1016/j.spen.2025.101200 2025

  13. [13]

    Treatment gaps in epilepsy

    Pellinen J. Treatment gaps in epilepsy. Front Epidemiol . 2022;2:976039. doi:10.3389/fepid.2022.976039

    work page doi:10.3389/fepid.2022.976039 2022

  14. [14]

    Smartphone EEG and remote online interpretation for children with epilepsy in the Republic of Guinea: Quality, characteristics, and practice implications

    Williams JA, Cisse FA, Schaekermann M, et al. Smartphone EEG and remote online interpretation for children with epilepsy in the Republic of Guinea: Quality, characteristics, and practice implications. Seizure . 2019;71:93-99. doi:10.1016/j.seizure.2019.05.025

    work page doi:10.1016/j.seizure.2019.05.025 2019

  15. [15]

    Validation of a smartphone-based EEG among people with epilepsy: A prospective study

    McKenzie ED, Lim AS, Leung EC, et al. Validation of a smartphone-based EEG among people with epilepsy: A prospective study. Sci Rep . 2017;7:45567. doi:10.1038/srep45567

    work page doi:10.1038/srep45567 2017

  16. [16]

    The Acceptability, Feasibility, and Utility of Portable Electroencephalography to Study Resting-State Neurophysiology in Rural Communities

    Bhavnani S, Parameshwaran D, Sharma KK, et al. The Acceptability, Feasibility, and Utility of Portable Electroencephalography to Study Resting-State Neurophysiology in Rural Communities. Front Hum Neurosci . 2022;16:802764. doi:10.3389/fnhum.2022.802764

    work page doi:10.3389/fnhum.2022.802764 2022

  17. [17]

    BC-1: A Revolution in EEG

    BrainCapture. BC-1: A Revolution in EEG. Available from: https://www.braincapture.dk/ [21] Beniczky S, Aurlien H, Brøgger JC, et al. Standardized computer-based organized reporting of EEG: SCORE - Second version. Clin Neurophysiol . 2017;128(11):2334-2346. doi:10.1016/j.clinph.2017.07.418

    work page doi:10.1016/j.clinph.2017.07.418 2017

  18. [18]

    Yield of epileptiform electroencephalogram abnormalities in incident unprovoked seizures: a population-based study

    Baldin E, Hauser WA, Buchhalter JR, Hesdorffer DC, Ottman R. Yield of epileptiform electroencephalogram abnormalities in incident unprovoked seizures: a population-based study. Epilepsia . 2014;55(9):1389-1398. doi:10.1111/epi.12720

    work page doi:10.1111/epi.12720 2014

  19. [19]

    Diagnostic Yield of Routine EEG in Adults with Active Epilepsy

    McGinty RN, Costello DJ, Kinirons P, McNamara B. Diagnostic Yield of Routine EEG in Adults with Active Epilepsy. Ir Med J. 2019;112(1):851. Published 2019 Jan 15

    work page 2019

  20. [20]

    O., Kidiga, Z

    Jowi, J. O., Kidiga, Z. P., & Gitau, M. G. (2008). A review of electroencephalograms done at the Kenyatta National Hospital, Nairobi. East African medical journal , 85(2), 92–97. https://doi.org/10.4314/eamj.v85i2.9612

    work page doi:10.4314/eamj.v85i2.9612 2008

  21. [21]

    The diagnostic yield of a first EEG in children with suspected epilepsy: A retrospective age-related comparison between awake and sleep recordings

    Gustafsson G, Broström A, Svanborg E, Vrethem M, Ulander M. The diagnostic yield of a first EEG in children with suspected epilepsy: A retrospective age-related comparison between awake and sleep recordings. Clin Neurophysiol Pract . 2025;10:181-187. doi:10.1016/j.cnp.2025.05.002

    work page doi:10.1016/j.cnp.2025.05.002 2025

  22. [22]

    Electroencephalogram

    Rayi A, Murr NI. Electroencephalogram. StatPearls. 2022. [27] Hasan TF, Tatum WO. When should we obtain a routine EEG while managing people with epilepsy?. Epilepsy Behav Rep . 2021;16:100454. doi:10.1016/j.ebr.2021.100454

    work page doi:10.1016/j.ebr.2021.100454 2022