Artificial intelligence (AI)-powered diagnostic support for stroke via Telegram bot: preliminary findings.

Overview

1. University College Hospital, Ibadan, Nigeria

Abstract

Background: Annually, stroke affects over 15 million people globally. Early intervention is critical in the management of stroke. However, the “golden hour” opportunity for timely intervention is often missed in underserved regions where experts in neuroimaging are scarce, with some countries having 1 per million inhabitants in comparison to high-income countries with 10 per million inhabitants. This study explores the feasibility of a lightweight AI-powered diagnostic support system for stroke deployed via a widely accessible platform (Telegram) to help clinicians in underserved settings.

Methods: This study utilized a comparative analysis of two transfer learning models (EfficientNetB0 and MobileNetV2) which were employed for training, using 6,650 publicly available, anonymized but radiologist annotated brain CT images from three classes: normal (n = 4,427), hemorrhagic stroke (n = 1,093), and ischemic stroke (n = 1,130). An 80/20 split was executed at slice-level as a result of lack of patient identifiers which this study acknowledges as a limitation. A separately sourced Kaggle dataset with labels but no metadata on annotator provenance was used for quasi-external validation with further evaluation using standard performance metrics. The selected model was integrated into a Telegram bot (@BrainfloBot) with real-time inference capabilities, and automatic data deletion to ensure privacy compliance.

Results: EfficientNetB0 demonstrated superior performance over MobileNetV2, achieving 99% accuracy (95% Cl: 98.2–99.5%) with excellent inter-rater reliability (κ = 0.985) during training and internal validation with precision and recall values exceeding 96% across all classes. While quasi-external validation using the balanced set, the selected model achieved a robust performance with 95% accuracy level (95% CI: 90.3%-97.9%, n = 150) with excellent agreement (κ = 0.925). For the unbalanced set, 97% accuracy level (95% Cl: 95.77%-98.03%) with excellent agreement(κ = 0.948) The model showed particularly strong performance in hemorrhagic stroke detection (98% precision, 96% recall), critical for preventing inappropriate thrombolytic therapy.

Conclusions: These preliminary findings demonstrates a successful integration of a novel AI-powered stroke diagnostics with a widely accessible messaging platform. This system can potentially close neuroimaging gaps in underserved regions where neuroimaging specialists are scarce. However, the study limitations include lack of patient-level separation, annotation provenance for external validation dataset, possible selection bias and lack of real world testing. Future work can integrate real world validation, out of distribution handling and robust testing with clinical images.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• kaggle.com/datasets/mouhsinenaghach, at Kaggle; found in “Data availability”
• kaggle.com/datasets/ozguraslank, at Kaggle; found in “Data availability”

Data availability

The dataset used for model training and internal validation—comprised of 6,650 CT images spanning normal, hemorrhagic, and ischemic classes—was obtained from the Kaggle repository by ozguraslank at https://www.kaggle.com/datasets/ozguraslank/brain-stroke-ct-dataset.

The independent dataset used for external validation (balanced and unbalanced brain CT sets) was also obtained from Kaggle, via https://www.kaggle.com/datasets/mouhsinenaghach/brainstrocksplit.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 1 author, 6 keywords, 6 MeSH terms, 7 references.

Cite

This paper

Ogunmiloro, B. (2026). Artificial intelligence (AI)-powered diagnostic support for stroke via Telegram bot: preliminary findings. BMC neurology, 26(1), 549. https://doi.org/10.1186/s12883-026-05065-3

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/diagnostics16172861 [code]

Microstructural Changes in the Corpus Callosum in Different Forms of Sporadic Age-Related Cerebral Small Vessel Disease.

Journal: Diagnostics (Basel, Switzerland)

In common: stroke, clinical / translational

[2] doi:10.3389/fneur.2026.1849021

Early pharmacologic venous thromboembolism prophylaxis and in-hospital mortality in ICU patients with intracerebral hemorrhage: a landmark, propensity-weighted cohort study.

Journal: Frontiers in neurology

In common: stroke, clinical / translational

[3] doi:10.1002/alz.71811

Female vulnerability to microvascular transport dysfunction emerges early across the Alzheimer's disease continuum.

Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association

In common: stroke, clinical / translational

[4] doi:10.1002/alz.71822 [code]

SynthPET: A 3D generative AI approach for FDG-PET image synthesis from T1-weighted MRI and ASL CBF in Alzheimer's disease.

Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association

In common: stroke, clinical / translational

[5] doi:10.1212/wnl.0000000000218472 [code]

Lesion-Level Subtypes of White Matter Hyperintensity Evolution Beyond Spatial Location.

Journal: Neurology

In common: stroke, clinical / translational

[6] doi:10.3390/brainsci16080882 [code]

How Long Is the Brain Perfusable After Global Ischemia? A Systematic Review.

Journal: Brain sciences

In common: stroke, clinical / translational

[7] doi:10.3390/biomedicines14081829

Transvenous Embolisation-Based Strategies for Brain Arteriovenous Malformations: Systematic Review and Meta-Analysis.

Journal: Biomedicines

In common: stroke, clinical / translational

[8] doi:10.1093/braincomms/fcag309 [code]

Neurovascular effects of tadalafil in patients with cerebral small vessel disease: ETLAS-2 substudy.

Journal: Brain communications

In common: stroke, clinical / translational

[9] doi:10.1016/j.eclinm.2026.104143 [code]

Intensive versus standard blood pressure control and overall brain small vessel disease burden: a post-hoc analysis of the SPRINT randomized clinical trial.

Journal: EClinicalMedicine

In common: stroke, clinical / translational

[10] doi:10.3389/fneur.2026.1879894

Perivascular diffusion and white matter free water improve identification of cognitive impairment in cerebral small vessel disease.

Journal: Frontiers in neurology

In common: stroke, clinical / translational

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.