When neuroscience meets machine learning: a taxonomic scoping review of machine and statistical learning approaches in sub-Saharan Africa
Résumé
In high-resource economies, computational neuroscience research frequently employs machine learning (ML) and statistical learning (SL) techniques. While these methods provide effective ways to analyse multimodal, high-dimensional, and complex data they are underexplored in low resource settings. This taxonomic scoping review uses a systematic methodological approach to synthesise the application of ML and SL techniques in neuroscience research in sub-Saharan Africa. In addition to discussing findings, strengths, limitations, and future prospects, the work classifies current research by neuroscience domains, applications, learning tasks, datasets, tools, and techniques. In order for African researchers to contribute to and benefit from the global computational neuroscience landscape, our review contends that low- and middle-income countries must create and augment context-specific and representative datasets and incorporate appropriate features for model training. Future studies should focus on pragmatic rather than complex modelling, external validation, reproducibility, interpretability, and utilise real-world data to determine clinical utility.
Citer ce document
Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)
Accès au document
Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter
Voir l'article sur le site de la revueLicence et provenance
Licence : CC BY
Notice moissonnée depuis OpenAlex le 16/11/2026. Le document reste hébergé par sa source.
Voir le document à la source →