![[2602.13047] Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.13047] Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech
Summary
This study investigates the reliability of AI in detecting cognitive impairment among multilingual English speakers in the UK, revealing significant biases against certain ethnic groups.
Why It Matters
As dementia prevalence rises among ethnic minorities in the UK, understanding AI's biases in diagnosing cognitive impairments is crucial. This research highlights the need for more equitable AI tools to ensure accurate diagnoses across diverse populations.
Key Takeaways
- AI models show bias against multilingual speakers, particularly in cognitive assessments.
- Misclassification of multilingual individuals as cognitively impaired is a significant concern.
- Current AI tools are not reliable for diagnostic use in diverse populations.
- The study emphasizes the importance of developing bias-mitigated AI models.
- Findings highlight the urgency of addressing AI bias in healthcare applications.
Computer Science > Computation and Language arXiv:2602.13047 (cs) [Submitted on 13 Feb 2026] Title:Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech Authors:Madhurananda Pahar, Caitlin Illingworth, Dorota Braun, Bahman Mirheidari, Lise Sproson, Daniel Blackburn, Heidi Christensen View a PDF of the paper titled Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech, by Madhurananda Pahar and 6 other authors View PDF HTML (experimental) Abstract:Conversational speech often reveals early signs of cognitive decline, such as dementia and MCI. In the UK, one in four people belongs to an ethnic minority, and dementia prevalence is expected to rise most rapidly among Black and Asian communities. This study examines the trustworthiness of AI models, specifically the presence of bias, in detecting healthy multilingual English speakers among the cognitively impaired cohort, to make these tools clinically beneficial. For experiments, monolingual participants were recruited nationally (UK), and multilingual speakers were enrolled from four community centres in Sheffield and Bradford. In addition to a non-native English accent, multilinguals spoke Somali, Chinese, or South Asian languages, who were further divided into two Yorkshire accents (West and South) ...