Automated Phone Speech Test Identifies Alzheimer’s Pathology for Prescreening

Providers and trial sponsors need remote tools that can help triage candidates and monitor cognition without requiring in-person visits. A new automated, phone-based speech biomarker now offers a scalable approach for detecting cognitive impairment and signals of underlying Alzheimer’s pathology across multiple languages.

ki:elements’ (Saarbrücken, Germany) Speech Biomarker for Cognition (SB-C) was evaluated in peer-reviewed research conducted with the PROSPECT-AD consortium. The assessment is delivered via the Mili platform, which places a phone call to participants at home and administers a 10-minute task through an AI voice agent. The study enrolled 736 participants across five independent cohorts in Spain, the UK, Germany, and Sweden.

SB-C analyzes 70 distinct speech features to index cognitive efficiency and generate an automatic biomarker score. The approach distinguished cognitively unimpaired individuals from those with mild cognitive impairment (MCI) or early dementia and classified cerebrospinal fluid biomarker status remotely. Performance included identification of amyloid-beta positivity with an AUC of up to 0.74 and phosphorylated tau 181 positivity with an AUC of up to 0.82.

The tool showed multilingual sensitivity across Spanish, Catalan, German, English, and Swedish. It demonstrated strong convergent validity with established measures such as MMSE and PACC-5 and is validated following the Digital Medicine Society’s V3 Framework. It is currently deployed as a pre-screening tool in multiple Alzheimer’s disease clinical trials to enrich for biomarker‑positive participants prior to invasive testing.

“This study gives us real-world, multi-site evidence that a speech assessment can track with established cognitive measures and distinguish patients by their underlying pathology. For sponsors, this translates directly into faster, smarter recruitment, and a lower-burden tool for participants,” said Dr. Alexandra König, Chief Clinical Research Officer of ki:elements and corresponding author of the study.

Related Links
ki:elements