A remote speech-based AI system to screen for early Alzheimer's disease via smartphones

Emil Fristed; Caroline Skirrow; Marton Meszaros; Raphael Lenain; Udeepa Meepegama; Stefano Cappa; Dag Aarsland; Jack Weston

doi:10.1002/dad2.12366

A remote speech-based AI system to screen for early Alzheimer's disease via smartphones

Alzheimers Dement (Amst). 2022 Nov 3;14(1):e12366. doi: 10.1002/dad2.12366. eCollection 2022.

Authors

Emil Fristed¹, Caroline Skirrow¹, Marton Meszaros¹, Raphael Lenain¹, Udeepa Meepegama¹, Stefano Cappa^{2

3}, Dag Aarsland^{4

5}, Jack Weston¹

Affiliations

¹ Novoic Ltd London UK.
² IUSS Cognitive Neuroscience (ICoN) Center University School for Advanced Studies Pavia Italy.
³ IRCCS Mondino Foundation Pavia Italy.
⁴ Department of Old Age Psychiatry Institute of Psychiatry Psychology & Neuroscience King's College London London UK.
⁵ Centre for Age-Related Diseases Stavanger University Hospital Stavanger Norway.

Abstract

Introduction: Artificial intelligence (AI) systems leveraging speech and language changes could support timely detection of Alzheimer's disease (AD).

Methods: The AMYPRED study (NCT04828122) recruited 133 subjects with an established amyloid beta (Aβ) biomarker (66 Aβ+, 67 Aβ-) and clinical status (71 cognitively unimpaired [CU], 62 mild cognitive impairment [MCI] or mild AD). Daily story recall tasks were administered via smartphones and analyzed with an AI system to predict MCI/mild AD and Aβ positivity.

Results: Eighty-six percent of participants (115/133) completed remote assessments. The AI system predicted MCI/mild AD (area under the curve [AUC] = 0.85, ±0.07) but not Aβ (AUC = 0.62 ±0.11) in the full sample, and predicted Aβ in clinical subsamples (MCI/mild AD: AUC = 0.78 ±0.14; CU: AUC = 0.74 ±0.13) on short story variants (immediate recall). Long stories and delayed retellings delivered broadly similar results.

Discussion: Speech-based testing offers simple and accessible screening for early-stage AD.

Keywords: Alzheimer's disease; artificial intelligence; clinical assessment; clinical screening; deep learning; diagnostics; digital health; episodic memory; language; machine learning; mild cognitive impairment; remote; speech.