Speech-Based Artificial Intelligence for Detection of Dementia in Danish Patients (DetectAI)

Overview

The goal of this observational study is to learn if an artificial intelligence (AI)-based speech analysis tool can identify which patients with memory problems need specialist evaluation at a memory clinic. The main questions it aims to answer are: Can the AI model accurately distinguish between patients who need referral to a memory clinic (those with dementia or Mild Cognitive Impairment) and patients who don't (those with normal cognition or memory problems from other causes like depression)? Which speech patterns and cognitive test features are most useful for making this distinction? Researchers will compare speech recordings and cognitive test results from patients diagnosed with dementia or MCI to those from patients with normal cognition or non-neurodegenerative cognitive impairment to see if the AI model can reliably predict who needs specialist dementia care. Participants will: Complete standard cognitive tests at the memory clinic Perform structured speech tasks while being audio-recorded Receive their usual clinical evaluation and diagnosis from memory clinic specialists The results of this study will help develop a tool that can assist doctors in making faster, more accurate decisions about which patients need specialist dementia evaluation, potentially leading to earlier diagnosis and better patient outcomes.

Background Dementia is a growing public health challenge, and early and accurate diagnosis is essential for effective care and potential future disease-modifying treatments. Current diagnostic pathways are resource-intensive and associated with long waiting times. Speech reflects cognitive functioning, and recent international studies have shown that machine learning models can detect dementia-related patterns in speech recordings with promising accuracy. This study aims to develop a speech-based deep learning model in a Danish setting, providing a non-invasive and scalable screening tool for use in primary care. Study Design and Sampling Methods This is an observational, cross-sectional study. Participants are recruited using two different sampling strategies corresponding to two artificial intelligence (AI) model development tracks: Track A (Model A) - Retrospective case-control sampling: This track addresses a focused diagnostic task: identification of Mild Cognitive Impairment (MCI). Participants are patients with a recent diagnosis from the memory clinic at Region Zealand University Hospital (ZUH). Sampling uses convenience sampling prioritizing patients who live close to the hospital, as data collection occurs during home visits. Patients with more recent diagnoses are prioritized to minimize the risk that participants have progressed to a new disease stage since diagnosis (e.g., from MCI to dementia). Track B (Model B) - Prospective consecutive sampling: This track uses prospective inclusion of newly referred patients to the memory clinic without pre-selection by diagnosis, reflecting a real-world clinical screening population. All eligible, consenting patients are included consecutively at their first clinic visit, before final diagnosis is established. Model Development Following Best Practice Guidelines The study follows TRIPOD-AI (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis - Artificial Intelligence) and PROBAST-AI (Prediction model Risk Of Bias ASsessment Tool - Artificial Intelligence) guidelines for developing and validating clinical prediction models. Key methodological features include: Transparent model development: All preprocessing steps, feature extraction methods, model architectures, and hyperparameters will be documented Robust validation strategy: Data will be split into training, validation, and hold-out test sets for in-depth internal validation. Minimizing bias: Participant selection, predictor measurement, outcome determination, and statistical analysis are designed to minimize bias according to PROBAST-AI domains Clinically relevant performance metrics: Sensitivity, specificity, area under the receiver operating characteristic curve (AUC-ROC), positive and negative predictive values, and calibration Interpretability: Feature importance analysis to understand which speech characteristics contribute to predictions Data Collection Speech data is collected through structured tasks including picture description, verbal fluency tests, story recall, and spontaneous speech. Audio is recorded using standardized equipment with quality control checks. Clinical diagnoses are established by experienced clinicians at the memory clinic following international diagnostic criteria.