An observational study in Dementia (Diagnosis), Alzheimer Dementia (AD) and Vascular Dementia (VaD), sponsored by Zealand University Hospital. Not yet recruiting at 1 site in Denmark. Open to participants aged 50 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-09-02.
Sponsored by Zealand University Hospital · Observational
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.
Participants are recruited from patients who are followed at- or referred to the memory clinic at Zealand University Hospital. Age and gender matched healthy controls for model A are recruited from the participants' relatives.
Model A (patient participants)
Model A (cognitively healthy controls)
Model B:
Exclusion Criteria:
Model A:
Patients:
Cognitively healthy controls:
Model B:
We seek to enroll 40 age-matched cognitively healthy control participants for the training of model A.
Diagnostic Test: Mini-mental State Examination · Diagnostic Test: Addenbrooke's Cognitive Examination · Other: Speech Task - Picture Description · Other: Speech Task - Picture Recall · Diagnostic Test: MRI · Diagnostic Test: blood sampling · Diagnostic Test: Depression screening · Other: Somatic- and neurological examination · Other: Speech Task - Picture Narrative
We seek to retrospectively enroll patients from the ZUH memory clinic with a diagnosis of either Alzheimer's Disease (AD, n=50) or MCI (n=50), made within 6 months prior to enrollment. These participants will be used for the training of model A.
Diagnostic Test: Mini-mental State Examination · Diagnostic Test: Addenbrooke's Cognitive Examination · Other: Speech Task - Picture Description · Other: Speech Task - Picture Recall · Other: Speech Task - Picture Narrative
We will prospectively recruit newly referred patients for the memory clinic at ZUH. Enrollment happens at first patient visit. At this time, diagnosis is not yet known, but assumed present.
Diagnostic Test: Mini-mental State Examination · Diagnostic Test: Addenbrooke's Cognitive Examination · Other: Speech Task - Picture Description · Other: Speech Task - Picture Recall · Other: Speech Task - Picture Narrative
Participants will be recorded during the test in order til allow the AI to learn and analyze speech patterns.
Also known as: MMSE
Participants will be recorded during the test in order til allow the AI to learn and analyze speech patterns.
Also known as: ACE
Participants will be asked to describe the Cookie Theft Picture from the Boston Diagnostic Aphasia Examination. The task will take 2 minutes. Participants will be recorded during the speech task in order to allow the AI to learn and analyze the speech patterns.
Participants will be asked to recall the picture shown in the previous speech task "Picture Narrative". This task will take 2 minutes. Participants will be recorded during the test in order til allow the AI to learn and analyze speech patterns.
For healthy controls an MRI will be conducted to provide comparable imaging and as part of screening to ensure they do not meet exclusion criteria (neuroradiological findings that could affect cognitive functions). For patient participants, imaging will be performed as part of the standard diagnostic battery and results will be obtained from the electronic journal.
Healthy control participants will undergo a standard blood test panel commonly used in dementia diagnostics. The panel includes complete blood counts, inflammatory markers, kidney- and liver function markers, thyroid-stimulating hormone (TSH), vitamine B12 and folate. These tests are performed to exclude underlying medical conditions that could mimic cognitive impairment. For patient participants, blood sampling will be performed as part of the standard diagnostic battery and results will be obtained from the electronic journal.
Performed on healthy controls to rule out depression using either the geriatric depression scale (GDS) for patients \> 65 year of age or the Major Depression Index (MDI) for patiens \<65 year of age. For patient participants, depression screening will be performed as part of the standard diagnostic battery and results will be obtained from the electronic journal.
Healthy controls will undergo a standard somatic and neurological examination to exclude conditions that may affect cognition. This includes basic neurological assessment and clinical evaluation of general health status. For patient participants, a somatic and neurological examination will be performed as part of the standard diagnostic battery and results will be obtained from the electronic journal
The participant is asked to tell a brief story based on a culturally neutral picture. This task will take approximately 2 minutes. Participants will be recorded during the speech task in order to allow the AI to learn and analyze the speech patterns
Model A: Primary measure is the AUC-ROC of the model in distinguishing between MCI and AD as well as between MCI and cognitively healthy control participants.
We will measure the AUR-ROC of AI predictions compared to clinical consensus diagnosis. Metrics will be presented including uncertainty estimates. Model performance will be measured on an independent test-set consisting of patients from the model B training population.
Time frame: At baseline (speech recording)
Accuracy for dementia vs. depression
Measured by sensitivity, specificity, AUR-ROC of AI predictions compared to clinical consensus diagnosis, using baseline speech recordings from participants. Model performance will be measured after database lock at study completion.
Time frame: At baseline (speech recording)
Sub-classification of Mild Cognitive Impairment (MCI) into progressive vs. non-progressive
Measured by sensitivity, specificity, AUR-ROC of AI predictions compared to clinical consensus diagnosis, using baseline speech recordings from participants. Model performance will be measured after database lock at study completion. Progression is defined as new dementia diagnosis during study period.
Time frame: At baseline (speech recording) and up to 12 months after enrollment (to determine progression)
Classification of dementia subtypes (AD, VaD, LBD, FTD)
Measured by sensitivity, specificity, AUR-ROC of AI predictions compared to clinical consensus diagnosis, using baseline speech recordings from participants. Model performance will be measured after database lock at study completion.
Time frame: At baseline (speech recording)
Comparison with established biomarkers
Differences in diagnostic accuracy between AI predictions and state-of-the-art biomarkers for dementia diagnosis
Time frame: At baseline, or at time of biomarker testing if performed after baseline
Feature importance analysis
Feature importance will be evaluated using interpretability analyses (e.g. permutation importance, SHAP values, and/or ablation of feature groups) to quantify the contribution of acoustic and linguistic features to the model's predictions.
Time frame: At baseline (speech recording)
Contribution of individual speech tasks to AI model performance
Contribution of individual speech tasks will be evaluated by comparing model performance (e.g. accuracy, sensitivity, specificity, AUC-ROC) when trained and tested on subsets of speech tasks (memory tests, story recall, picture description). This will identify which tasks provide the strongest diagnostic signal.
Time frame: At baseline (speech recording)
Number of tasks required for optimal accuracy
Evaluation of whether a reduced set of speech tasks provide accuracy comparable to the full test battery.
Time frame: At baseline (speech recording)
Plan to share: No
This study is not yet recruiting, as verified in Jan 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Zealand University Hospital