Automated Language Analysis in Neurodegenerative Diseases: Application of Artificial Intelligence Models (AILAN)
Analisi Automatizzata Del Linguaggio Nelle Malattie Neurodegenerative: Applicazione di Modelli di Intelligenza Artificiale
This multicenter study aims to characterize the language profiles of patients with various neurodegenerative diseases, including Alzheimer's disease (AD), Primary Progressive Aphasia (PPA), behavioral variant Frontotemporal Dementia (bvFTD), Dementia with Lewy Bodies (DLB), and Parkinson's disease (PD), using artificial intelligence (AI) models. By analyzing speech and language data collected during remote neuropsychological assessments, the researchers intend to identify objective linguistic biomarkers suitable for early and differential diagnosis, overcoming the limitations of traditional, invasive, and costly diagnostic tools. The project will develop and validate an AI-driven pipeline to provide scalable and individualized linguistic profiles, ultimately supporting personalized treatment strategies and improving clinical workflow efficiency in the Italian population.
Study Overview
Status
Status
Conditions
Conditions
Intervention / Treatment
Intervention / Treatment
Detailed Description
Neurodegenerative disorders pose significant diagnostic challenges, particularly in differentiating conditions with overlapping clinical symptoms and neuroanatomy. Although language impairment is a hallmark symptom across several forms of dementia, existing diagnostic tools are often costly, time-consuming, and lack cultural sensitivity, particularly for the Italian language. Artificial Intelligence (AI) offers a promising, non-invasive approach to extracting objective acoustic, prosodic, and linguistic markers from speech data.
The primary objective of this study is to characterize the language profiles of patients diagnosed with AD, PPA, bvFTD, DLB, and PD compared to healthy controls (HC). Specific objectives include: 1) Identifying distinct linguistic and speech features that act as surrogate biomarkers for early and differential diagnosis; 2) Using machine learning to optimize classification algorithms; and 3) Implementing Explainable AI (XAI) to ensure the interpretability of diagnostic outputs, thereby facilitating clinical trust and adoption of AI-driven tools in the diagnostic process.
This is a prospective, experimental, multicenter study. A total of 168 participants (24 per group: AD, PPA, bvFTD, DLB, PD, and HC) will be enrolled. Participants will undergo a 1.5-hour remote neuropsychological and logopedic evaluation via a secure, HIPAA-compliant videoconferencing platform. The assessment includes spontaneous speech tasks (e.g., image descriptions) and standardized language and cognitive tests. Audio data will be recorded and processed using an AI pipeline, including automatic speech recognition for transcription and various Natural Language Processing (NLP) techniques-such as BERT, RoBERTa, and UmBERTo-to extract complex linguistic and semantic features.
Data analysis will involve training machine learning classifiers (e.g., Support Vector Machines, Random Forests) to distinguish between diagnostic groups, utilizing nested cross-validation to ensure robustness. XAI techniques, including SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations), will be applied to enhance the transparency of the model's decisions, allowing clinicians to interpret the pathological language patterns driving the classification. The study aims to establish the first structured Italian corpus for the linguistic characterization of neurodegenerative disorders, providing a foundation for future cross-linguistic analysis.
Study Type
Study Type
Enrollment (Estimated)
Enrollment
Phase
Phase
- Not Applicable
Contacts and Locations
Study Contact
Study Contact
- Name: Petronilla Battista, PhD
- Phone Number: +390807814331
- Email: petronilla.battista@icsmaugeri.it
Study Contact Backup
- Name: Gaia C Santi, PhD
- Email: gaia.santi@icsmaugeri.it
Study Locations
-
-
-
Bari, Italy, 70124
- Recruiting
- Istituti Clinici Scientifici Maugeri IRCCS Bari
-
Contact:
- Petronilla Battista, PhD
- Email: petronilla.battista@icsmaugeri.it
-
Contact:
- Simona Aresta
- Email: simona.aresta@icsmaugeri.it
-
Sub-Investigator:
- Gaia C Santi, PhD
-
-
Participation Criteria
Eligibility Criteria
Eligibility Criteria
Ages Eligible for Study
Accepts Healthy Volunteers
Genders Eligible for Study
Description
Participants with neurodegenerative diseases
Inclusion criteria
- Diagnosis of mild cognitive impairment due to Alzheimer's disease (AD), primary progressive aphasia (PPA), behavioral variant frontotemporal dementia (bvFTD), dementia with Lewy bodies (DLB), or Parkinson's disease (PD).
- Age 40-85 years.
- Italian native speaker.
- Able to provide informed consent.
Exclusion criteria
- Mini-Mental State Examination (MMSE) score below 15.
- Other neurological or psychiatric diagnoses, including cerebrovascular disease documented by MRI or CT.
- Severe, uncorrected hearing or visual impairment.
- Clinical Dementia Rating (CDR) score above 1.
Healthy controls
Inclusion criteria
- Italian native speaker.
- Matched to the patient groups for age, sex, and education level.
Exclusion criteria
- History of systemic, neurological, or psychiatric disease.
- Substance abuse.
- Family history of neurodegenerative disease.
- MMSE score below 27/30.
Study Plan
How is the study designed?
Design Details
- Primary Purpose: Diagnostic
- Allocation: Non-Randomized
- Interventional Model: Single Group Assignment
- Masking: None (Open Label)
Number of Arms
Arms and Interventions
Participant Group / ArmParticipant Group / Arm |
Intervention / TreatmentIntervention / Treatment |
|---|---|
|
Active Comparator: Healthy Controls
Healthy control participants will complete a one-time remote speech and language assessment. No therapeutic intervention will be administered. |
Participants will complete a one-time remote speech and language assessment. Speech and language samples will be collected and analyzed using artificial intelligence and machine-learning methods. No therapeutic intervention will be administered. |
|
Experimental: Lewy bodies or Parkinson's
Participants with dementia with Lewy bodies or Parkinson's disease will complete a one-time remote speech and language assessment. No therapeutic intervention will be administered. |
Participants will complete a one-time remote speech and language assessment. Speech and language samples will be collected and analyzed using artificial intelligence and machine-learning methods. No therapeutic intervention will be administered. |
|
Experimental: frontotemporal dementia
Participants with frontotemporal dementia will complete a one-time remote speech and language assessment. No therapeutic intervention will be administered. |
Participants will complete a one-time remote speech and language assessment. Speech and language samples will be collected and analyzed using artificial intelligence and machine-learning methods. No therapeutic intervention will be administered. |
|
Experimental: Alzheimer's Disease (AD)
Participants with Alzheimer's disease will complete a one-time remote speech and language assessment. No therapeutic intervention will be administered. |
Participants will complete a one-time remote speech and language assessment. Speech and language samples will be collected and analyzed using artificial intelligence and machine-learning methods. No therapeutic intervention will be administered. |
What is the study measuring?
Primary Outcome Measures
Primary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Performance of AI-based language analysis in distinguishing diagnostic groups
Time Frame: Day 1 (At completion of the one-time remote speech and language assessment and analysis.)
|
Accuracy of machine-learning models in classifying participants into the study groups (Alzheimer's disease, primary progressive aphasia, behavioral variant frontotemporal dementia, dementia with Lewy bodies, Parkinson's disease, and healthy controls) based on speech and language features from the remote assessment. |
Day 1 (At completion of the one-time remote speech and language assessment and analysis.)
|
Collaborators and Investigators
Sponsor
Sponsor
Collaborators
Collaborators
Investigators
Investigators
- Principal Investigator: Petronilla Battista, PhD, Istituti Clinici Scientifici Maugeri IRCCS Bari
- Study Chair: Gaia Santi, PhD, Istituti Clinici Scientifici Maugeri IRCCS Lumezzane
- Study Director: Simona Aresta, PhD, Istituti Clinici Scientifici Maugeri IRCCS Bari
Publications and helpful links
General Publications
- Battista P, Salvatore C, Berlingeri M, Cerasa A, Castiglioni I. Artificial intelligence and neuropsychological measures: The case of Alzheimer's disease. Neurosci Biobehav Rev. 2020 Jul;114:211-228. doi: 10.1016/j.neubiorev.2020.04.026. Epub 2020 May 11.
- Palmirotta C, Aresta S, Battista P, Tagliente S, Lagravinese G, Mongelli D, Gelao C, Fiore P, Castiglioni I, Minafra B, Salvatore C. Unveiling the Diagnostic Potential of Linguistic Markers in Identifying Individuals with Parkinson's Disease through Artificial Intelligence: A Systematic Review. Brain Sci. 2024 Jan 28;14(2):137. doi: 10.3390/brainsci14020137.
- Battista, P., Aresta, S., Santacesaria, P., Benzini, A., Palmirotta, C., Tagliente, S., ... & Benussi, A. (2025). Natural Language Processing differentiates between Italian individuals with Nonfluent/Agrammatic from Logopenic variants of PPA. Alzheimer's & Dementia, 21, e105208.
- Aresta S, Battista P, Palmirotta C, Tagliente S, Lagravinese G, Santacesaria P, Benzini A, Mongelli D, Minafra B, Lunetta C, Garcia AM, Salvatore C. Digital phenotyping of Parkinson's disease via natural language processing. NPJ Parkinsons Dis. 2025 Jun 23;11(1):182. doi: 10.1038/s41531-025-01050-8.
Study record dates
Study Major Dates
Study Start (Actual)
Study Start
Primary Completion (Estimated)
Primary Completion
Study Completion (Estimated)
Study Completion
Study Registration Dates
First Submitted
First Submitted
First Submitted That Met QC Criteria
First Submitted That Met QC Criteria
First Posted (Actual)
First Posted
Study Record Updates
Last Update Posted (Actual)
Last Update Posted
Last Update Submitted That Met QC Criteria
Last Update Submitted That Met QC Criteria
Last Verified
Last Verified
More Information
Terms related to this study
Keywords
Additional Relevant MeSH Terms
- Synucleinopathies
- Brain Diseases
- Central Nervous System Diseases
- Nervous System Diseases
- Mental Disorders
- Metabolic Diseases
- Neurocognitive Disorders
- Dementia
- Tauopathies
- Movement Disorders
- Parkinsonian Disorders
- Basal Ganglia Diseases
- TDP-43 Proteinopathies
- Proteostasis Deficiencies
- Frontotemporal Lobar Degeneration
- Nutritional and Metabolic Diseases
- Alzheimer Disease
- Parkinson Disease
- Neurodegenerative Diseases
- Frontotemporal Dementia
- Lewy Body Disease
Other Study ID Numbers
Other Study ID Numbers
- Prot.2541/CEL
Plan for Individual participant data (IPD)
Plan to Share Individual Participant Data (IPD)?
IPD Plan Description
Individual participant data will not be shared because the speech and language recordings and related clinical information are sensitive and potentially identifiable. The study team will protect participant confidentiality and use the data only for the purposes described in the protocol.
Drug and device information, study documents
Studies a U.S. FDA-regulated drug product
Studies a U.S. FDA-regulated device product
This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.