Using Artificial Intelligence to Detect Early Signs of Alzheimer's Disease in People With Memory Concerns (AHEAD)

AHEAD: AI-driven Brain Health for Early Alzheimer's Disease Detection in Individuals With Subjective Cognitive Decline

AHEAD is a prospective, longitudinal, risk-stratified single-arm interventional study enrolling 300 patients with Subjective Cognitive Decline (SCD) at IRCCS San Raffaele Hospital, Milan, Italy.

The study uses artificial intelligence (AI) to integrate multimodal data - including MRI, EEG, Optical Coherence Tomography (OCT), neuropsychological assessments, and plasma biomarkers - to identify individuals with underlying Alzheimer's disease (AD) biology and predict cognitive progression.

Only participants found to be AD plasma biomarker positive (SCD+) undergo longitudinal follow-up at 12 and 24 months. Participants classified as high risk additionally receive a 6-month personalized multidisciplinary intervention combining high-frequency transcranial magnetic stimulation (TMS), digital cognitive training, structured physical exercise, and targeted management of modifiable vascular and behavioral risk factors.

Study Overview

• Status: Not yet recruiting
• Conditions: Alzheimer Disease; Mild Cognitive Impairment; Cognitive Decline; Subjective Cognitive Decline
• Intervention / Treatment: Device: High-frequency Transcranial Magnetic Stimulation (TMS); Behavioral: Digital Cognitive Training; Behavioral: Structured Physical Exercise; Other: Management of Modifiable Vascular and Behavioral Risk Factors

Detailed Description

Subjective Cognitive Decline (SCD) refers to the self-perception of worsening cognitive abilities despite normal performance on standardized neuropsychological testing. It affects approximately 10% of the general population and 20-35% of patients attending memory clinics. Although the majority of individuals with SCD do not progress to clinical forms of Alzheimer's disease (AD), they show a higher prevalence of AD-related pathological biomarkers compared with individuals without subjective cognitive complaints, with rates of cognitive decline estimated at approximately 20% per 1,000 person-years in memory clinic patients.

Plasma biomarkers for AD represent minimally invasive and easily accessible diagnostic tools; however, their large-scale implementation in the broad SCD population is neither economically nor ethically sustainable because of costs, the risk of overdiagnosis, and the associated psychological burden. Artificial intelligence (AI) may represent a transformative tool for addressing the complexity of SCD management. By integrating multimodal data including cognitive assessments, MRI, EEG, and OCT, AI may help identify those individuals with SCD most likely to benefit from further diagnostic investigations, including plasma biomarker assessment.

At baseline (T0), all participants undergo a minimum assessment dataset including clinical evaluation, standard neuropsychological assessment, structural MRI, and blood sampling. A subset additionally undergoes a comprehensive risk assessment, extended neuropsychological evaluation including digital cognitive testing and the Preclinical Alzheimer Cognitive Composite (PACC), resting-state EEG, and retinal imaging through Optical Coherence Tomography (OCT).

Only patients found to be AD plasma biomarker positive (SCD+) undergo longitudinal follow-up visits at 12 months (M12) and 24 months (M24), including clinical evaluation, neuropsychological assessments, and blood sampling to monitor cognitive and biological progression.

Participants stratified as high risk - defined as plasma p-tau217 greater than 0.1325 pg/mL, and/or APOE epsilon4 carrier, and/or elevated CAIDE Dementia Risk Score - enter a 6-month single-arm multidisciplinary intervention comprising: (1) targeted management of modifiable vascular and behavioral risk factors with monthly remote follow-up; (2) high-frequency TMS during the first 4 weeks (2-3 sessions per week); (3) home-based digital cognitive training, 2 sessions per week of 30 minutes each over 5 months; (4) structured physical exercise (walking, cycling, resistance training), 2 sessions per week of 30 minutes each.

A retrospective SCD cohort (rSCD), comprising patients who underwent the minimum assessment dataset within one year prior to enrollment and were found to be AD plasma biomarker positive, undergoes follow-up at M12 and M24 according to the same longitudinal protocol, with the intervention starting at M12.

AI models will integrate multimodal baseline data using machine learning (logistic regression, random forest), deep learning (CNNs for MRI/OCT, RNNs/Transformers for EEG), and survival analysis (Cox proportional hazards, DeepSurv). All models will be validated using k-fold cross-validation with performance metrics including AUC, sensitivity, specificity, balanced accuracy, and positive and negative predictive values.

• Study Type: Interventional
• Enrollment (Estimated): 300
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Federica FA Agosta, MD; Phone Number: 0226433051; Email: agosta.federica@hsr.it
• Study Contact Backup: Name: Elisa EC Canu, PhD; Phone Number: 0226433033; Email: canu.elisa@hsr.it

Study Locations

• Italy
  • Milano
    • Milan, Milano, Italy, 20132
      • San Raffaele Neurology Unit
      • Contact: Federica Agosta, MD; Phone Number: 0226433051; Email: agosta.federica@hsr.it
      • Contact: Elisa EC Canu, PhD; Phone Number: 0226433033; Email: canu.elisa@hsr.it
      • Principal Investigator: Massimo Filippi, Prof

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. Diagnosis of Subjective Cognitive Decline (SCD) according to international diagnostic criteria (Jessen et al., 2014).
2. Self-experienced persistent decline in cognitive capacity in comparison with a previously normal status and unrelated to an acute event.
3. Normal age-, gender-, and education-adjusted performance on standardized cognitive tests used to classify mild cognitive impairment (MCI) or prodromal AD.
4. Age greater than or equal to 40 years.
5. Native Italian Speaker.
6. Stable pharmacological treatment for at least 4 weeks prior to enrollment.
7. Provision of oral and written informed consent to study participation.

Exclusion Criteria:

1. Presence of MCI, prodromal AD, or dementia.
2. Any major systemic, psychiatric, or neurological disturbance.
3. Medical conditions or substance abuse that could interfere with cognition.
4. Pacemaker and/or other implanted neurostimulation devices in the head/neck district.
5. Contraindications to undergoing MRI examination.
6. Brain damage at routine MRI, including extensive cerebrovascular disorders.
7. Traumatic or surgical wounds that could determine a risk of infection at the site of non-invasive stimulation.
8. Scalp alterations that could determine the spread of excessive current from the device.
9. Known history of epilepsy (due to small risk of seizure induction from rTMS in epileptic patients).
10. Denial of oral and written informed consent to study participation.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: SCD Participants; All 300 SCD participants undergo baseline multimodal assessment. Those found to be AD plasma biomarker positive (SCD+) undergo longitudinal follow-up at M12 and M24. Those classified as high risk (plasma p-tau217 greater than 0.1325 pg/mL, and/or APOE epsilon4 carrier, and/or elevated CAIDE Dementia Risk Score) additionally receive a 6-month multidisciplinary personalized intervention combining high-frequency TMS, digital cognitive training, structured physical exercise, and targeted vascular and behavioral risk factor management.

Device: High-frequency Transcranial Magnetic Stimulation (TMS); High-frequency repetitive TMS (rTMS) delivered according to an intensive protocol during the first 4 weeks of the intervention period (2-3 sessions per week). Applied to brain regions associated with cognitive function to optimize brain health and reduce risk of cognitive decline. Administered by trained professionals following international safety guidelines (Rossi et al., 2009).; Behavioral: Digital Cognitive Training; Home-based cognitive training delivered via digital platform over 5 months: 2 sessions per week of 30 minutes each. Targets perceived cognitive deficits and related domains (memory, executive functions, attention, visuospatial abilities, language) with progressive adaptation to individual performance level. Compliance monitored via dedicated applications and/or activity diaries. Monthly remote meetings with neuropsychologists to monitor progress.; Behavioral: Structured Physical Exercise; Home-based structured physical exercise program over 5 months: 2 sessions per week of 30 minutes each. Activities include walking, cycling, and global resistance training. An in-person familiarization session is conducted before program start. Monthly remote meetings with physiotherapists to monitor progress and adapt the program. Compliance remotely monitored via dedicated applications and/or activity diaries.; Other: Management of Modifiable Vascular and Behavioral Risk Factors; Personalized pharmacological and non-pharmacological interventions targeting modifiable vascular and behavioral risk factors including blood pressure, cholesterol, BMI, physical inactivity, dietary habits, sleep quality, and social isolation. Monthly remote follow-up visits over 6 months to monitor treatment adherence and optimize risk factor control.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of AI models in identifying AD biomarker-positive SCD subjects (AUC)	Area under the ROC curve (AUC), sensitivity, and specificity of AI models in discriminating between plasma AD biomarker-positive and biomarker-negative SCD subjects, assessed at study entry.	Baseline (study entry)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Predictive accuracy of AI models for cognitive progression (AUC)	Area under the ROC curve (AUC), sensitivity, and specificity of AI models in discriminating between SCD progressors and non-progressors (conversion to Mild Cognitive Impairment or dementia) over a 24-month follow-up period.	Baseline, 12 months (M12), and 24 months (M24)

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Change in Preclinical Alzheimer Cognitive Composite (PACC) score	Preclinical Alzheimer Cognitive Composite (PACC) score assessed before and after the intervention. Higher scores indicate better cognitive performance. Primary outcome is maintenance of a stable PACC score after the intervention.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in self-perceived quality of life (EQ-5D-3L)	Self-perceived quality of life measured by the EQ-5D-3L patient-reported instrument. Higher scores indicate better quality of life.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in 6-minute walking test distance	Distance in meters walked in 6 minutes. An increase in distance indicates improved physical performance.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in functional upper limb strength	Global upper limb strength changes assessed via standardized functional strength tests before and after the intervention.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in functional lower limb strength	Global lower limb strength changes assessed via standardized functional strength tests before and after the intervention.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in heart rate (bpm)	Change in heart rate (bpm), measured before and after the intervention program.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in systolic blood pressure (mmHg)	Change in systolic blood pressure (mmHg), measured before and after the intervention program.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in diastolic blood pressure (mmHg)	Change in diastolic blood pressure (mmHg), measured before and after the intervention program.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)
Change in Borg perceived exertion scale	Change in Borg perceived exertion scale measured before and after the intervention program.	Before and after the 6-month intervention (Baseline to Month 6 , or Month12 to Month 18 for rSCD cohort)

Collaborators and Investigators

• Sponsor: IRCCS San Raffaele
• Investigators: Principal Investigator: Massimo Filippi, Prof, IRCCS San Raffaele

Study record dates

Study Major Dates

• Study Start (Estimated): August 1, 2026
• Primary Completion (Estimated): August 1, 2028
• Study Completion (Estimated): August 1, 2029

Study Registration Dates

• First Submitted: June 8, 2026
• First Submitted That Met QC Criteria: June 11, 2026
• First Posted (Actual): June 17, 2026

Study Record Updates

• Last Update Posted (Actual): June 17, 2026
• Last Update Submitted That Met QC Criteria: June 11, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: MRI; Alzheimer's disease; Transcranial Magnetic Stimulation; EEG; Artificial Intelligence; APOE; Cognitive Training; Optical Coherence Tomography; Deep Learning; Physical Exercise; Machine Learning; Subjective Cognitive Decline; Brain Health; Plasma biomarkers; p-tau217
• Additional Relevant MeSH Terms: Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Mental Disorders; Neurocognitive Disorders; Cognition Disorders; Dementia; Tauopathies; Neurodegenerative Diseases; Behavior; Cognitive Dysfunction; Alzheimer Disease; Motor Activity
• Other Study ID Numbers: RF-2024-12380444

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No