AI-based predictive biomarkers for chronic neurological diseases: the rAIdD prospective, multicenter, observational study protocol - Report - MDSpire

Predictive Biomarkers Utilizing AI for Chronic Neurological Disorders: Protocol for the rAIdD Multicenter Observational Study

  • By

  • Simone Varrasi

  • Alfredo Pulvirenti

  • Vincenzo Catania

  • Maurizio Palesi

  • Concetto Spampinato

  • Davide Patti

  • Orazio Tomarchio

  • Giovanni Micale

  • Alessia Simone

  • Lisa Passarello

  • Federica Proietto Salanitri

  • Giovanni Patanè

  • Salvatore Ravidà

  • Clara Grazia Chisari

  • Giuseppe Zappalà

  • Emanuele D'Amico

  • Carlo Avolio

  • Federica Felicetti

  • Claudio Gasperini

  • Simone Rossi

  • Paolo Manganotti

  • Pierpaolo Busan

  • Carmelo Rodolico

  • Rossella Laudani

  • Roberto Marino

  • Massimo Villari

  • Francesco Patti

  • July 17, 2026

Share

Clinical Report: Predictive Biomarkers Utilizing AI for Chronic Neurological Disorders

Overview

The rAIdD multicenter observational study aims to develop predictive digital biomarkers for chronic neurological disorders, including Multiple Sclerosis, Parkinson's disease, and Alzheimer's Disease. The study will enroll 780 participants and utilize AI and wearable technologies for data collection and analysis.

Background

Chronic neurological disorders pose a significant global health challenge, leading to disability and cognitive decline. Identifying predictive biomarkers is crucial for personalized disease management and improving patient outcomes. The rAIdD initiative seeks to leverage AI and integrated data to enhance early diagnosis and monitoring of these conditions.

Data Highlights

ConditionParticipants
Multiple Sclerosis300
Parkinson's Disease150
Alzheimer's Disease150
Healthy Controls180

Key Findings

  • The study will follow participants for 18 months within a 48-month period.
  • Standardized assessments will include clinical, neuropsychological, and digital evaluations.
  • Wearable sensors will continuously monitor biometric and behavioral data.
  • Machine learning will be used to identify multimodal predictive biomarkers.
  • The study has received ethical approval and will ensure informed consent from all participants.

Clinical Implications

The findings from this study may provide insights into the mechanisms of chronic neurological disorders and the development of interventions.

Conclusion

The rAIdD study aims to integrate AI and digital technologies in the management of chronic neurological disorders.

Related Resources & Content

  1. Frontiers in Neurology, 2026 -- Integrating neuroimaging and plasma biomarkers to predict preclinical Alzheimer’s disease progression
  2. BMC Psychiatry, 2025 -- Study protocol for a randomized controlled trial assessing clinical efficacy of digital cognitive rehabilitation for preclinical and mild clinical stages of alzheimer’s disease continuum: the MI-RICORDO project
  3. Acta Neuropathologica, 2025 -- Pathological Associations of Cognitive Decline in Alzheimer’s Disease with Varied CSF Biomarker Profiles: A Focus on Co-existing Conditions
  4. Alzheimer's Association Clinical Practice Guideline on the use of blood-based biomarkers in the diagnostic workup of suspected Alzheimer's disease within specialized care settings - PubMed
  5. The 2024 McDonald criteria for the diagnosis of multiple sclerosis: implications for clinical practice - PubMed
  6. Acta Neuropathologica — Unique cerebrovascular mechanisms contributing to neurodegeneration in Alzheimer's disease
  7. Alzheimer's Association Clinical Practice Guideline on the use of blood-based biomarkers in the diagnostic workup of suspected Alzheimer's disease within specialized care settings - PubMed
  8. Alzheimer's Association Workgroup Publishes Biology-Based Criteria for Diagnosis and Staging of Alzheimer's Disease
  9. Blood‐based biomarkers for detecting Alzheimer's disease pathology in cognitively impaired individuals within specialized care settings: A systematic review and meta‐analysis - PMC
  10. Posttreatment Amyloid Levels and Clinical Outcomes Following Donanemab for Early Symptomatic Alzheimer Disease: A Secondary Analysis of the TRAILBLAZER-ALZ 2 Randomized Clinical Trial - PubMed
  11. The 2024 McDonald criteria for the diagnosis of multiple sclerosis: implications for clinical practice - PubMed
  12. 1 2024 MAGNIMS-CMSC-NAIMS consensus recommendatio
  13. Best Practices Guideline on the Use of Neurofilament – Consortium of Multiple Sclerosis Centers
  14. Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review - PMC
  15. V I E W P O I N T
  16. The α-synuclein seed amplification assay: Interpreting a test of Parkinson's pathology - ScienceDirect
  17. Digital biomarkers for non-motor symptoms in Parkinson’s disease: the state of the art | npj Digital Medicine
  18. Systematic review of prognostic models in Parkinson’s disease | npj Parkinson's Disease

Original Source(s)

AI-based predictive biomarkers for chronic neurological diseases: the rAIdD prospective, multicenter, observational study protocol

  • by Simone Varrasi, Alfredo Pulvirenti, Vincenzo Catania, Maurizio Palesi, Concetto Spampinato, Davide Patti, Orazio Tomarchio, Giovanni Micale, Alessia Simone, Lisa Passarello, Federica Proietto Salanitri, Giovanni Patanè, Salvatore Ravidà, Clara Grazia Chisari, Giuseppe Zappalà, Emanuele D'Amico, Carlo Avolio, Federica Felicetti, Claudio Gasperini, Simone Rossi, Paolo Manganotti, Pierpaolo Busan, Carmelo Rodolico, Rossella Laudani, Roberto Marino, Massimo Villari, Francesco Patti

  • July 17, 2026

Related Content

Menopause and ageing in women with multiple sclerosis

In Memoriam: J. Richard Baringer, MD (1935–2025)

FDA Approves Low-Dose Macrocyclic Contrast Agent for MRI

The macrocyclic gadolinium-based contrast agent has a recommended dose of 0.01 mmol/kg actual body weight.