Study Rationale: The ability to track alpha-synuclein pathology in tissues outside the brain would facilitate accurate diagnosis of Parkinson's disease (PD), enable inclusion of individuals with alpha-synuclein pathology in clinical trials that target alpha-synuclein and permit tracking of PD progression. In this project, we will develop a novel approach that combines super-resolution microscopy (SRM) and artificial intelligence (AI) using machine learning (ML) to analyze alpha-synuclein aggregates in skin samples. This sensitive and specific method will allow diagnosis and monitoring of disease progression and severity by measuring alpha-synuclein burden as a biomarker and correlating its levels with an individual’s clinical status.
Hypothesis: We hypothesize that the high sensitivity of SRM and AI analysis will reveal traits of alpha-synuclein aggregates that were previously impossible to detect, allowing quantitative correlation between alpha-synuclein pathology and clinical status. This platform will allow better diagnosis and tracking of disease progression and the efficacy of disease-modifying treatment.
Study Design: We will assess the clinical status of individuals with PD and healthy volunteers, collect minimally invasive skin biopsies and image these samples using SRM. We will then employ ML tools to develop an AI-SRM PD classifier, determine the alpha-synuclein aggregates that best describe pathological aggregates and define them as a new biomarker for PD and, lastly, develop the first correlation platform between alpha-synuclein aggregates' traits and clinical status. The results will establish a quantitative tool to track disease progression and efficacy of disease-modifying treatment.
Impact on Diagnosis/Treatment of Parkinson’s disease: The AI-SRM PD classifier allows PD diagnosis and identification of patients with alpha-synuclein aggregates as candidates for clinical trials targeting alpha-synuclein aggregation. Correlating aggregation and disease severity will allow tracking of disease progression and efficacy of treatment and set a new threshold for recruitment of patients to clinical trials.
Next Steps for Development: If successful, this platform could identify alpha-synuclein aggregation years before the manifestation of clinical symptoms and allow early diagnosis in first-degree relatives and other at-risk populations during the prodromal stage of the disease. It could allow differentiation between PD and other synucleinopathies in a non-invasive manner.