• Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.
Principal Investigator  
Principal Investigator's Name: Micol de Ruvo
Institution: Philyra UG
Department: -
Proposed Analysis: Aim: We are building a test for risk assessment of PD through machine learning driven assessment of olfactory disorders and early symptoms, in order to to provide non invasive and real time identification of individuals at low or high risk of developing these diseases. Product: We provide physicians with a software that instructs the patients on answering a questionnaire and take an olfactory test. The patients can take the test by themselves/with little supervision and the physician analises the resulting risk score and gives a recommendation on further steps (e.g. repeat the test in a year or see a neurologist). In a second phase, we build a product that patients or their relatives could buy at pharmacies for self test and monitoring of the progress. Background The current diagnosis of Parkinson's Disease (PD) occurs when the stage is already advanced. In this view, early diagnosis is needed and early intervention through treatments or lifestyle changes could slow down the progression of the disease by several years, thus having a major impact on quality of life, costs and human burden. Current research is focusing on PD biomarkers that are thought to indicate the early stages of the disease, such as tau protein levels and amyloid beta deposits in cerebrospinal fluid (CSF). However, these diagnostics tools are invasive and costly. Among the non invasive biomarkers, olfactory changes are a reliable biomarker of several neurological and psychiatric disorders including PD disease. Consequently, measurements of olfactory performance might serve as a useful tool to significantly improve diagnostic accuracy. However, olfactory tests provide limited specificity and a data driven approach that takes into account risk factors and early symptoms, is needed. Benefits: The impact of our test is manifold. First, Parkinson’s patients that are diagnosed with a high risk can benefit from using targeted treatments earlier and delay the onset of severe symptoms. Second, our test identifies those individuals who are eligible for clinical trials and later on will benefit from the availability of early drugs. Third, the negative predictive value of our test will help giving answers to those patients who are worried of developing a neurodegenerative disease and will cut costs on unnecessary exams. Last, given that memory and the sense of smell can be trained if identified early, awareness plays a crucial role. The insights from our learning algorithm will direct us towards the development of an automatic disease screening tool which could be used by researchers and doctors working with clinical conditions marked by olfactory deficits including Alzheimer’s Disease and Parkinson’s Disease. We hope that with identifying abnormal olfactory and risk factor patterns we can speed up the diagnostic screening procedures in a non invasive, cheap and reliable manner.
Additional Investigators