Diagnosing Parkinson`s disease with an ‘optimal predictor machine’
Diagnosing Parkinson`s disease with an ‘optimal predictor machine’
Where did the research take place?
The study site has not been established. Author addresses may differ from where the research occurred.
A plain-language reading has not been prepared for this paper yet.
Original abstract
Parkinson’s Disease (PD) is a progressive neurodegenerative disorder affecting 1-2% of the population above the age of 65. The disease attacks brain regions which affect the movement of the patient. Today, there is no available cure for the disease, but symptomatic treatments offer some relief. The lack of reliable tools for prognosis and personalized intervention remains a significant barrier in clinical research. This thesis explores the use of "Bayesian nonparametric infer ence", referred to as the "Optimal Predictor Machine" (OPM), as a framework for diagnostic and prognostic modeling in PD. The OPM offers a model-free, prob abilistically rigorous alternative to traditional statistical and machine learning approaches, with particular strength in quantifying uncertainty and visualizing generalizability. By applying the OPM to data from different medical studies, this thesis explores its ability to quantify uncertainty, generate individualized predictions, and potentially outperform traditional statistical methods. Through collaboration with medical researchers, the studies presented in this thesis highlight the feasibility and value of integrating OPM into PD research, paving the way for more informed clinical decision-making and future applications in precision medicine. Masteroppgave i Anvendt datateknologi og ingeniørvitenskap. Fakultet for teknologi, miljø- og samfunnsvitskap/ Institutt for datateknologi, elektroteknologi og realfag/ Høgskulen på Vestlandet. ADA599