Report

by: Peter Hirschmann Diagnosing Methods Monitor symptoms such as: Resting Tremor Bradykinesia Rigidity Postural Instability Sub-symptom Voice Problems Use classification teaching algorithms to identify Parkinson’s Parkinson’s Disease “Movement disorder that is chronic and progressive” Parkinson's Disease Foundation There is currently no cure Treatment involves surgery or medication Parkinson Disease Data – UCI Machine Learning Repository Status - Health status of the subject (one) - Parkinson's, (zero) - healthy MDVP:Fo(Hz) - Average vocal fundamental frequency MDVP:Fhi(Hz) - Maximum vocal fundamental frequency MDVP:Flo(Hz) - Minimum vocal fundamental frequency MDVP:Jitter(%),MDVP:Jitter(Abs),MDVP:RAP,MDVP:PPQ,Jitter:DDP – Several measures of variation in fundamental frequency MDVP:Shimmer,MDVP:Shimmer(dB),Shimmer:APQ3,Shimmer:APQ5,MDVP: APQ,Shimmer:DDA - Several measures of variation in amplitude NHR,HNR - Two measures of ratio of noise to tonal components in the voice RPDE,D2 - Two nonlinear dynamical complexity measures DFA - Signal fractal scaling exponent spread1,spread2,PPE - Three nonlinear measures of fundamental frequency variation Leave One Out – Useful for realistic testing, since all known data would be used for testing new patients. Classification Methods Tries to fit the known data to a polynomial model Provided the mean and variance, it bases the identified vectors on a chosen model, Gaussian, and attempts to fit model parameters Searches and labels vectors based on the closest identified vectors Results – Polynomial Model Sum Square Error Training Error - Blue Testing Error - Green LOO Error - Red Clearly, LOO has the lowest Sum of Square Error Features 1-22 Training Data increases with x-axis and Testing Data Decreases Classification Rate Results – Maximum Likelihood Classification Rate Samples: 1-185 Samples: 1-195 LOO testing method 7 neighbors, Classification Rate vs. Percentage of Data as Testing Data Percentage of Data used as Testing Data 1%-95% Classification Rate Classification Rate Results – Nearest Neighbor # of Neighbors 1-7 LOO Method, Classification Rate vs. # of Neighbors Summary This classification method only proves that single feature vectors are not adequate but that LOO is best way to train Max Percentage when Training vs. Testing Data = 0.8203 Classification Rate using LOO = 0.9330 Neighbors: 1 C_Rate: 1.0 2 0.8814 3 0.8763 4 0.8711 5 0.8711 6 0.8454 7 0.8247 Best Classification Rate occurs when over 95% of the data is for training for every amount of neighbors When using LOO, the best results occur from one nearest neighbor Conclusion using methodology with 1-7 neighbors are all above 80% KNN is the best method of the three tested Still does not beat the comfort and knowledge of a doctor, but highly useful as a tool for mass testing. Would not require a M.D. to eliminate people the majority of people who do not have Parkinson’s