Improving Downs Syndrome Prediction with a Smart Medical Data Classification Model- Case of Study

Abstract

In health areas like drugs application, surgeries, projection of the spreading of contagious diseases, study of cancer and others, estimation, accuracy and precision are crucial. In the last few years, machine-learning methods have been used to obtain the best precision in prediction and classification of sensitive data for the medical community. Currently the Down’s syndrome risk estimation process uses established inferior and superior limits to determine if a chemical test is normal or abnormal. Using machine-learning methods we can calculate these limits dynamically. It would adapt the process to the parameters of the population improving it´s results. In this paper we first propose a model to dynamically calculate the values of the upper and lower limits of a healthy population, second the model is implemented and the process is explained and third we compare the results of applying Support Vector Machine and Naive Bayes machine learning methods to predict the risk of having Downs syndrome.