BSc Project, using Android SDK and Python.
The purpose of this application is to predict a diagnosis based on the user's symptoms. The training data was provided by several DBs (Wikidata / DBpedia / MayoClinic) ~ 5000 diseases; each containing symptoms.
The prediction was made using 3 classifiers from scikit-learn library (Naive Bayes/ Random Forests/ Logistic Regression). Each prediction contains a chance rate of occurence alongside useful suggestions, that would improve the accuracy of the prediction, if that symptom has evidence in that individual.
Images and icons provided by :