Thyroid Detection and Interpretation using XAI (eXplanable Artificial Intelligence)

We have designed this machine learning model in order to help the victims of thyroid suffering from its chronic effects. In our machine learning model we will be using various classification algorithms like KNN(K-nearest neighbours) classifiers, random forest classifier, Naive bayes classifier, random forest classifier, SVM(support vector machines) and decision trees. Among all the above classification algorithms random forest have produced more accurate results. We will be taking the data of different patients from the laboratories and convert into. csv file. We will train the model using the above algorithms and the performance of the model is calculated on the basis of Accuracy, Precision, Recall and F1-Score. In our paper we will be using explainable AI (XAI) to explain the results and output produced by our model. There are several methods and processes in the field of XAI, here we are using an open source python library called SHAP(shapely additive explanations). The main advantage of SHAP is that it will help the user to understand which feature is most influential in the model.