The convergence of smart mobility and smart healthcare creates new opportunities for integrating predictive health intelligence into intelligent transport systems. Genetic disorders are disorders caused due to faulty gene or genetic mutation and associated with high mortality. Diseases like Cancer, Sickle Cell Disease are certain examples of genetic diseases. In order to ensure timely detection of these disorders we need robust systems ensuring low false negative rates and higher accuracy. In this project we aim to highlight a comparative analysis of various classification models like support vector machine, AdaBoost, XGBoost, logistic regression, etc. for 3 class and multiclass classification of various genetic disorders in our dataset based on patient history and medical data provided in open access Kaggle dataset. We applied GridSearchCV to find the optimal hyperparameters in our model. Further we have used metrics like accuracy, confusion matrix to compare the models for maximum recall. KNN and AdaBoost provided the least accuracy in multiclass classification while all other models outperformed from 99 to 100% accuracy stating their importance in text based medical data analysis. Using Explainable AI like LIME and Stratified K-Fold cross validation further helped us cross check our results. We were able to improve the recall of genetic disorder prediction which is crucial in healthcare setup to limit false negative cases.