There are now various issues regarding data processing and data storage in the healthcare sector. The amount of data is increasing daily due to the rise of new health issues throughout the populace. The healthcare sector can use machine learning (ML) algorithms in an assortment of ways since methods based on ML support physicians in diagnostics and prophylaxis in addition to about treatment and especially during operations. There is only a small number of industries which are not benefiting about increased Information Technology (IT) assets and self-learning computer networks. The Internet of Things (IOT), on the other hand, is crucial to the health care system and aids in its transformation into a smart one. Numerous medical records with patient diagnosis information are used as input. The characteristic scaling procedure handles the supplied data. For scaling features in such a system, a robust scalar is employed. Using principal component analysis (PCA), the dimension is reduced. Employing the more trustworthy random forest classifier, the dimensions compressed data are categorized. Subsequently, it is discovered that the categorization outcomes are more precise.