The healthcare sector is an important pillar of every community, numerous research studies have been carried out in this context to optimize medical processes and improve care quality and facilitate patient management. In this article we have analyzed and examined different works concerning the exploitation of the most recent technologies such as big data, artificial intelligence, machine learning, and deep learning for the improvement of health care, which enabled us to propose our general approach concentrating on the collection, preprocessing and clustering of medical data to facilitate access, after analysis, to the patients and health professionals to predict the most frequent pathologies with better precision within a notable timeframe. keywords: Healthcare, big data, artificial intelligence, automatic language processing, data mining, predictive models.