Hypertension is known to be one of the leading causes of heart disease and stroke, killing around 7.5 million people worldwide every year, mostly because of its late diagnosis.In order to confirm the diagnosis of Hypertension, it is necessary to collect repeated medical measurements. One solution is to exploit these measurements and integrate them into Electronic Health Records by Machine Learning algorithms.In this work, we focused on ensemble learning methods that combine several machine learning algorithms for classification. These models have been widely used to improve classification performance of a single classifier. For that purpose, methods such as Bagging and Boosting are used. These methods mainly use majority or weighted voting to integrate the results of the classifiers. However, one major drawback of these approaches is their opacity, as they do not provide results explanation and they do not allow prior knowledge integration. As we use machine learning for healthcare, the explanation of classification results and the ability to introduce domain and clinical knowledge inside the learned model become a necessity.In order to overcome theses weaknesses, we introduce a new ensemble method based on multiagent argumentation.The integration of argumentation and machine learning has been proven to be fruitful and the use of argumentation is a relevant way for combining the classifiers. Indeed, argumentation can imitate human decision-making process to realize resolution of the conflicts.Our idea is to automatically extract the arguments from ML models and combine them using argumentation. This allows to exploit the internal knowledge of each classifier, to provide an explanation for the decisions and to facilitate integration of domain and clinical knowledge.In this thesis, objectives were multiple. From the medical application point of view, the goal was to predict the treatment of Hypertension and the date of the next doctor visit. From the scientific point of view, the objective was to add transparency to ensemble method and to inject domain and clinical knowledge.The contributions of the thesis are various:-Explaining predictions;-Integrating internal classification knowledge;-Injecting domain and clinical knowledge;-Improving predictions accuracy.The results demonstrate that our method effectively provides explanations and transparency of the ensemble methods predictions and is able to integrate domain and clinical knowledge into the system. Moreover, it improves the performance of existing machine learning algorithms.