Abstract: Abstract: In the past decade, machine learning has acquired great attention driven by cheaper computing power and cost effective storage, data processing and analysis. Enhanced algorithms are built and deployed to broad datasets in order to detect hidden insights and links between data items which are not evident to humans. These insights assist companies to decide better and optimise key interest indicators. The increasing popularity of machine learning is also derived from the agnosticness in the field of application of learning algorithms. For example, classification techniques that may be used to categorise windmill blade problems can also be used to categorise television watchers in a survey. However the true value of machine learning depends on how these algorithms can be tailored and applied to tackle particular issues in the real world. Two of these applications for medical interpretation for automated analysis are discussed in this document. Our first case study shows how we diagnose the condition of Alzheimer based on cognitive test results and demographic data, using Bayesian Inference, a machine learning approach. The second study focuses on automated cell classification, in order to determine the progression and severity of breast cancer through the use of artificial neural networks. Although this study are yet preliminary, the importance of machine learning approaches in rapid, efficient and automated processing of data is demonstrated. Machine learning gives patients hope in early disease identification, supports informed treatment choices and may help to improve overall quality of life.