IIDS62702 15 Semester 2 Postgraduate Taught Level 6 Division of Informatics, Imaging and Data Sciences 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 7.5 <p>This module explores the fundamental principles of applied ‘machine learning’ in healthcare. This course has a focus on applied methods for problems in prevention, diagnosis, therapy, and prognosis. Authentic health data and examples serve as an opportunity to explore the concepts in greater depth, raise questions, and enable participants to acquire greater understanding regarding the role of different Machine Learning-algorithms in healthcare to automatically discover new associations and the construction of clinical rules and predictive models. The structure for each topic is organised in the following typical order: (a) online lecture or narrated presentation, (b) online discussion of current research, and (c) implementation of a mini-project. &nbsp;&nbsp;</p> <p>This module explores the fundamental principles of applied ‘machine learning’ in healthcare. This course has a focus on applied methods for problems in prevention, diagnosis, therapy, and prognosis. Authentic health data and examples serve as an opportunity to explore the concepts in greater depth, raise questions, and enable participants to acquire greater understanding regarding the role of different Machine Learning-algorithms in healthcare to automatically discover new associations and the construction of clinical rules and predictive models. The structure for each topic is organised in the following typical order: (a) online lecture or narrated presentation, (b) online discussion of current research, and (c) implementation of a mini-project. &nbsp;&nbsp;</p> <p>The module provides an introduction into the principles of machine learning in healthcare, covering the key concepts involved in designing and evaluating approaches to machine learning. It also will provide a practical introduction to common approaches to machine learning, so that students acquire experience in using different machine learning algorithms in the context of real health problems.</p> <p>By the end of the course students will understand the rationale for using machine learning in healthcare and biomedicine.</p><p>Students will understand the basic principles of machine learning and be able to construct feature vectors and use multidimensional feature spaces to solve problems of classification and prediction of values.</p><p>Students should be able carry out tasks such as simplifying the dimensionality of a health feature space, designing and evaluate different classification algorithms (k Nearest Neighbours, Bayesian Classifiers, Decision Trees, Neural Nets, Support Vector Machines) &nbsp;</p><p>Students will be familiar with the different forms of data used in healthcare and their use in decisions in the prevention of diseases, the diagnosis of diseases from health data, and in the selection of therapeutic options.&nbsp;</p> 5 Portfolio 100% <p>Students will be surveyed via Opinio. Comments will be solicited via an appointed student rep and discussed at departmental teaching meetings.</p><p>Course materials will discussed with the programme director at the outset and then be peer reviewed annually. &nbsp;At least one lecture will be observed annually. Assessments will be moderated internally and reviewed by the external examiner</p> N Lectures 150 0 0