Clinical Informatics Year 3

BIOL72230 Clinical Informatics Year 3 30 Full year Postgraduate Taught Level 7 Helen Hulme Unit coordinator School of Biological Sciences 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 15.0 Policy, Strategy and Operations Current national and international health and social care policies including health informatics The policy/strategy development process National indicators and outcome frameworks in health and social care, and informatics (e.g., digital maturity index) Tools for strategic decision-making and planning including those to identify issues, and consult with stakeholders to agree policy/strategy Monitoring the effectiveness and consequences of policy/strategy implementation Development of key performance indicators/measures for services distinguishing between quantity and quality, and between effort and effect Sources of data available to monitor and evaluate policy/strategy implementation Communication strategies to framing policy and strategy changes Business and commercial models and management Approaches and frameworks used in health and social care Acquisition of products, services and people The healthcare sector management and organisational structures Mechanisms, processes and methodologies for addressing and improving efficiency and productivity (e.g., Lean and Six Sigma) Methods, mechanisms, processes and tools to collect assess and provide evidence based medicine and practiceDigital Health Tools and Clinical Decision Making Digital adoption and usage Factors to consider including usage of frameworks such as NASSS Requirement for decision support, susceptibility for bias and error Knowledge generation, acquisition and modelling tools Computable knowledge Personalised medicine Pharmacogenomics The role of decision support tools in genomics bioinformatics, including practical considerations of this Computer aided diagnosis in imaging Barriers to implementation Automation bias Bias within datasets and how these propagate into decision support Applicability of guidanceArtificial IntelligenceBig data in biomedicine and health (including open resources) Overview of use cases of AI/ML in healthcare, including their critical evaluation e.g., robotic surgery, health monitoring with wearables, automated image diagnosis and deep-learning in image classification Programming for AI in python (or similar software) Explanation of the following methods, including the strengths and limitations of each, and how to interpret their outputs to draw meaning: High dimensional methods (e.g., PCA) Supervised machine learning (introduction, fundamental and advanced methods) Unsupervised machine learning Model performance metrics Ethics and bias Reporting – standards for journal articles and quality guidelines Regulatory environment Policy, Strategy and Operations Current national and international health and social care policies including health informatics The policy/strategy development process National indicators and outcome frameworks in health and social care, and informatics (e.g., digital maturity index) Tools for strategic decision-making and planning including those to identify issues, and consult with stakeholders to agree policy/strategy Monitoring the effectiveness and consequences of policy/strategy implementation Development of key performance indicators/measures for services distinguishing between quantity and quality, and between effort and effect Sources of data available to monitor and evaluate policy/strategy implementation Communication strategies to framing policy and strategy changes Business and commercial models and management Approaches and frameworks used in health and social care Acquisition of products, services and people The healthcare sector management and organisational structures Mechanisms, processes and methodologies for addressing and improving efficiency and productivity (e.g., Lean and Six Sigma) Methods, mechanisms, processes and tools to collect assess and provide evidence based medicine and practiceDigital Health Tools and Clinical Decision Making Digital adoption and usage Factors to consider including usage of frameworks such as NASSS Requirement for decision support, susceptibility for bias and error Knowledge generation, acquisition and modelling tools Computable knowledge Personalised medicine Pharmacogenomics The role of decision support tools in genomics bioinformatics, including practical considerations of this Computer aided diagnosis in imaging Barriers to implementation Automation bias Bias within datasets and how these propagate into decision support Applicability of guidanceArtificial IntelligenceBig data in biomedicine and health (including open resources) Overview of use cases of AI/ML in healthcare, including their critical evaluation e.g., robotic surgery, health monitoring with wearables, automated image diagnosis and deep-learning in image classification Programming for AI in python (or similar software) Explanation of the following methods, including the strengths and limitations of each, and how to interpret their outputs to draw meaning: High dimensional methods (e.g., PCA) Supervised machine learning (introduction, fundamental and advanced methods) Unsupervised machine learning Model performance metrics Ethics and bias Reporting – standards for journal articles and quality guidelines Regulatory environment The overarching aim of this module is to introduce key digital tools and technologies (e.g., AI) to inform clinical decision making. To do this effectively students need to have an understanding of the wider context from policy through to operations, and in turn, they will need to know how to introduce these safely and efficiently into our healthcare system using a theory of change approach. The module is made of three constituent parts:Policy Strategy and Operations This section will provide trainees with the key knowledge and skills required by professionals to understand, contribute to, write and deliver policy and strategy for safe and secure health systems.Digital Health Tools and Clinical Decision Making The aim of this section is to introduce trainees to how patient data and clinical knowledge is used to inform decision-making. Trainees will learn about the different forms of healthcare knowledge, how they are defined and represented, and the design and evaluation of decision support systems.Artificial Intelligence This section introduces the field of Artificial Intelligence (AI) providing the key concepts and knowledge in how it is used or has the potential to be used to solve healthcare challenges, whilst also discussing the wider issues considering its usage. This module will also provide hands-on experience in developing algorithms/systems to address real world healthcare problems. Policy, Strategy and Operations<ul><li>Discuss the policy-making process in healthcare, including an understanding of where to find and identify key existing healthcare policies and legislation.</li><li>Explain the current organisational structures of healthcare, including the associated regulation and performance frameworks, and the role of health informatics within these structures.</li><li>Discuss the role of health data in developing and evaluating health policies to support safe and efficient services.</li><li>Communicate health and informatics policy management issues using appropriate channels and technologies.</li></ul>Digital Tools and Clinical Decision Support<ul><li>Assess the application of clinical decision support to benefit individuals and/or populations, including real-world examples.</li><li>Demonstrate a practical understanding of how knowledge is transformed into a clinical decision support tool.</li><li>Discuss and apply frameworks for successful digital health tool adoption.</li></ul>Artificial Intelligence<ul><li>Demonstrate an understanding of the main advanced analytic and machine learning methodologies, and settings where each method might be more/less applicable.</li><li>Demonstrate an understanding of the current limitations of common AI/ML methods, including their dependence on data, computational resources and causal explanation.</li></ul> Intellectual skills:<ul><li>Critically evaluate existing AI/ML solutions in healthcare, and be able to explain the key strengths and limitations.</li><li>Critically appraise the uses of AI in healthcare and how they could impact the delivery of healthcare.</li><li>Critically evaluate strategies for the evaluation of digital health and decision support tools.</li><li>Critically evaluate the types of clinical decision support, including their strengths and weaknesses and areas where each might be applied.</li><li>Critically evaluate the role of health informatics in current national health policy and appraise how national policy is translated into local strategy, planning and activity.</li></ul> Practical skills:  <ul><li>Design and implement AI/ML systems in a suitable programming language and evaluate their performance using standard performance metrics.</li><li>Apply a ‘systems thinking’ approach to resolve identified organisational/departmental problems.</li><li>Critically appraise the methods, mechanisms and processes commonly used for change management activity in the healthcare sector in the context of health informatics.</li></ul> Transferable skills and personal qualities:<ul><li>Present complex ideas in simple terms in written formats.</li><li>Manage personal workload and objectives to achieve module of work.</li><li>Actively seek accurate and validated information from all available sources.</li><li>Work as part of a team to understand a common problem.</li></ul> 1. Lectures, tutorials, case studies and PBL - in particular we will make extensive use of PBL workshops to explore case-studies that focus on how to introduce digital tools into the healthcare setting. 2. E-learning:  - evidence-based learning supported by course notes, audio lectures, case studies - online tutorials   2 Written assignment (inc essay) 35% 3 Report 35% 7 Oral assessment/presentation 30% Policy, Strategy and Operations (30%) An annotated slide deck, plus 15 minute presentation on how to introduce AI in a healthcare setting Summative feedback provided 15 working days following the submissionClinical Decision Support (35%) A written protocol/guidelines for decision support (1,500 words) Summative feedback provided 15 working days following the submissionArtificial Intelligence for Healthcare (35%) 6-page written report Summative feedback provided 15 working days following the submission N Lectures 300 0 0