Applied Health Data Analytics

IIDS61601 Applied Health Data Analytics 15 Semester 1 Postgraduate Taught Level 7 Glen Martin Unit coordinator 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 <div style="border:1.0pt solid windowtext;mso-border-alt:solid windowtext .5pt;mso-element:para-border-div;padding:1.0pt 6.0pt 1.0pt 4.0pt;">The unit aims to provide students with an understanding of techniques in statistical modelling and inference that allow a deeper insight into health data. The unit will develop student’s literacy in the strengths, characteristics and correct application of modelling techniques, and how to interpret results. On completion, students will also be able to implement analyses in an appropriate scripting language. In addition, the unit will develop student’s ability to critically appraise literature that describe previously implemented methods to address healthcare problems. <o:p></o:p></div> <div style="border:1.0pt solid windowtext;mso-border-alt:solid windowtext .5pt;mso-element:para-border-div;padding:1.0pt 6.0pt 1.0pt 4.0pt;">The health sector is rich with data that currently remains under-utilised.  A key component of the skill set of a health data scientist or health informatician is to be able to plan, implement and interpret analyses using a suite of modelling and statistical inference methods of such data. This unit will introduce approaches and frameworks for planning analyses of health data – including writing Statistical Analysis Plans (SAPs). The unit will provide introductions to a range of commonly applied analytical methods, such as regression, including understanding when such techniques are appropriate, and interpretating the output from these analyses. We will cover techniques for both prediction and addressing causal hypotheses, including simulation. Consideration of emerging analytical infrastructure, such as secure data environments, will be overviewed. The unit will be application-driven, with case-studies and examples drawn from health research across the University of Manchester and beyond.The unit will be split into three sections, covering the following topics:Section 1 (Modelling Methods)<o:p></o:p>Recap of sampling, sampling error and linear regression<o:p></o:p>Data Wrangling and Cleaning<o:p></o:p>Describe the use of generalised linear models and survival analysis <o:p></o:p>Introduction to causal analysis (DAGs, confounders, simulation, and methods for causal analysis in observational data)Section 2 (Analysis Plans)<o:p></o:p>Statistical Analysis Plans<o:p></o:p>Critical appraisal of published literature<o:p></o:p>Ethical considerations of analysis (e.g., statical disclosure control, fairness/sample representation)Section 3 (Emerging Analytical Workflows)<o:p></o:p>Secure Data Environments/Trustworthy Research Environments<o:p></o:p>Federated Analysis/ Meta-Analysis<o:p></o:p></div> <div style="border:1.0pt solid windowtext;mso-border-alt:solid windowtext .5pt;mso-element:para-border-div;padding:1.0pt 6.0pt 1.0pt 4.0pt;">The unit aims to provide students with an understanding of techniques in statistical modelling and inference that allow a deeper insight into health data. The unit will develop student’s literacy in the strengths, characteristics and correct application of modelling techniques, and how to interpret results. On completion, students will also be able to implement analyses in an appropriate scripting language. In addition, the unit will develop student’s ability to critically appraise literature that describe previously implemented methods to address healthcare problems. <o:p></o:p></div>  A1: Explain, discuss and interpret modelling and causal inference techniques and appraise their application in healthcare<o:p></o:p>A2: Appraise the strengths and weakness of modelling methods, and the appropriateness of a given method to a given analytical question.<o:p></o:p>A3: Discuss the advantages and disadvantages of emerging analytical workflows, including specifical analytical considered that are required.<o:p></o:p>A4: Consider ethical considerations of analysis of health data<o:p></o:p>  B1: Critically appraise literature that uses statistical methods for health data<o:p></o:p>B2: Assess the appropriateness of a modelling tool or technique of a given research question<o:p></o:p>B3: Apply modelling techniques and methods to healthcare data<o:p></o:p>B4: Interpret analytical results  C1:  Design and write scripts to implement statistical methods to analyse health data<o:p></o:p>C2: Write analytical plans into a statistical analysis plan<o:p></o:p> D1: Communicate and write analytical methods based on completed work and available literature in this area<o:p></o:p>D2: Develop problem solving skills<o:p></o:p>D3: Demonstrate a critical understanding of technical descriptions of statistical/mathematical analysis methods 2 Written assignment (inc essay) 60% 7 Oral assessment/presentation 40% Group-based project: <o:p></o:p>Groups will be assigned a health-related research area (e.g., diabetes, cancer, infections) and will work together to design the integration of various data types and sources to answer a key research question. To present in a dragons-den style of proposed project to the class, with a 5-minute Q&A session. Individual written report: <o:p></o:p>Students will be given a dataset relevant for the health-related question that they worked on in their group-based project. Using the plans developed in the group assessment (adapting where needed based on feedback), students will analyse the data to answer their assigned research question, before writing their findings into an individual report. The report will consist of summary of methods (400 words), and results/conclusion (800 words), and conclusion (300 words). <o:p></o:p><o:p></o:p> N 0 0 0