Applied Health Data Analytics

Details

Title

Applied Health Data Analytics

Type

Stage Two

Module code

HBI122

Requirement

Compulsory

Module objective

There is a wealth of health data available that can now be analysed in order to operationalise standard, effective healthcare practices, learn about patient populations, enhance preventative care and drive business decisions that will lead to quality improvement and increased patient safety. Ultimately, data analysis is required to inform evidence- based decision making and this module will develop basic skills in Health Informatics into expertise: identifying and using data sources (including electronic patient records, health geography data, public health data and non-health data collected for health purposes, such as global positioning, accelerometers and wearable devices), knowing when and how to use data analytical techniques, what the information is needed for, and how to clearly communicate analysis results and information. Expertise also consists of an understanding of cutting-edge technologies and methods that are likely to lead the way for the future of Health Informatics.

By the end of this module the Clinical Scientist in HSST will be able to apply advanced analytics appropriately to a range of healthcare science, biomedical, social, behavioural and wellbeing data to inform decision making. This will require an expert understanding of the strengths and limitations of advanced analytics to this range of biomedical data used in clinical support systems, monitoring, audit, evaluation and scenario modelling.

They will be responsible for their own working practice and the appropriate (ethical and professional) handling of the level and type of data that they work with, and will consistently demonstrate the attitudes and behaviours necessary for the role of a CCS.

Knowledge and understanding

By the end of this module the Clinical Scientist in HSST will be able to analyse, synthesise, evaluate and critically apply their expert knowledge of advanced health data analysis methodologies to support and influence key healthcare practice and delivery decisions and evaluate the impact these have on the patient, including:

Clinical support systems

• How to identify patient pathway components that cause/result in negative patient experiences.

Monitoring

• How to identify blockages/attrition in patient pathways or supply chains.
• How to determine which services/drugs are over/under-used.
• How to identify disease patterns, outbreaks or adverse events.
• How to map health profiles of communities, through direct and indirect factors that affect health (e.g.,socio-demographic factors, health behaviours and policies.

Audit

• How to identify non-adherence to recommended practice.
• How to identify areas that need service delivery improvement.

Evaluation

• How to appraise the effectiveness of a programme, including how it is delivered and how it affects different populations, scenario modelling and research.
• The costs and benefits of changing a service/programme; what is likely to happen in the future.

Clinical trials

• How to design and evaluate the comparative effectiveness of a randomised trial under different clinical strategies.

Data and methodologies

• Data analysis steps, and strengths and limitations of study designs and methods, including simple pragmatic trials and observational studies.
• How to evaluate types and scope of data sources, such as: genotype information; patient-reported outcomes; health geography data; mobile health data; public health data; surveillance data; and electronic health records,
• Measurements of data quality.
• The application of data analytics methods and programming modules, including regression analysis, machine learning, predictive analytics, natural-language processing and forecasting to a range of scenarios such as modelling patient pathways and disease progression, identification of gaps in evidence (also see above).
• When and how to apply appropriate methods for analysis with a thorough understanding of the strengths and limitations of each.

Visualisation and communication strategies

• The application of data visualisation techniques and software to communicate data analyses and information (e.g., geographical information systems)
• How to represent data and information to support clinical, operational, public health and management decision making, for example determining outbreak detection.

Technical and clinical skills

By the end of this module the Clinical Scientist in HSST will have a critical understanding of current evidence and its application to the performance and mastery of a range of technical skills and will be able to apply analytical skills to a range of data to assist in decision making that impacts on individuals, practice and population. In particular they will be able to:

• Identify appropriate health data sources across the system to be able to perform complex analysis.
• Identify and use appropriate tools and methods to perform and direct analysis of data, and build models that can predict clinical, operational, public health and managerial outcomes (e.g. prognosis of disease in patients).
• Lead complex health data analyses and be able to prepare, present and communicate recommendations to a range of stakeholders, including, for example, board-level executives and clinicians.
• Adopt and adapt statistical/mathematical methodologies from other disciplines to analyse complex health data.
• Choose appropriate software and design appropriate data visualisations for a range of stakeholders, including patients, board members, public health professionals and clinicians.
• Design a health analytics strategy that will lead to the development or improvement of the delivery of a healthcare system along the clinical pathway.
• Choose, perform and direct analyses that will contribute to the redesign of a clinical pathway and present results back to the pathway stakeholders.

By the end of this module the Clinical Scientist in HSST will be expected to critically reflect and apply in practice a range of clinical and communication skills and will be able to:

• Critically review a scientific protocol or publication for the validity of analytical methods.
• Contribute to the discussion at multidisciplinary and board meetings, including justifying methodologies and interpretation of analyses.
• Describe in clear language that is accessible to other Clinical Scientists from other domains, clinicians, laboratory managers and senior management (among others) clinical, operational and informatics consequences of analyses and justify the evidence from health informatics analyses used to inform conclusions.
• Promote evidence-based developments in service delivery that enable patients to have improved and safer access to information about their care.
• Write peer-reviewed reports/publications (include data visualisation) detailing an analysis and provide interpretation, recommend action and evaluation methods.
• Synthesise complex information and communicate to others about a health data analysis so that they can reflect and learn from this.
• Provide consultant-level clinical scientific advice, including interpretation of health informatics data and developments.
• Recognise the potential impact of health informatics developments on patients/populations/services and their implications for patient care, patient safety and management, and recommendations for additional or more complex data collection and analysis.
• Critically reflect on the challenges of applying research to practice in relation to these areas of practice and suggest improvements, building on a critique of available evidence.

Professional practice

The Clinical Scientist in HSST will:

• Critically reflect and apply in practice a range of clinical and communication skills as they work in partnership with the public, patients, clinicians, academics and other healthcare professionals.
• Critically analyse the practice of Health Informatics, ensuring that regular review of research and evidence is undertaken so that adaptation to practice can be made in a timely and cost-effective manner.
• Protect research data on conclusion of the project in order to defend any relevant publication and/or challenge to the research findings.