City Research Online

Evidence based policy making in healthcare using big data analytics

Prasinos, M. (2019). Evidence based policy making in healthcare using big data analytics. (Unpublished Doctoral thesis, City, University of London)


The effective management of various health conditions depends on and requires appropriate public health policies (PHP). Public health policy can affect several aspects of healthcare provision including: (a) prevention and early diagnosis of diseases; (b) early treatment of diagnosed conditions through the provision of appropriate health care devices; (c) longer term treatment of long term disabilities and chronic diseases through systematic checks of the patient’s condition and the provision of other vital rehabilitation related services; (d) protection of people with health care devices from the harmful effects of their living environment; (e) setup of standards, services and technology for promoting and ensuring patients’ participation and inclusion within various settings (e.g., at work, at school/educational establishments, in everyday life). Although there is a need for evidence based public health policy making, there is currently no computerised tool to enable the process.

The overall aim of our research is to develop an integrated platform by incorporating a big data analytics (BDA) platform that facilitates the collection and analysis of heterogeneous data related to healthcare services, including health care device usage, physiological, cognitive, medical, personal, occupational, behavioural, lifestyle, environmental and open web data. For the purposes of the development of this integrated platform we are introducing a Public Health Policy Decision Making modeling language that allows the specification of models that are executable by the platform.

For the evaluation of the developed platform, we developed a scenario, instantiated the ontology model using Protégé and generated synthetic data. We also ran the scenario using real patient data from EVOTION project. We performed subjective evaluation of the platform as a policy making tool using three questionnaires (one for policy makers, one for clinicians and one for data analysts) and analysed the results.

The novelty of this thesis lies not only in the specification of the PHPDM modeling language, as there is no other ontology on public health policy decision making, but also in the development of the BDA engine and the prototype, as there is no other similar policy making platform to date.

Some open issues regarding the developed platform include (a) further formalization and addition of new constructs to the developed PHPDM specification language to support the full lifecycle of policy formation processes, (b) the provision of templates, Evidence Based Policy Making in Healthcare using Big Data Analytics guidelines and supportive material (e.g. tooltips in the interface and tutorial videos) to help policy makers specify data analytics workflows and criteria, (c) interoperability with other data analytics tools and existing health data repositories, (d) the provision of the developed platform as a service, (e) the implementation of more data mining and statistical analysis algorithms and (f) the development of a decision support system that will enable the platform to not only support the execution of big data analytics, but to also directly support the policy making process.

Publication Type: Thesis (Doctoral)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: Doctoral Theses
School of Science & Technology > School of Science & Technology Doctoral Theses
School of Science & Technology > Computer Science
[thumbnail of Prasinos, Marios_vols merged_Redacted.pdf]
Text - Accepted Version
Download (8MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login