NETIMIS: Dynamic Simulation of Health Economics Outcomes Using Big Data

Netimis

Owen Johnson, Director of X-Lab and Senior Fellow at the University of Leeds, has published an article for the PharmacoEconomics Journal. The article describes how NETIMIS can be utilised to generate ideas and evaluate healthcare scenarios. (For more information on the PharmacoEconomics Journal please see here: http://link.springer.com/journal/40273)

The article abstract is available below:

“Many healthcare organizations are now making good use of electronic health record (EHR) systems to record clinical information about their patients and the details of their healthcare. Electronic data in EHRs is generated by people engaged in complex processes within complex environments, and their human input, albeit shaped by computer systems, is compromised by many human factors. These data are potentially valuable to health economists and outcomes researchers but are sufficiently large and complex enough to be considered part of the new frontier of ‘big data’. This paper describes emerging methods that draw together data mining, process modelling, activity- based costing and dynamic simulation models.

Our research infrastructure includes safe links to Leeds hospital’s EHRs with 3 million secondary and tertiary care patients. We created a multidisciplinary team of health economists, clinical specialists, and data and computer scientists, and developed a dynamic simulation tool called NETIMIS (Network Tools for Intervention Modelling with Intelligent Simulation; http://​www.​netimis.​com) suitable for visualization of both human-designed and data-mined processes which can then be used for ‘what-if’ analysis by stakeholders interested in costing, designing and evaluating healthcare interventions. We present two examples of model development to illustrate how dynamic simulation can be informed by big data from an EHR. We found the tool provided a focal point for multidisciplinary team work to help them iteratively and collaboratively ‘deep dive’ into big data.”

(For the full article please see: http://link.springer.com/article/10.1007/s40273-015-0330-7 )