Toward Value-Based Healthcare through Interactive Process Mining in Emergency Rooms: The Stroke Case

Abstract

The application of Value-based Healthcare requires not only the identification of key processes in the clinical domain but also an adequate analysis of the value chain delivered to the patient. Data Science and Big Data approaches are technologies that enable the creation of accurate systems that model reality. However, classical Data Mining techniques are presented by professionals as black boxes. This evokes a lack of trust in those techniques in the medical domain. Process Mining technologies are human-understandable Data Science tools that can fill this gap to support the application of Value-Based Healthcare in real domains. The aim of this paper is to perform an analysis of the ways in which Process Mining techniques can support health professionals in the application of Value-Based Technologies. For this purpose, we explored these techniques by analyzing emergency processes and applying the critical timing of Stroke treatment and a Question-Driven methodology. To demonstrate the possibilities of Process Mining in the characterization of the emergency process, we used a real log with 9046 emergency episodes from 2145 stroke patients that occurred from January 2010 to June 2017. Our results demonstrate how Process Mining technology can highlight the differences between the flow of stroke patients compared with that of other patients in an emergency. Further, we show that support for health professionals can be provided by improving their understanding of these techniques and enhancing the quality of care.

Dynamic Models Supporting Personalised Chronic Disease Management through Healthcare Sensors with Interactive Process Mining

“…If both situations, for a p -Value lower than a given threshold, it is concluded that the distributions are significantly different. Following the literature, the threshold was set to 0.05 [ 46 ].…”

“…This technique can be used to highlight the differences with statistical significance between the two models referring to two cohorts. This approach can not only discover when a process is different but also in which parts of the models the differences lie [ 46 ]. Figure 13 and Figure 14 show where processes for adult and young populations differ with respect to the elderly process.…”

“…It has been applied to the analysis of follow up protocols of patients with diabetes [ 35 , 53 ]; to measure and discover the individualised behaviour of older adults at risk of dementia [ 33 ]; for the characterisation of emergency flows, measuring organisational changes effects [ 46 ], for discovering surgery department flow [ 52 ], malnutrition assessment [ 49 ] or obesity characterisation [ 54 ]. PMApp also enables the creation of interactive dashboards that respond to the selection of arrows and nodes by capturing GUI events and it also allows the user to create custom forms and algorithms for discovery, filters, enhancement maps, and so forth [ 46 ]. On the other hand, to allow stratification based on the behavioural aspects of risk models, it is necessary to detect patients with different risk behaviours.…”

“…Although the use of Process Mining in healthcare is emergent, several works have shown the feasibility of applying Process Mining in this domain [ 43 ]. Process Mining techniques have been used for administrative analysis in health domains for specific illnesses [ 44 ], like gynaecological oncology [ 45 ], for the analysis of services like Emergencies [ 46 ], or even for modelling the human behaviour [ 33 ]. In Reference [ 47 ], there is a first attempt to characterise processes for the patient’s conduct with promising results.…”

Process Mining-Supported Emergency Room Process Performance Indicators

“…In addition, [ 16 ] proposed time-related indicators that focus on the elapsed time between two ER activities, such as triage and doctor seen. In addition to presenting indicators, there have been several applications with the ad-hoc approaches to understand ER processes [ 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. For example, [ 18 ] introduced an approach to evaluate the capabilities of process mining to the ER process on the stroke case, and [ 19 ] explored the effects of interactive process mining using the value-based technologies.…”