Process mining for healthcare: Characteristics and challenges.

Process mining techniques can be used to analyse business processes using the data logged during their execution. These techniques are leveraged in a wide range of domains, including healthcare, where it focuses mainly on the analysis of diagnostic, treatment, and organisational processes. Despite the huge amount of data generated in hospitals by staff and machinery involved in healthcare processes, there is no evidence of a systematic uptake of process mining beyond targeted case studies in a research context. When developing and using process mining in healthcare, distinguishing characteristics of healthcare processes such as their variability and patient-centred focus require targeted attention. Against this background, the Process-Oriented Data Science in Healthcare Alliance has been established to propagate the research and application of techniques targeting the data-driven improvement of healthcare processes. This paper, an initiative of the alliance, presents the distinguishing characteristics of the healthcare domain that need to be considered to successfully use process mining, as well as open challenges that need to be addressed by the community in the future.

Revealing Work Practices in Hospitals Using Process Mining.

In order to improve health care processes (both in terms of quality and efficiency), we do need insight into how these processes are actually executed in reality. Interviewing health personnel and observing them in their work, are proven field-work techniques for gaining this insight. In this paper, we will introduce a complementary technique. This technique, called process mining, is based on the automatic analysis of digital events, registered in different information systems that support clinical work. Based on an event log, process mining can help in constructing a model of the process (discovery) or with checking to which extend an actual process confirms to a prescriptive model of it (conformance). This paper will briefly discuss two examples, which illustrate the use of process mining.

Coping with the unforeseen in surgical work.

OBJECTIVE: The purpose of this study was to investigate how staff working in the perioperative domain copes with unforeseen events and in what way, if at all; they are supported in this by formal systems such as information systems. DESIGN: Case study. We conducted our study in the Department of Surgery in a large academic hospital in Norway. The department consists of eight operating rooms for planned surgery. The study included observations and interviews, in addition to one design workshop with health personnel. We focused on planned surgery. RESULTS: Our observations showed that unforeseen events that cause deviations from plans are characteristic and that staff apply different coping strategies to make the plan work regardless. Support of these coping strategies by formal systems is poor. DISCUSSION: We used the concept of high-reliability organisations as proposed by Weick and Sutcliffe, 2007, to analyse the observed coping strategies. The coping strategies can be seen as examples of the principles for managing the unexpected that Weick and Sutcliffe propose. IT support for this must include both awareness-creating systems and systems that enable workers to control the effects of unforeseen events once they have occurred.

Visualizing patient trajectories on wall-mounted boards - information security challenges.

Since operating room departments are among the costliest resources at a hospital, much attention is devoted to maximize their utilization. Operating room activities are however notoriously hard to plan in advance. This has to do with the unpredictable, problem-solving nature of the work and that the work is carried out by a multidisciplinary team of health personnel, members of which also have commitments outside the operating room department. We assume that operating room teams have the capacity to coordinate themselves and that coordination might be facilitated by visualizing relevant information on wall-mounted boards. To characterize clinical situations that require coordination and re-planning of the teams' work, we have developed a realistic scenario. We analyse and discuss the information security challenges that follow from displaying information on the whereabouts of other teams, actors and patients on wall-mounted boards in the operating rooms. Information security threats could be mitigated by de-identification techniques. Information demands could thereby be met without sacrificing the privacy of those whose information is displayed.

Effectiveness of the introduction of an International Classification of Functioning, Disability and Health-based rehabilitation tool in multidisciplinary team care in patients with rheumatoid arthritis.

OBJECTIVE: To investigate whether the use of an International Classification of Functioning, Disability and Health (ICF)-based instrument to structure multidisciplinary care improves clinical effectiveness and satisfaction in patients with rheumatoid arthritis (RA) admitted for multidisciplinary team care. METHODS: Consecutive patients with RA admitted to an inpatient or day patient multidisciplinary team care ward were included during a 12-month period before (period I) and after (period II) the introduction of an ICF-based rehabilitation tool (Rehabilitation Activities Profile [RAP]). Patients were assessed at admission, discharge, and 6 weeks thereafter. The primary outcome measure was a patient-oriented measure of functional ability (McMaster Toronto Arthritis Patient Preference Disability Questionnaire [MACTAR]), whereas secondary outcome measures included measures of physical and mental functioning, quality of life, disease activity, and patient satisfaction. Change scores between periods were compared using analysis of covariance. RESULTS: A total of 80 and 85 patients were included in periods I and II, respectively. Concerning the improvement of the MACTAR score and all other secondary clinical outcome measures, there was no significant difference between the 2 periods. Patient satisfaction with care was slightly higher in period II than in period I, with the differences regarding the total score of a multidimensional satisfaction questionnaire and the domains focusing on individual problems and empathy reaching statistical significance. CONCLUSION: The introduction of the RAP did not change clinical effectiveness but had a modest beneficial impact on patient satisfaction with care in patients with RA admitted for multidisciplinary team care.

Experimenting with Case-Based Reasoning to Present Educative Health Information on the Internet: The Example of SeniorGezond.

BACKGROUND: Information about health prevention can contribute to the awareness and the knowledge of consumers and patients about their own health. Messages originating from other users (cases) can be perceived as more credible and hence more persuasive. With this in mind, we have developed an informative website called SeniorGezond, which includes a case-based tailoring component, in the domain area of fall incidences. OBJECTIVES: To investigate whether the use of cases is suitable for presenting and tailoring educative health information; and to gain insights in the user's opinion about the use of cases to provide tailored preventive information. METHODS: We conducted a qualitative study using questionnaires, focus group discussions, interviews, and observations. Participants were elderly, family caregivers and healthcare professionals. RESULTS: Users were able to find relevant cases for their problems, but had a mixed reaction on the usefulness and appreciation of the cases. CONCLUSIONS: There is a need for a delicate balance between a recognizable story with all the important health information and good readable and concise information. A good text structure is required to support this. While cases do have potential in health education, further research is needed in order to identify the necessary requirements which will make the cases successful.