Process Mining in Healthcare
Permanent URI for this collectionhttps://hdl.handle.net/10125/107487
Browse
Recent Submissions
Item type: Item , Process Mining Using Electronic Health Records Data - Quo Vadis? Reflections from Observing Nurses' Activities and Data Registration Behavior(2024-01-03) Martin, Niels; Gielen, Isabeau; Bergs, JochenProcess mining leverages process execution data to better understand and improve operational processes. In hospitals, data from the Electronic Health Records (EHR) system that supports their daily operations is often used as input data for process mining. As limitations of EHR data in terms of data quality have also been highlighted in literature, it remains an open question how well EHR data reflects how work actually gets done in a care process. Against this background, this paper reports on the outcomes of an observation study at a Belgian hospital. In particular, the activities that nurses perform have been observed, as well as their data registration behavior. From the findings, it follows that EHR data will provide a highly fragmented and inaccurate view of how nursing work gets done. This constitutes a basis for reflection upon the extent to which EHR data is a truthful basis for process mining.Item type: Item , Care records and healthcare processes: adding context to clinical codes(2024-01-03) Chammas, Lara; Dwyer, Owen; Sallinger, Emanuel; Davies, Jim; Morris, Eva JaProcess mining techniques are being used to explore healthcare processes based upon information recorded about individual patients. In most cases, this information consists of clinical codes and dates: codes used to classify care events; dates indicating when these events occurred. These codes will not, in general, form part of the contemporaneous care record used by clinicians. At the same time, that record contains other, more detailed information about the care delivered. This paper explains how the provenance of coded information can affect its interpretation and how information from a care record can be used to stratify patient populations and provide context for process mining. The proposed methodology is illustrated through application to real-world data in an area of particular concern: the treatment and care of patients with colon cancer.Item type: Item , Whetting the SWORD: Detecting Workarounds by Using Active Learning and Logistic Regression(2024-01-03) Van Der Waal, Wouter; Weerd, Inge; Haitjema, Saskia; Kappen, Teus; Alexander Reijers, HajoIn many organizations, especially in healthcare, workers may work around prescribed procedures. Detecting these workarounds can give insights into difficulties concerning the procedures, which in turn can be used to improve them. Previous studies have shown that workarounds may be discovered from an event log using a set of predefined patterns such as the duration of a trace or the number of resources involved in one. However, domain experts may find it difficult to evaluate and monitor results if there are multiple patterns that indicate workarounds. Training a model that merges the features is often difficult because there are no available datasets covering workarounds. Labeling traces generally requires a lot of time from domain experts. In addition, this would have to be repeated for every new domain, company, or even department since the types of workarounds that occur may differ strongly between them. In this work, we propose to combine the features using a Logistic Regression model and train through Active Learning. In a case study at a hospital, we find that after training the model on only 10 to 15 traces, it stabilizes with an approximate F1 score of .75. This shows that we create and train a model that can detect workarounds well without requiring a large amount of labeled data or a lot of time from a domain expert.Item type: Item , Introduction to the Minitrack on Process Mining in Healthcare(2024-01-03) Martin, Niels; Weske, Mathias; Pufahl, Luise