Incorporating Topic Assignment Constraint and Topic Correlation Limitation into Clinical Goal Discovering for Clinical Pathway Mining

Abstract

Clinical pathways are widely used around the world for providing quality medical treatment and controlling healthcare cost. However, the expert-designed clinical pathways can hardly deal with the variances among hospitals and patients. It calls for more dynamic and adaptive process, which is derived from various clinical data. Topic-based clinical pathway mining is an effective approach to discover a concise process model. Through this approach, the latent topics found by latent Dirichlet allocation (LDA) represent the clinical goals. And process mining methods are used to extract the temporal relations between these topics. However, the topic quality is usually not desirable due to the low performance of the LDA in clinical data. In this paper, we incorporate topic assignment constraint and topic correlation limitation into the LDA to enhance the ability of discovering high-quality topics. Two real-world datasets are used to evaluate the proposed method. The results show that the topics discovered by our method are with higher coherence, informativeness, and coverage than the original LDA. These quality topics are suitable to represent the clinical goals. Also, we illustrate that our method is effective in generating a comprehensive topic-based clinical pathway model.

Process mining applications in the healthcare domain: A comprehensive review

“…TM can be implemented with the R library topicmodels. Among the surveyed papers, those that adopted the TM approach are (Huang et al, 2014;Stefanini et al, 2016;Xu et al, 2017;Prokofyeva and Zaytsev, 2020;Chiudinelli et al, 2020).…”

“…Besides (Chiudinelli et al, 2020); Huang et al, 2014); Prokofyeva and Zaytsev, 2020), where authors applied TM on medical event logs, X. Xu et al (2017) used billing data as the reflection of medical behaviors, and used LDA to organize billing items into high-granularity topics. They start from the assumption that billing items used for patient are goal-oriented, and thus different items that occurred in 1 day represent the day goals.…”

“…Stefanini et al, 2016;Valero-Ramon et al, 2019;X. Xu et al, 2017;Lee & Rismanchian, 2018;Zhang & Chen, 2012; Automated with clustering (deToledo et al, 2019;Delias et al, 2014Delias et al, , 2015Huang et al, 2014;Kovalchuk et al, 2018;Lakshmanan et al, 2013;Lismont et al, 2016;Najjar et al, 2018;Pebesma et al, 2019;Prokofyeva & Zaytsev, 2020;Ronny et al, 2015;Lu et al, 2019;S.…”

Variance Analysis and Handling of Clinical Pathway: An Overview of the State of Knowledge

“…Results based on the text mining method indicate that the existing research of clinical pathway variance include the monitoring and prediction of clinical pathway variance based on electronic medical records, and the handling of clinical pathway variance through process analysis. Compared with the clinical pathway designed by experts, data-driven execution clinical pathway is more objective, convenient to design, implement and detect variation of clinical pathway [76], [77]. Several studies analyzed and managed clinical pathway variance based on semantic web technologies, process mining, data mining and ECA modeling.…”

A Knowledge Management System for the Variation in Regional Clinical Pathways of Traditional Chinese Medicine Based on Smart Cloud Services

“…The variation law of the TCM CPs could be discovered by mining the objective indices (e.g. gender, age, drug dosage, and nursing grade) of data sources like hospital information system (HIS) [13] and electronic medical records (EMR), laying the basis for early warning of the variation [14][15][16]. Nevertheless, there is little report on the knowledge management of the variation in the TCM CPs from the regional perspective.…”