Graph Network Techniques to Model and Analyze Emergency Department Patient Flow

Reychav, Iris; McHaney, Roger; Babbar, Sunil; Weragalaarachchi, Krishanthi; Azaizah, Nadeem; Nevet, Alon

doi:10.3390/math10091526

Cited by 4 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Degree and assortativity were chosen by Liljeros, Giesecke, and Holme (2007) to represent the number of contacts between patients as they moved between care facilities. A time varying graph approach was employed by Reychav et al (2022) to assess emergency department flow by measurement of the path length to determine the sequence of care activities. Degree centrality and weighted degree centrality were then used to assess the activity and the time spent at each stage of the care process.…”

Section: Patient Flowmentioning

confidence: 99%

See 1 more Smart Citation

Understanding health system operation using networks: A literature review

Manzi¹

2023

Preprint

View full text Add to dashboard Cite

Network analysis has been identified as an important approach for understanding and improving large scale health system operations. This review sought to understand the existing ways in which network analysis has been applied to health system operations by assessing; the topic areas, entity interaction types, network metrics used to describe system operations, the real world correlates of those network metrics and appraise the current and future trends in this area.The review included 52 articles identified using a snowball sampling method. Theanalysis showed that ’Care coordination’ was the most common topic topic area. The networks were most often constructed using patient level data describing care collaboration, patient transfers, physician collaboration and patient referrals. Measures of connectedness were most often applied such as density, centrality measures and degree. These measures were used to describe collaboration between clinicians and organisations, assess resource requirements and assess how patients were moving through the health system.The majority of the studies reported in the literature present descriptive studies of health system operations. Future work in this area should focus on using network analysis for predictive purposes e.g. forecasting and simulation parameterisation. There is also great potential in the use of dynamic network analysis to assess trendsin system operations over time.

show abstract

Section: Patient Flowmentioning

confidence: 99%

“…The evolution of network structures over time is an emerging trend in the field such as the time varying graph (TVG) approach used by Reychav et al (2022). proposed a framework for measuring changes to nodes in a network using the term longitudinal network analysis.…”

Section: Summary Of Key Findingsmentioning

confidence: 99%

Understanding health system operation using networks: A literature review

Manzi¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

Leveraging graph neural networks for supporting automatic triage of patients

Defilippo,

Veltri,

Lió

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Patient triage is crucial in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency-level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. A growing interest has recently been focused on leveraging artificial intelligence (AI) to develop algorithms to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI-based module to manage patients’ emergency code assignments in emergency departments. It uses historical data from the emergency department to train the medical decision-making process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method, we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

show abstract