Building artificial intelligence and machine learning models : a primer for emergency physicians.

There has been a rise in the number of studies relating to the role of artificial intelligence (AI) in healthcare. Its potential in Emergency Medicine (EM) has been explored in recent years with operational, predictive, diagnostic and prognostic emergency department (ED) implementations being developed. For EM researchers building models de novo, collaborative working with data scientists is invaluable throughout the process. Synergism and understanding between domain (EM) and data experts increases the likelihood of realising a successful real-world model. Our linked manuscript provided a conceptual framework (including a glossary of AI terms) to support clinicians in interpreting AI research. The aim of this paper is to supplement that framework by exploring the key issues for clinicians and researchers to consider in the process of developing an AI model.

Discrete Event Simulation-Based Resource Modelling in Health Technology Assessment.

OBJECTIVE: The objective of this article was to conduct a systematic review of published research on the use of discrete event simulation (DES) for resource modelling (RM) in health technology assessment (HTA). RM is broadly defined as incorporating and measuring effects of constraints on physical resources (e.g. beds, doctors, nurses) in HTA models. METHODS: Systematic literature searches were conducted in academic databases (JSTOR, SAGE, SPRINGER, SCOPUS, IEEE, Science Direct, PubMed, EMBASE) and grey literature (Google Scholar, NHS journal library), enhanced by manual searchers (i.e. reference list checking, citation searching and hand-searching techniques). RESULTS: The search strategy yielded 4117 potentially relevant citations. Following the screening and manual searches, ten articles were included. Reviewing these articles provided insights into the applications of RM: firstly, different types of economic analyses, model settings, RM and cost-effectiveness analysis (CEA) outcomes were identified. Secondly, variation in the characteristics of the constraints such as types and nature of constraints and sources of data for the constraints were identified. Thirdly, it was found that including the effects of constraints caused the CEA results to change in these articles. CONCLUSION: The review found that DES proved to be an effective technique for RM but there were only a small number of studies applied in HTA. However, these studies showed the important consequences of modelling physical constraints and point to the need for a framework to be developed to guide future applications of this approach.

Simulation Modelling in Healthcare: An Umbrella Review of Systematic Literature Reviews.

BACKGROUND: Numerous studies examine simulation modelling in healthcare. These studies present a bewildering array of simulation techniques and applications, making it challenging to characterise the literature. OBJECTIVE: The aim of this paper is to provide an overview of the level of activity of simulation modelling in healthcare and the key themes. METHODS: We performed an umbrella review of systematic literature reviews of simulation modelling in healthcare. Searches were conducted of academic databases (JSTOR, Scopus, PubMed, IEEE, SAGE, ACM, Wiley Online Library, ScienceDirect) and grey literature sources, enhanced by citation searches. The articles were included if they performed a systematic review of simulation modelling techniques in healthcare. After quality assessment of all included articles, data were extracted on numbers of studies included in each review, types of applications, techniques used for simulation modelling, data sources and simulation software. RESULTS: The search strategy yielded a total of 117 potential articles. Following sifting, 37 heterogeneous reviews were included. Most reviews achieved moderate quality rating on a modified AMSTAR (A Measurement Tool used to Assess systematic Reviews) checklist. All the review articles described the types of applications used for simulation modelling; 15 reviews described techniques used for simulation modelling; three reviews described data sources used for simulation modelling; and six reviews described software used for simulation modelling. The remaining reviews either did not report or did not provide enough detail for the data to be extracted. CONCLUSION: Simulation modelling techniques have been used for a wide range of applications in healthcare, with a variety of software tools and data sources. The number of reviews published in recent years suggest an increased interest in simulation modelling in healthcare.