Finding clusters of similar events within clinical incident reports: a novel methodology combining case based reasoning and information retrieval

Tsatsoulis, Costas; Amthauer, Heather

doi:10.1136/qhc.12.suppl_2.ii24

Cited by 9 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kyung-Sup and Ingoo ( 2001) describe the method of clustering linking with CBR but not in the usage of production processes and in the risk prediction. Tsatsoulis and Amthauer (2003) use this tool to medical database. Oyelade et al (2010) suggest the usage of basic algorithm of sharp division into k clusters, called k-means, developed from 1956 (Steinhaus, 1956).…”

Section: Clustering Risk Assessment Methodsmentioning

confidence: 99%

Clustering risk assessment method for shipbuilding industry

Iwańkowicz

Rosochacki

2014

Industrial Management &Amp; Data Systems

View full text Add to dashboard Cite

Purpose – The purpose of this paper is to develop a risk assessment method for production processes of large-size steel ship hulls. Design/methodology/approach – This study uses a quantitative-probabilistic approach with involvement of clustering technique in order to analyse the database of accidents and predict the process risk. The case-based reasoning is used in here. A set of technological hazard classes as a basis for analysing the similarities between the production processes is proposed. The method has been explained using a case study on large-size shipyard. Findings – Statistical and clustering approach ensures effective risk managing in shipbuilding process designing. Results show that by selection of adequate number of clusters in the database, the quality of predictions can be controlled. Research limitations/implications – The suggested k-means method using the Euclidean distance measure is initial approach. Testing the other distance measures and consideration of fuzzy clustering method is desirable in the future. The analysis in the case study is simplified. The use of the method according to prediction of risk related to loss of health or life among people exposed to the hazards is presented. Practical implications – The risk index allows to compare the processes in terms of security, as well as provide significant information at the technology design stage of production task. Originality/value – There are no studies on quantitative methods developed specifically for managing risks in shipbuilding processes. Proposed list of technological hazard classes allows to utilize database of past processes accidents in risk prediction. The clustering method of analysing the database is agile thanks to the number of clusters parameter. The case study basing on actual data from the real shipyard constitutes additional value of the paper.

show abstract

Section: Clustering Risk Assessment Methodsmentioning

confidence: 99%

Clustering risk assessment method for shipbuilding industry

Iwańkowicz

Rosochacki

2014

Industrial Management &Amp; Data Systems

View full text Add to dashboard Cite

show abstract

“…Novel information retrieval methods, such as natural language processing (NLP), when applied to electronic health records (EHRs) have demonstrated underreporting by clinicians and the potential to improve detection. [80][81][82] Alternatively, Roubinian et al 83 and Nguyen et al 84 incorporated novel biomarkers into classification models and decision tree analysis, respectively. While the focus of ML is on prediction, and a causal relationship cannot be assumed of the covariates found to have high predictive value, identification of novel risk factors for hypothesis generation and further research can be useful as seen in transfusion-associated lung injury (TRALI) 85 and in pediatric transfusion-associated hyperkalemia.…”

Section: Hemovigilancementioning

confidence: 99%

Machine learning in transfusion medicine: A scoping review

Maynard,

Farrington,

Alimam

et al. 2023

Transfusion

View full text Add to dashboard Cite

“…CBR research recognized accident reports as reusable experiences, and a special workshop challenge about analysing air investigation reports was organized as a part of the 4th Workshop on Textual case-based Reasoning in 2007 [6]. Accident reports were used by CBR researchers also before this workshop [11,10,22,9]. Much of these work combines CBR with information retrieval and focuses on the retrieval stage of the CBR cycle.…”

Section: Introductionmentioning

confidence: 99%

Acquisition and Reuse of Reasoning Knowledge from Textual Cases for Automated Analysis

Sizov

Öztürk

Styrak

2014

Case-Based Reasoning Research and Development

View full text Add to dashboard Cite

Abstract. Analysis is essential for solving complex problems such as diagnosing a patient, investigating an accident or predicting the outcome of a legal case. It is a non-trivial process even for human experts. To assist experts in this process we propose a CBR-based approach for automated problem analysis. In this approach a new problem is analysed by reusing reasoning knowledge from the analysis of a similar problem. To avoid the laborious process of manual case acquisition, the reasoning knowledge is extracted automatically from text and captured in a graphbased representation, which we dubbed Text Reasoning Graph (TRG), that consists of causal, entailment and paraphrase relations. The reuse procedure involves adaptation of a similar past analysis to a new problem by finding paths in TRG that connect the evidence in the new problem to conclusions of the past analysis. The objective is to generate the best explanation of how the new evidence connects to the conclusion. For evaluation, we built a system for analysing aircraft accidents based on the collection of aviation investigation reports. The evaluation results show that our reuse method increases the precision of the retrieved conclusions.

show abstract

Finding clusters of similar events within clinical incident reports: a novel methodology combining case based reasoning and information retrieval

Cited by 9 publications

References 3 publications

Clustering risk assessment method for shipbuilding industry

Clustering risk assessment method for shipbuilding industry

Machine learning in transfusion medicine: A scoping review

Acquisition and Reuse of Reasoning Knowledge from Textual Cases for Automated Analysis

Contact Info

Product

Resources

About