Using statistical models and case-based reasoning in claims prediction: experience from a real-world problem

Daengdej, Jirapun; Lukose, Dickson; Murison, R. D.

doi:10.1016/s0950-7051(99)00015-5

Cited by 22 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With sound results in applying CBR for problem-solving in the medical domain, several researchers argued that the chance of reusing a case from CBR is not high in some areas, such as insurance claims prediction [42] and multiple medical disorder cases [43]. Such a statement is also true in the domain of prescription support.…”

Section: Case-based Reasoning In Medical Prescriptionmentioning

confidence: 99%

A hybrid knowledge-based approach to supporting the medical prescription for general practitioners: Real case in a Hong Kong medical center

Ting

Kwok

Tsang

et al. 2011

Knowledge-Based Systems

View full text Add to dashboard Cite

ObjectiveWith the increased complexity and uncertainty in drug information, issuing medical prescriptions has become a vexing issue. As many as 240,000 medicines are available on the market, so this paper proposes a novel approach to the issuing of medical prescriptions. The proposed process will provide general practitioners (GPs) with medication advice and suggest a range of medicines for specific medical conditions by taking into consideration the collective pattern as well as the individual preferences of physicians' prescription decisions. Methods and MaterialA hybrid approach is described that uses a combination of case-based reasoning (CBR) and Bayesian reasoning. In the CBR process, all the previous knowledge retrieved via similarity measures is made available for the reference of physicians as to what medicines have been prescribed (to a particular patient) in the past. After obtaining the results from CBR, Bayesian reasoning is then applied to model the prescription experience of all physicians within the organization. By comparing the two sets of results, more refined recommendations on a range of medicines are suggested along with the ranking for each recommendation. ResultsTo validate the proposed approach, a Hong Kong medical center was selected as a testing site. Through application of the hybrid approach in the medical center for a period of one month, the results demonstrated that the approach produced satisfactory performance in terms of user satisfaction, ease of use, flexibility and effectiveness. In addition, the proposed approach yields better results and a faster learning rate than This is the Pre-Published Version. 2 when either CBR or Bayesian reasoning are applied alone. ConclusionEven with the help of a decision support system, the current approach to anticipating what drugs are to be prescribed is not flexible enough to cater for individual preferences of GPs, and provides little support for managing complex and dynamic changes in drug information. Therefore, with the increase in the amount of information about drugs, it is extremely difficult for physicians to write a good prescription. By integrating CBR and Bayesian reasoning, the general practitioners' prescription practices can be retrieved and compared with the collective prescription experience as modeled by probabilistic reasoning. As a result, physicians can select the drugs which are supported by informed evidential decisions. That is, they can take into consideration the pattern of decisions made by other physicians in similar cases.

show abstract

Section: Case-based Reasoning In Medical Prescriptionmentioning

confidence: 99%

A hybrid knowledge-based approach to supporting the medical prescription for general practitioners: Real case in a Hong Kong medical center

Ting

Kwok

Tsang

et al. 2011

Knowledge-Based Systems

View full text Add to dashboard Cite

show abstract

“…The CBR method is also considered as a MCDM method because it can support decision makers with candidate solutions to solve new problems [37][38][39][40]. Meanwhile the AHP method is "a theory of measurement through pairwise comparisons and relies on the judgments of experts to derive priority scales" [41].…”

Section: The Proposal: a Hybrid Cbr-ahp Methods Integrated Into An Emsmentioning

confidence: 99%

A CBR–AHP Hybrid Method to Support the Decision-Making Process in the Selection of Environmental Management Actions

et al. 2019

View full text Add to dashboard Cite

This paper proposes a hybrid method integrating case-based reasoning (CBR) and analytic hierarchy process (AHP) methods to reinforce the sustainable performance of an environmental management system. The CBR–AHP method aims to support the decision-making process to select environmental management actions (EMAs) aimed at reducing risky trends of the environmental state of a region. The CBR methods takes advantage of a set of situation–solution pairs called cases, which are stored in a memory and then retrieved as candidates to solve new problems. Situations in this work are represented by a set of risky trends of key environmental pathways (KEPs) related to CO2 emissions, air quality, loss of vegetation cover, water availability, and solid waste, the combination of which damage the environmental state quality of a region. Meanwhile, solutions are represented by a set of EMAs. Similar situations to a given current situation are retrieved from the memory of cases, and then their solutions are combined through an adaptation mechanism, until the solution of the current problem is obtained. The AHP method is used to assign weights to environmental variables and to alternative solutions represented by EMAs. We used risky trends derived from real data related to the environmental states of a Mexican region to test the proposed CBR–AHP hybrid method. The results obtained provided insights into the potential of the CBR–AHP hybrid method to support the decision-making process to select EMAs aimed at reducing risky trends of current environmental states.

show abstract

“…There are several MCDM techniques proposed by researchers. These include: AHP 1 [9], TOPSIS 2 [11], CBR 3 [42], ANP 4 [43], GP 5 [44], ELECTRE 6 [45] and PROMETHEE 7 [46]. This paper, however, focuses on AHP and TOPSIS and the aim of the study is to find suitable dam sites in southern parts of Sistan and Baluchestan Province using these methods.…”

Section: Ranking Selected Sites By Using Mcdm Methodsmentioning

confidence: 99%

A Comparative Study of the AHP and TOPSIS Techniques for Dam Site Selection Using GIS: A Case Study of Sistan and Baluchestan Province, Iran

Jozaghi¹,

Heidary²,

Hatami³

et al. 2018

Preprint

View full text Add to dashboard Cite

The application of multiple criteria decision-making (MCDM) techniques in real-life problems has increased in recent years. The need to build advanced decision models with higher capabilities that can support decision making in a broad spectrum of applications, promotes the integration of MCDM techniques with applicable systems, including artificial intelligence, and Geographic Information Systems (GIS). The Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) are amongst the most widely adopted MCDM techniques capable of resolving water resources challenges. A critical problem associated with water resource management is dam site selection. This paper presents a comparative analysis of TOPSIS and AHP in the context of decision making using GIS for dam site selection. The comparison was made based on geographic and water quality criteria. A ratio estimation procedure was used to determine the weights of these criteria. Both methods were applied for selection of optimal sites for dams in the Sistan and Baluchestan province, Iran. The results show that the TOPSIS method is better suited to the problem of dam site selection for this case study. Actual locations of dams constructed in the area were used to verify the results of both methods.

show abstract

Using statistical models and case-based reasoning in claims prediction: experience from a real-world problem

Cited by 22 publications

References 23 publications

A hybrid knowledge-based approach to supporting the medical prescription for general practitioners: Real case in a Hong Kong medical center

A hybrid knowledge-based approach to supporting the medical prescription for general practitioners: Real case in a Hong Kong medical center

A CBR–AHP Hybrid Method to Support the Decision-Making Process in the Selection of Environmental Management Actions

A Comparative Study of the AHP and TOPSIS Techniques for Dam Site Selection Using GIS: A Case Study of Sistan and Baluchestan Province, Iran

Contact Info

Product

Resources

About