EHR Data Preparation for Case Based Reasoning Construction

El–Sappagh, Shaker; Elmogy, Mohammed; Riad, A. M.; Zaghlol, Hosam; Badria, Farid A.

doi:10.1007/978-3-319-13461-1_45

Cited by 8 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the OWL 2 ontology that is created in this study enhances the previously created ontology in El-Sappagh et al (2014c).All diabetes symptoms are categorized or codified in the pre-processing phase, as shown in our framework in Fig. 6 ( El-Sappagh et al, 2014a). Table 3 SCT concept that matches a particular clinical term, we search three hierarchies in the following order: Clinical finding, observable entity, and then procedure.…”

Section: The Proposed Case-base Encoding Methodologymentioning

confidence: 98%

An encoding methodology for medical knowledge using SNOMED CT ontology

El–Sappagh

Elmogy

2016

Journal of King Saud University - Computer and Information Scie

Self Cite

View full text Add to dashboard Cite

Knowledge-Intensive Case Based Reasoning (KI-CBR) systems mainly depend on ontology. Using ontology as domain knowledge supports the implementation of semanticallyintelligent case retrieval algorithms. The case-based knowledge must be encoded with the same concepts of the domain ontology. Standard medical ontologies, such as SNOMED CT (SCT), can play the role of domain ontology to enhance case representation and retrieval. This study has three stages. First, we propose an encoding methodology using SCT. Second, this methodology is used to encode the case-based knowledge. Third, all the used SCT concepts are collected in a reference set, and an OWL2 ontology of 550 pre-coordinated concepts is proposed. A diabetes diagnosis is chosen as a case study of our proposed framework. SCT is used to provide a pre-coordination concept coverage of $75% for diabetes diagnosis terms. Whereas, the uncovered concepts in SCT are proposed. The resulting OWL2 ontology will be used as domain knowledge representation in diabetes diagnosis CBR systems. The proposed framework is tested by using 60 real cases. Ó 2015 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

show abstract

Section: The Proposed Case-base Encoding Methodologymentioning

confidence: 98%

An encoding methodology for medical knowledge using SNOMED CT ontology

El–Sappagh

Elmogy

2016

Journal of King Saud University - Computer and Information Scie

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [30] a CBR for data preparation in electronic diabetes records was built. Experts in this work include the handling of missing values, feature selection, feature weighing, outlier detection, and normalization.…”

Section: Background 16mentioning

confidence: 99%

A case-based reasoning system for recommendation of data cleaning algorithms in classification and regression tasks

Corrales

Ledezma

Corrales

2020

Applied Soft Computing

View full text Add to dashboard Cite

“…The methylene chloride layers were combined and evaporated to dryness, and the total alkaloids were weighed out. The previous method was carried out 80 times with 11 Table 1 lists the used variables in our experiments and their ranges. Moreover, all previous sets produced total Harmala alkaloid yield range from 1.15% to 5.6% from the total plant material (1.15 -2.6 low), (2.6 -4.1 med.…”

Section:  Extraction Processmentioning

confidence: 99%

“…It is an unnatural interdisciplinary field, with a high interest and applied focus, but it also handles various essential research problems in addition to planning and policy issues. It uses the devices, resources, and methods need optimizing the acquisition, retrieval, storage and using the information on health and biomedical fields [8][9][10][11][12].…”

mentioning

confidence: 99%