GGM: Efficient Navigation and Mining in Distributed Genomedical Data

Pierson, Jean‐Marc; Gossa, Julien; Wehrle, Pascal; Cardenas, Yonny; Cahon, S.; Samad, Mahmoud El; Brunie, Lionel; Dhaenens, Clarisse; Hameurlain, Abdelkader; Melab, Nouredine; Miquel, Maryvonne; Morvan, Franck; Talbi, El‐Ghazali; Tchounikine, Anne

doi:10.1109/tnb.2007.897477

Cited by 5 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More than the size of data to be analyzed, the relational multiplicity of the data may cause problems. Algorithmic development such as those proposed in [45] and computational infrastructures to handle the combination of these data for a data mining application will be the next challenge on clinical data mining [95].…”

Section: Discussionmentioning

confidence: 99%

Clinical Data Mining: a Review

Iavindrasana

Cohen²,

Depeursinge³

et al. 2009

Yearb Med Inform

View full text Add to dashboard Cite

Summary Objective Clinical data mining is the application of data mining techniques using clinical data. We review the literature in order to provide a general overview by identifying the status-of-practice and the challenges ahead. Methods The nine data mining steps proposed by Fayyad in 1996 [4] were used as the main themes of the review. MEDLINE was used as primary source and 84 papers were retained based on our inclusion criteria. Results Clinical data mining has three objectives: understanding the clinical data, assist healthcare professionals, and develop a data analysis methodology suitable for medical data. Classification is the most frequently used data mining function with a predominance of the implementation of Bayesian classifiers, neural networks, and SVMs (Support Vector Machines). A myriad of quantitative performance measures were proposed with a predominance of accuracy, sensitivity, specificity, and ROC curves. The latter are usually associated with qualitative evaluation. Conclusion Clinical data mining respects its commitment to extracting new and previously unknown knowledge from clinical databases. More efforts are still needed to obtain a wider acceptance from the healthcare professionals and for generalization of the knowledge and reproducibility of its extraction process: better description of variables, systematic report of algorithm parameters including the method to obtain them, use of easy-to-understand models and comparisons of the efficiency of clinical data mining with traditional statistical analyses. More and more data will be available for data miners and they have to develop new methodologies and infrastructures to analyze the increasingly complex medical data.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical Data Mining: a Review

Iavindrasana

Cohen²,

Depeursinge³

et al. 2009

Yearb Med Inform

View full text Add to dashboard Cite

show abstract

“…Grid technology is now being used to deploy large infrastructures outside the computer science domain. In the biomedical field there are numerous examples of grid infrastructures [7][8][9][10][11][12][13][14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Enabling GeneHunter as a Grid Service

Krikov¹,

Price²,

Matney³

et al. 2011

Methods Inf Med

View full text Add to dashboard Cite

show abstract

“…[ 15 ]The Globus MEDICUS project supports the federation of DICOM medical imaging devices into a healthcare grid to address image sharing, processing and archiving among providers and researchers. [ 16 ] In addition, shared resources through grid computing have allowed for parallel execution of existing algorithms and applications in such areas as mining genomic data,[ 17 ] determination of a protein secondary structure,[ 18 ] and analysis of microbial genome sequences to identify potential drug targets for new antibiotics. [ 19 ] While an extensive list of all grid systems in use today in biomedical research is outside the scope of this paper, our modest listing illustrates the diversity of biomedical informatics specialties that use grid technology to provide the scientific community with shared access to tools and resources.…”

Section: Introductionmentioning

confidence: 99%

A case for using grid architecture for state public health informatics: the Utah perspective

Staes

LeFevre

et al. 2009

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

This paper presents the rationale for designing and implementing the next-generation of public health information systems using grid computing concepts and tools. Our attempt is to evaluate all grid types including data grids for sharing information and computational grids for accessing computational resources on demand. Public health is a broad domain that requires coordinated uses of disparate and heterogeneous information systems. System interoperability in public health is limited. The next-generation public health information systems must overcome barriers to integration and interoperability, leverage advances in information technology, address emerging requirements, and meet the needs of all stakeholders. Grid-based architecture provides one potential technical solution that deserves serious consideration. Within this context, we describe three discrete public health information system problems and the process by which the Utah Department of Health (UDOH) and the Department of Biomedical Informatics at the University of Utah in the United States has approached the exploration for eventual deployment of a Utah Public Health Informatics Grid. These three problems are: i) integration of internal and external data sources with analytic tools and computational resources; ii) provide external stakeholders with access to public health data and services; and, iii) access, integrate, and analyze internal data for the timely monitoring of population health status and health services. After one year of experience, we have successfully implemented federated queries across disparate administrative domains, and have identified challenges and potential solutions concerning the selection of candidate analytic grid services, data sharing concerns, security models, and strategies for reducing expertise required at a public health agency to implement a public health grid.

show abstract

GGM: Efficient Navigation and Mining in Distributed Genomedical Data

Cited by 5 publications

References 19 publications

Clinical Data Mining: a Review

Clinical Data Mining: a Review

Enabling GeneHunter as a Grid Service

A case for using grid architecture for state public health informatics: the Utah perspective

Contact Info

Product

Resources

About