Transforming Heterogeneous Data into Knowledge for Personalized Treatments—A Use Case

Vidal, María-Esther; Endris, Kemele M.; Jazashoori, Samaneh; Sakor, Ahmad; Rivas, Ariam

doi:10.1007/s13222-019-00312-z

Cited by 18 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The processing of medical data also requires the development of appropriate solutions that allow for the collection, transmission, storage and protection of data. [19,20,26,27] To date, most existing algorithms that allow to you effectively solve current problems do not cover the entire list of problems associated with the personalization of decisions during the maintenance of the treatment process. Against this background, there is a need for new solutions that allow valid processing and storage of data without losing the quality of the results.…”

Section: Discussionmentioning

confidence: 99%

Data Driven Analytics for Personalized Medical Decision Making

Melnykova¹,

Shakhovska²,

ml.³

et al. 2020

Preprint

View full text Add to dashboard Cite

The study was conducted on applying machine learning and data mining methods to personalizing the treatment. This allows investigating individual patient characteristics. Personalization is built on the clustering method and associative rules. It was suggested to determine the average distance between instances for optimal performance metrics finding. The formalization of the medical data pre-processing stage for finding personalized solutions based on current standards and pharmaceutical protocols is proposed. The model of patient data is built. The paper presents the novel approach to clustering built on ensemble of cluster algorithm with better than k-means algorithm Hopkins metrics. The personalized treatment usually is based on decision tree. Such approach requires a lot of computation time and cannot be paralyzed. Therefore, it is proposed to classify persons by conditions, to determine deviations of parameters from the normative parameters of the group, as well as the average parameters. This made it possible to create a personalized approach to treatment for each patient based on long-term monitoring. According to the results of the analysis, it becomes possible to predict the optimal conditions for a particular patient and to find the medicaments treatment according to personal characteristics.

show abstract

Section: Discussionmentioning

confidence: 99%

Data Driven Analytics for Personalized Medical Decision Making

Melnykova¹,

Shakhovska²,

ml.³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This methodology was approved with a proof-of-concept prototype developed on the OpenStack cloud architecture. Vidal et al have presented a knowledge-driven framework [35]. This framework extracts knowledge from short text and unstructured data.…”

Section: Review Of Healthcare Sectormentioning

confidence: 99%

Big Data Integration Solutions in Organizations: A Domain-Specific Analysis

Karanam¹,

Kamath²,

Kulkarni³

et al. 2021

Data Integrity and Quality

View full text Add to dashboard Cite

Big Data Integration (BDI) process integrates the big data arising from many diverse data sources, data formats presents a unified, valuable, customized, holistic view of data. BDI process is essential to build confidence, facilitate high-quality insights and trends for intelligent decision making in organizations. Integration of big data is a very complex process with many challenges. The data sources for BDI are traditional data warehouses, social networks, Internet of Things (IoT) and online transactions. BDI solutions are deployed on Master Data Management (MDM) systems to support collecting, aggregating and delivering reliable information across the organization. This chapter has conducted an exhaustive review of BDI literature and classified BDI applications based on their domain. The methods, applications, advantages and disadvantage of the research in each paper are tabulated. Taxonomy of concepts, table of acronyms and the organization of the chapter are presented. The number of papers reviewed industry-wise is depicted as a pie chart. A comparative analysis of curated survey papers with specific parameters to discover the research gaps were also tabulated. The research issues, implementation challenges and future trends are highlighted. A case study of BDI solutions implemented in various organizations was also discussed. This chapter concludes with a holistic view of BDI concepts and solutions implemented in organizations.

show abstract

“…Entity Alignment (EA) is an important solution to overcome interoperability issues while creating a knowledge graph from heterogeneous data sources. Dimou et al [8], Michel et al [16], and Vidal et al [19] propose EA as a pre-processing step, prior to the semantic enrichment and integration of data. In this case, pre-processing performs the task of EA on the whole provided data sources, independent of their involvement in the goal KG.…”

Section: Related Workmentioning

confidence: 99%

EABlock: A Declarative Entity Alignment Block for Knowledge Graph Creation Pipelines

Jozashoori,

Sakor,

Iglesias

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Despite encoding enormous amount of rich and valuable data, existing data sources are mostly created independently, being a significant challenge to their integration. Mapping languages, e.g., RML and R2RML, facilitate declarative specification of the process of applying meta-data and integrating data into a knowledge graph. Mapping rules can also include knowledge extraction functions in addition to expressing correspondences among data sources and a unified schema. Combining mapping rules and functions represents a powerful formalism to specify pipelines for integrating data into a knowledge graph transparently. Surprisingly, these formalisms are not fully adapted, and many knowledge graphs are created by executing ad-hoc programs to pre-process and integrate data. In this paper, we present EABlock, an approach integrating Entity Alignment (EA) as part of RML mapping rules. EABlock includes a block of functions performing entity recognition from textual attributes and link the recognized entities to the corresponding resources in Wikidata, DBpedia, and domain specific thesaurus, e.g., UMLS. EABlock provides agnostic and efficient techniques to evaluate the functions and transfer the mappings to facilitate its application in any RML-compliant engine. We have empirically evaluated EABlock performance, and results indicate that EABlock speeds up knowledge graph creation pipelines that require entity recognition and linking in state-of-the-art RML-compliant engines. EABlock is also publicly available as a tool through a GitHub repository and a DOI.

show abstract

Transforming Heterogeneous Data into Knowledge for Personalized Treatments—A Use Case

Cited by 18 publications

References 32 publications

Data Driven Analytics for Personalized Medical Decision Making

Data Driven Analytics for Personalized Medical Decision Making

Big Data Integration Solutions in Organizations: A Domain-Specific Analysis

EABlock: A Declarative Entity Alignment Block for Knowledge Graph Creation Pipelines

Contact Info

Product

Resources

About