Marcos Da Silveira

A Semantic Big Data Platform for Integrating Heterogeneous Wearable Data in Healthcare

Advances supported by emerging wearable technologies in healthcare promise patients a provision of high quality of care. Wearable computing systems represent one of the most thrust areas used to transform traditional healthcare systems into active systems able to continuously monitor and control the patients’ health in order to manage their care at an early stage. However, their proliferation creates challenges related to data management and integration. The diversity and variety of wearable data related to healthcare, their huge volume and their distribution make data processing and analytics more difficult. In this paper, we propose a generic semantic big data architecture based on the “Knowledge as a Service” approach to cope with heterogeneity and scalability challenges. Our main contribution focuses on enriching the NIST Big Data model with semantics in order to smartly understand the collected data, and generate more accurate and valuable information by correlating scattered medical data stemming from multiple wearable devices or/and from other distributed data sources. We have implemented and evaluated a Wearable KaaS platform to smartly manage heterogeneous data coming from wearable devices in order to assist the physicians in supervising the patient health evolution and keep the patient up-to-date about his/her status.

Understanding semantic mapping evolution by observing changes in biomedical ontologies

Knowledge Organization Systems (KOSs) are extensively used in the biomedical domain to support information sharing between software applications. KOSs are proposed covering different, but overlapping subjects, and mappings indicate the semantic relation between concepts from two KOSs. Over time, KOSs change as do the mappings between them. This can result from a new discovery or a revision of existing knowledge which includes corrections of concepts or mappings. Indeed, changes affecting KOS entities may force the underline mappings to be updated in order to ensure their reliability over time. To tackle this open research problem, we study how mappings are affected by KOS evolution. This article presents a detailed descriptive analysis of the impact that changes in KOS have on mappings. As a case study, we use the official mappings established between SNOMED CT and ICD-9-CM from 2009 to 2011. Results highlight factors according to which KOS changes in varying degrees influence the evolution of mappings.

Mapping adaptation actions for the automatic reconciliation of dynamic ontologies

The highly dynamic nature of domain ontologies has a direct impact on semantic mappings established between concepts from different ontologies. Mappings must therefore be maintained according to ongoing ontology changes. Since many software applications exploit mappings for managing information and knowledge, it is important to define appropriate adaptation strategies to apply to existing mappings in order to keep their validity over time. In this article, we propose a set of mapping adaptation actions and present how they are used to maintain mappings up-to-date based on ontology change operations of different nature. We conduct an experimental evaluation using life sciences ontologies and mappings. We measure the evolution of mappings based on the proposed approach to mapping adaptation. The results confirm that mappings must be individually adapted according to the different types of ontology change.

Inferring Recommendation Interactions in Clinical Guidelines: Case-studies on Multimorbidity

The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.

Towards a Conceptual Model for Enhancing Reasoning About Clinical Guidelines - A Case-Study on Comorbidity.

Computer-Interpretable Guidelines (CIGs) are representations of Clinical Guidelines (CGs) in computer interpretable languages. CIGs have been pointed as an alternative to deal with the various limitations of paper based CGs to support healthcare activities. Although the improvements offered by existing CIG languages, the complexity of the medical domain requires advanced features in order to reuse, share, update, combine or personalize their contents. We propose a conceptual model for representing the content of CGs as a result from an iterative approach that take into account the content of real CGs, CIGs languages and foundational ontologies in order to enhance the reasoning capabilities required to address CIG use-cases. In particular, we apply our approach to the comorbidity use-case and illustrate the model with a realistic case study (Duodenal Ulcer and Transient Ischemic Attack) and compare the results against an existing approach.

A Conceptual Model for Detecting Interactions among Medical Recommendations in Clinical Guidelines

Representation of clinical knowledge is still an open research topic. In particular, classical languages designed for representing clinical guidelines, which were meant for producing diagnostic and treatment plans, present limitations such as for re-using, combining, and reasoning over existing knowledge. In this paper, we address such limitations by proposing an extension of the TMR conceptual model to represent clinical guidelines that allows re-using and combining knowledge from several guidelines to be applied to patients with multimorbidities. We provide means to (semi)automatically detect interactions among recommendations that require some attention from experts, such as recommending more than once the same drug. We evaluate the model by applying it to a realistic case study involving 3 diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with two other existing methods.

Medical Ontology Validation through Question Answering

Medical ontology construction is an interactive process that requires the collaboration of both ICT and medical experts. The complexity of the medical domain and the formal description languages makes this collaboration a time consuming and error-prone task. In this paper, we define an ontology validation method that hides the complexity of the formal description languages behind a question-answering game. The proposed approach differs from ”classic” logical-consistency validation approaches and tackles the validation of the domain conceptualization. Reasoning techniques and verbalization methods are used to transform statements inferred from ontologies into natural language questions. The answers of the domain experts to these questions are used to validate and improve the ontology by identifying where it needs to be modified. The validation system then performs automatically the ontology updates needed to correct the detected errors.

Towards the formalization of guidelines care actions using patterns and semantic web technologies

Computer Interpretable Guidelines (CIG) have largely contributed to the simplification and dissemination of clinical guidelines. However, the formalization of CIG contents, especially care actions, is still an open issue. Actually, this information, which is the heart of the guideline, is still expressed as free text and therefore prevents the development of intelligent tools for assisting physicians defining treatments. In this paper, we introduce a framework for formalizing care actions using natural language processing techniques, Semantic Web technologies and medical standards.

Leveraging the Impact of Ontology Evolution on Semantic Annotations

This paper deals with the problem of maintenance of semantic annotations produced based on domain ontologies. Many annotated texts have been produced and made available to end-users. If not reviewed regularly, the quality of these annotations tends to decrease over time due to the evolution of the domain ontologies. The quality of these annotations is critical for tools that exploit them e.g., search engines and decision support systems and need to ensure an acceptable level of performance. Although the recent advances for ontology-based annotation systems to annotate new documents, the maintenance of existing annotations remains under studied. In this work we present an analysis of the impact of ontology evolution on existing annotations. To do so, we used two well-known annotators to generate more than 66 million annotations from a pre-selected set of 5000 biomedical journal articles and standard ontologies covering a period ranging from 2004 to 2016. We highlight the correlation between changes in the ontologies and changes in the annotations and we discuss the necessity to improve existing annotation formalisms in order to include elements required to support semi- automatic annotation maintenance mechanisms.

Analyzing Recommendations Interactions in Clinical Guidelines - Impact of Action Type Hierarchies and Causation Beliefs.

Accounting for patients with multiple health conditions is a complex task that requires analysing potential interactions among recommendations meant to address each condition. Although some approaches have been proposed to address this issue, important features still require more investigation, such as (re)usability and scalability. To this end, this paper presents an approach that relies on reusable rules for detecting interactions among recommendations coming from various guidelines. It extends previously proposed models by introducing the notions of action type hierarchy and causation beliefs, and provides a systematic analysis of relevant interactions in the context of multimorbidity. Finally, the approach is assessed based on a case-study taken from the literature to highlight the added value of the approach.