A Chronic Illness System Using Biomedical Knowledge Sources and Relevance Feedback

Macedo, Alessandra Alaniz; Pollettini, Juliana Tarossi; Munson, Ethan V.

doi:10.1109/cbms.2015.45

Cited by 6 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…HSSF has been designed as a result of the development of previous surveillance systems: Automatic-SL [2] and CISS [3] presented in Section 2. Later, HSSF was reused to develop CISS+ [15] and CISS-SW [16] introduced in Section 4. We finally proposed HSSF and demonstrated its validation in Section 5.…”

Section: Discussionmentioning

confidence: 99%

“…Python Py4J connects these modules. Experiments with UTS and MetaMap demonstrated the effectiveness of the concept recognition task for both approaches: considering 150,664 terms, UTS and MetaMap recognized 15,988 and 9,589 concepts (reduction of 89 and 94% of terms), respectively [15]. Section 5.3.2 presents the results in terms of recall and precision.…”

Section: Ciss+mentioning

confidence: 98%

“…To expand the semantic meaning of terms of scientific papers and clinical records, we have created CISS+ using a careful study comparing the use of UMLS and the MetaMap tool [17]; we have also employed relevance feedback techniques, mainly automatic query expansion [15]. HSSF supported the development of CISS+, which demanded the use of two packages (the UTS and MetaMap packages) by the ConceptRecognition classes and the manipulation of the Similarity class.…”

Section: Ciss+mentioning

confidence: 99%

“…The first is a new version of CISS that uses higher-relevance terms/concepts from linguistic systems and automated techniques to refine queries [15]. The latter refers to the use of Semantic Web technologies to augment CISS [16].…”

Section: Proof-of-concept: Implementations From the Hssfmentioning

confidence: 99%

See 3 more Smart Citations

A Health Surveillance Software Framework to deliver information on preventive healthcare strategies

Macedo

Pollettini

Baranauskas

et al. 2016

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

A software framework can reduce costs related to the development of an application because it allows developers to reuse both design and code. Recently, companies and research groups have announced that they have been employing health software frameworks. This paper presents the design, proof-of-concept implementations and experimentation of the Health Surveillance Software Framework (HSSF). The HSSF is a framework that tackles the demand for the recommendation of surveillance information aiming at supporting preventive healthcare strategies. Examples of such strategies are the automatic recommendation of surveillance levels to patients in need of healthcare and the automatic recommendation of scientific literature that elucidates epigenetic problems related to patients. HSSF was created from two systems we developed in our previous work on health surveillance systems: the Automatic-SL and CISS systems. The Automatic-SL system aims to assist healthcare professionals in making decisions and in identifying children with developmental problems. The CISS service associates genetic and epigenetic risk factors related to chronic diseases with patient's clinical records. Towards evaluating the HSSF framework, two new systems, CISS+ and CISS-SW, were created by means of abstractions and instantiations of the framework (design and code). We show that HSSF supported the development of the two new systems given that they both recommend scientific papers using medical records as queries even though they exploit different computational technologies. In an experiment using simulated patients' medical records, we show that CISS, CISS+, and CISS-SW systems recommended more closely related and somewhat related documents than Google, Google Scholar and PubMed. Considering recall and precision measures, CISS+ surpasses CISS-SW in terms of precision.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Ciss+mentioning

confidence: 98%

Section: Ciss+mentioning

confidence: 99%

Section: Proof-of-concept: Implementations From the Hssfmentioning

confidence: 99%

See 2 more Smart Citations

A Health Surveillance Software Framework to deliver information on preventive healthcare strategies

Macedo

Pollettini

Baranauskas

et al. 2016

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dessa maneira, esses usuários não precisam formular consultas e ler todo o conteúdo do domínio de informação para encontrar informações relacionadas ao seu assunto de interesse. Serviços similares foram criados naárea de Informática Biomédica [11,2,12,30,9]. Atualmente, a pesquisadora está investigando a representação do seu domínio do problema (informações relacionadas, porém advindas de diferentes fontes em diferentes formatos e mídias), por meio de redes complexas heterogêneas de informação.…”

Section: Introductionunclassified

Manipulação e Relacionamento de Informação

Macedo¹

Self Cite

View full text Add to dashboard Cite

A Deus pela presença na minha vida. A Fundação de Amparo a Pesquisa do Estado de São Paulo (FAPESP), a CAPES e ao CNPq, que incentivam, financiam e dão suporteà pesquisa neste país. Aos professores-colegas de profissão, que compartilham a paixão pelo ensino e pela pesquisa e a esperança na transformação do mundo, utilizando essas ferramentas, principalmente ao Prof. Baranauskas com quem tenho colaborado em trabalhos e dividido angústias. Aos pesquisadores-colaboradores do Brasil e do exterior, que apoiam e discutem os trabalhos vislumbrados por mim. Ao pessoal, principalmente aos meus alunos, do laboratório 621 do DCM, que ajudou a traduzir ideias e pensamentos em trabalhos científicos. Aos funcionários e prestadores de serviço do DCM pelo suporte de infraestrutura. A minha família e amigos pelo apoio, carinho e amor eternos. Aos meus sogros e familiares distantes que, mesmo a milhares de quilômetros, sempre me incentivam e enviam muita energia positiva. Ao meu marido, José Antonio, e aos meus filhos, Helena e Santiago, pelo apoio e pela paciência inestimável!! i Sumário Lista de Figuras p. iv Normas e convenções p. vi Resumo p. vii Abstract p. viii 1 Introdução p. 2 Manipulação e Relacionamento de Informação Textual p.

show abstract