FindZebra: A search engine for rare diseases

Dragusin, Radu; Petcu, Paula; Lioma, Christina; Larsen, Birger; Jørgensen, Henrik L.; Cox, Ingemar J.; Hansen, Lars Kai; Ingwersen, Peter; Winther, Ole

doi:10.1016/j.ijmedinf.2013.01.005

Cited by 73 publications

(74 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are some other state-of-the-art works, such as POSSUM [Bankier and Keith 1989], The London Dysmorphology Database (LDDB) [Fryns and de Ravel 2002], and the search routines available with the OMIM [Hamosh et al 2005], Orphanet [Aymé 2003], and FindZebra [Dragusin et al 2013]. These systems do not provide explicit rankings or measures of plausibility for the potentially long lists of candidate diseases.…”

Section: Discussionmentioning

confidence: 99%

“…These systems do not provide explicit rankings or measures of plausibility for the potentially long lists of candidate diseases. Currently, we are comparing our system with the rare disease search engine FindZebra [Dragusin et al 2013].…”

Section: Discussionmentioning

confidence: 99%

“…FindZebra [Dragusin et al 2013] is a vertical search engine specially designed for rare diseases. This system does not consider the genetic effects on diseases or phenotypic effects on genes; rather, it presents a list of disease documents for a given set of symptoms.…”

Section: State Of the Artmentioning

confidence: 99%

See 2 more Smart Citations

Estimating a Ranked List of Human Genetic Diseases by Associating Phenotype-Gene with Gene-Disease Bipartite Graphs

Ullah

Aono

Seddiqui

2015

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

With vast amounts of medical knowledge available on the Internet, it is becoming increasingly practical to help doctors in clinical diagnostics by suggesting plausible diseases predicted by applying data and text mining technologies. Recently, Genome-Wide Association Studies (GWAS) have proved useful as a method for exploring phenotypic associations with diseases. However, since genetic diseases are difficult to diagnose because of their low prevalence, large number, and broad diversity of symptoms, genetic disease patients are often misdiagnosed or experience long diagnostic delays. In this article, we propose a method for ranking genetic diseases for a set of clinical phenotypes. In this regard, we associate a phenotype-gene bipartite graph (PGBG) with a gene-disease bipartite graph (GDBG) by producing a phenotype-disease bipartite graph (PDBG), and we estimate the candidate weights of diseases. In our approach, all paths from a phenotype to a disease are explored by considering causative genes to assign a weight based on path frequency, and the phenotype is linked to the disease in a new PDBG. We introduce the Bidirectionally induced Importance Weight (BIW) prediction method to PDBG for approximating the weights of the edges of diseases with phenotypes by considering link information from both sides of the bipartite graph. The performance of our system is compared to that of other known related systems by estimating Normalized Discounted Cumulative Gain (NDCG), Mean Average Precision (MAP), and Kendall's tau metrics. Further experiments are conducted with well-known TF·IDF, BM25, and Jenson-Shannon divergence as baselines. The result shows that our proposed method outperforms the known related tool Phenomizer in terms of NDCG@10, NDCG@20, MAP@10, and MAP@20; however, it performs worse than Phenomizer in terms of Kendall's tau-b metric at the top-10 ranks. It also turns out that our proposed method has overall better performance than the baseline methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating a Ranked List of Human Genetic Diseases by Associating Phenotype-Gene with Gene-Disease Bipartite Graphs

Ullah

Aono

Seddiqui

2015

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

show abstract

“…While the definition of RDs is based on the concept of prevalence or the maximum number of patients in a region, ranging in approximate terms from 1 in 1,000 to 1 in 10,000 people (Ayme et al, 2015), it differs from country to country (Dragusin et al, 2013;Facey et al, 2014;Facey and Hansen 2015). There is no single description of RDs for everybody (Cui and Han, 2015).…”

Section: Rare Disordersmentioning

confidence: 99%

A systematic review of research into rare diseases in the educational sphere

Darretxe¹,

Gaintza²,

Monzon-Gonzalez³

2017

Educ. Res. Rev.

View full text Add to dashboard Cite

Rare diseases (RDs) represent a wide, varied group of illnesses characterised by their low prevalence among the population. Moreover, they can appear at any time of life, including in infancy. For this reason, the aim of this article was to review and analyse research in the field of education to find out what kind of educational response is offered by schools to pupils with RDs. The following databases were used to find the pertinent bibliography: Web of Science, Scopus, Education Database (Proquest) and Eric. After retrieving the publications included in this study, each paper was reviewed and analysed on the basis of what journal they were published in and their abstracts. Out of the 53 studies included, only six bore any relation to the school context. The results showed that while there are scientific papers on RDs, most of them are restricted to the medical sphere. It was therefore concluded that further research is needed in the field of education to advance in the schooling of pupils with RDs.

show abstract

“…Es ist schlichtweg unmöglich, die häufig variablen Symptomkomplexe der mehr als 8 000 seltenen Erkrankungen zu erinnern. In diesem Bereich sind 3 Programme explizit zu nennen: «FindZebra» ist eine Suchmaschine speziell für seltene Erkrankungen [8,9]. Diese indexiert im Gegensatz zu Google nur qualitativ hochwertige und kuratierte Informationen.…”

unclassified

Hinschauen, lernen, anwenden

Mader¹

2019

Karger Kompass Dermatol

View full text Add to dashboard Cite

FindZebra: A search engine for rare diseases

Cited by 73 publications

References 40 publications

Estimating a Ranked List of Human Genetic Diseases by Associating Phenotype-Gene with Gene-Disease Bipartite Graphs

Estimating a Ranked List of Human Genetic Diseases by Associating Phenotype-Gene with Gene-Disease Bipartite Graphs

A systematic review of research into rare diseases in the educational sphere

Hinschauen, lernen, anwenden

Contact Info

Product

Resources

About