Your browser doesn't support javascript.
loading
Large-scale mining disease comorbidity relationships from post-market drug adverse events surveillance data.
Zheng, Chunlei; Xu, Rong.
Afiliação
  • Zheng C; Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, 2103 Cornell Road, Cleveland, 44106, OH, USA.
  • Xu R; Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, 2103 Cornell Road, Cleveland, 44106, OH, USA. rxx@case.edu.
BMC Bioinformatics ; 19(Suppl 17): 500, 2018 Dec 28.
Article em En | MEDLINE | ID: mdl-30591027
ABSTRACT

BACKGROUND:

Systems approaches in studying disease relationship have wide applications in biomedical discovery, such as disease mechanism understanding and drug discovery. The FDA Adverse Event Reporting System (FAERS) contains rich information about patient diseases, medications, drug adverse events and demographics of 17 million case reports. Here, we explored this data resource to mine disease comorbidity relationships using association rule mining algorithm and constructed a disease comorbidity network.

RESULTS:

We constructed a disease comorbidity network with 1059 disease nodes and 12,608 edges using association rule mining of FAERS (14,157 rules). We evaluated the performance of comorbidity mining from FAERS using known disease comorbidities of multiple sclerosis (MS), psoriasis and obesity that represent rare, moderate and common disease respectively. Comorbidities of MS, obesity and psoriasis obtained from our network achieved precisions of 58.6%, 73.7%, 56.2% and recalls 87.5%, 69.2% and 72.7% separately. We performed comparative analysis of the disease comorbidity network with disease semantic network, disease genetic network and disease treatment network. We showed that (1) disease comorbidity clusters exhibit significantly higher semantic similarity than random network (0.18 vs 0.10); (2) disease comorbidity clusters share significantly more genes (0.46 vs 0.06); and (3) disease comorbidity clusters share significantly more drugs (0.64 vs 0.17). Finally, we demonstrated that the disease comorbidity network has potential in uncovering novel disease relationships using asthma as a case study.

CONCLUSIONS:

Our study presented the first comprehensive attempt to build a disease comorbidity network from FDA Adverse Event Reporting System. This network shows well correlated with disease semantic similarity, disease genetics and disease treatment, which has great potential in disease genetics prediction and drug discovery.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Vigilância de Produtos Comercializados / Comorbidade / Efeitos Colaterais e Reações Adversas Relacionados a Medicamentos / Mineração de Dados Tipo de estudo: Screening_studies Limite: Humans País/Região como assunto: America do norte Idioma: En Ano de publicação: 2018 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Vigilância de Produtos Comercializados / Comorbidade / Efeitos Colaterais e Reações Adversas Relacionados a Medicamentos / Mineração de Dados Tipo de estudo: Screening_studies Limite: Humans País/Região como assunto: America do norte Idioma: En Ano de publicação: 2018 Tipo de documento: Article