Large-scale mining disease comorbidity relationships from post-market drug adverse events surveillance data

Zheng, Chunlei; Xu, Rong

doi:10.1186/s12859-018-2468-8

Cited by 23 publications

(18 citation statements)

References 32 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCN was built based on 6 480 372 patient health reports using data mining techniques ( Zheng and Xu, 2018 ). DCN includes 1059 disease nodes and 12 608 edges.…”

Section: Methodsmentioning

confidence: 99%

“…DCN includes 1059 disease nodes and 12 608 edges. Disease names on DCN have been mapped to the UMLS CUIs using MetaMap (2016 V2 release) ( Zheng and Xu, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

“…We demonstrated that the DSE-CSN-based approach had significantly higher performance in DTI prediction as compared to the traditional drug phenome network-based approach. In this study, we propose a significantly improved drug-target prediction approach (TargetPredict) by incorporating a large amount of human phenotype data that we extracted from tens of millions of research articles, patient health data and other free-text documents ( Xu and Wang, 2013 ; Zheng and Xu, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

“…TargetPredict incorporated 855 904 phenotypic and genetic relationships among 1430 drugs, 4251 SEs, 1059 diseases and 17 860 genes ( Fig. 1 ), including a disease comorbidity network (DCN) constructed from the 6 480 372 patient reports in FDA Adverse Event Reporting System (FAERS) ( Zheng and Xu, 2018 ), and TreatKB, a comprehensive drug–disease treatment knowledge source constructed using natural language processing from 21 million published biomedical research articles ( Xu and Wang, 2013 ). The complex relationships were modeled simultaneously using our CSN-based model.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Combining phenome-driven drug-target interaction prediction with patients’ electronic health records-based clinical corroboration toward drug discovery

Zhou

Zheng

2020

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Motivation Predicting drug–target interactions (DTIs) using human phenotypic data have the potential in eliminating the translational gap between animal experiments and clinical outcomes in humans. One challenge in human phenome-driven DTI predictions is integrating and modeling diverse drug and disease phenotypic relationships. Leveraging large amounts of clinical observed phenotypes of drugs and diseases and electronic health records (EHRs) of 72 million patients, we developed a novel integrated computational drug discovery approach by seamlessly combining DTI prediction and clinical corroboration. Results We developed a network-based DTI prediction system (TargetPredict) by modeling 855 904 phenotypic and genetic relationships among 1430 drugs, 4251 side effects, 1059 diseases and 17 860 genes. We systematically evaluated TargetPredict in de novo cross-validation and compared it to a state-of-the-art phenome-driven DTI prediction approach. We applied TargetPredict in identifying novel repositioned candidate drugs for Alzheimer’s disease (AD), a disease affecting over 5.8 million people in the United States. We evaluated the clinical efficiency of top repositioned drug candidates using EHRs of over 72 million patients. The area under the receiver operating characteristic (ROC) curve was 0.97 in the de novo cross-validation when evaluated using 910 drugs. TargetPredict outperformed a state-of-the-art phenome-driven DTI prediction system as measured by precision–recall curves [measured by average precision (MAP): 0.28 versus 0.23, P-value < 0.0001]. The EHR-based case–control studies identified that the prescriptions top-ranked repositioned drugs are significantly associated with lower odds of AD diagnosis. For example, we showed that the prescription of liraglutide, a type 2 diabetes drug, is significantly associated with decreased risk of AD diagnosis [adjusted odds ratios (AORs): 0.76; 95% confidence intervals (CI) (0.70, 0.82), P-value < 0.0001]. In summary, our integrated approach that seamlessly combines computational DTI prediction and large-scale patients’ EHRs-based clinical corroboration has high potential in rapidly identifying novel drug targets and drug candidates for complex diseases. Availability and implementation nlp.case.edu/public/data/TargetPredict.

show abstract

“…DCN was built based on 6 480 372 patient health reports using data mining techniques ( Zheng and Xu, 2018 ). DCN includes 1059 disease nodes and 12 608 edges.…”

Section: Methodsmentioning

confidence: 99%

“…DCN includes 1059 disease nodes and 12 608 edges. Disease names on DCN have been mapped to the UMLS CUIs using MetaMap (2016 V2 release) ( Zheng and Xu, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining phenome-driven drug-target interaction prediction with patients’ electronic health records-based clinical corroboration toward drug discovery

Zhou

Zheng

2020

Bioinformatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The FDA Adverse Event Reporting System (FAERS) contains rich information about patient diseases, medications, drug adverse events etc. Zheng and Xu [8] systematically explored this data resource to construct a disease comorbidity network (DCN) with 1,059 disease nodes and 12,608 edges using association rule mining (14,157 rules). The DCN shows good performance in capturing known disease comorbidities and is well correlated with disease semantic similarity, disease genetics and disease treatment.…”

Section: The Science Program For the Icibm 2018 Bioinformatics Trackmentioning

confidence: 99%

The International Conference on Intelligent Biology and Medicine (ICIBM) 2018: bioinformatics towards translational applications

Liu

Xie

et al. 2018

BMC Bioinformatics

View full text Add to dashboard Cite

The 2018 International Conference on Intelligent Biology and Medicine (ICIBM 2018) was held on June 10–12, 2018, in Los Angeles, California, USA. The conference consisted of a total of eleven scientific sessions, four tutorials, one poster session, four keynote talks and four eminent scholar talks, which covered a wild range of aspects of bioinformatics, medical informatics, systems biology and intelligent computing. Here, we summarize nine research articles selected for publishing in BMC Bioinformatics.

show abstract

Identifying frequent drug combinations associated with delirium in older adults: Application of association rules method to a case‐time‐control design

Chyou

Nishtala

2021

Pharmacoepidemiology and Drug

View full text Add to dashboard Cite

Background Older adults are at an increased risk of delirium because of age, polypharmacy, multiple comorbidities, frailty, and acute illness. Although medication‐induced delirium in older adults is well understood, limited population‐level evidence is available, particularly on combinations of medications associated with delirium in older adults. Objectives We aimed to apply association rule analysis to identify drug combinations contributing to delirium risk in adults aged 65 and older using a case‐time‐control design. Method We sourced a nationwide representative sample of New Zealander's aged ≥65 years from the pharmaceutical collections and hospital discharge information. Prescription records (2005–2015) were obtained from New Zealand pharmaceutical collections (Pharms). Medication exposures were coded as binary variables (exposed vs. not exposed) at the individual drug level. All medications, including antimicrobials, antihistamines, diuretics, opioids, and nonsteroidal anti‐inflammatory medications, were considered drugs of interest. The first‐time coded diagnosis of delirium was extracted from the National Minimal Dataset (NMDS). A unique patient identifier linked the prescription dataset to the event dataset to set up a case‐time‐control cohort, indexed at the first delirium event. Association rules were then applied to identify frequent drug combinations in the case and the control periods (l‐day with a 35‐day washout period) that are statistically associated with delirium, and the association was tested by computing a time‐trend adjusted matched odds‐ratio (MOR) and its 95% confidence interval (CI). Results We identified 28 503 individuals (mean age 84.1 years) from 2005 to 2015 with delirium. Our combined association rule and case‐time‐control analysis identified several drug classes, including antipsychotics, benzodiazepines, opioids, and diuretics associated with delirium. Our analysis also identified frequently used drug combinations that are associated with delirium. Examples include combined exposures to quetiapine and furosemide (MOR = 6.17; 95%CI = [2.05–18.54]), haloperidol (MOR = 4.81; 95%CI = [3.16–6.69]), combined exposures to furosemide, omeprazole, and lorazepam (MOR = 3.94; 95%CI = [3.03–5.10]), and fentanyl exposure (MOR = 3.46; 95%CI [2.05–9.21]). Conclusion The association rule method applied to a case‐time‐control design is a novel approach to identifying drug combinations contributing to delirium with adjustment for any temporal trends in exposures. The study provides new insight into the combination of medicines linked to delirium.

show abstract

Large-scale mining disease comorbidity relationships from post-market drug adverse events surveillance data

Cited by 23 publications

References 32 publications

Combining phenome-driven drug-target interaction prediction with patients’ electronic health records-based clinical corroboration toward drug discovery

Combining phenome-driven drug-target interaction prediction with patients’ electronic health records-based clinical corroboration toward drug discovery

The International Conference on Intelligent Biology and Medicine (ICIBM) 2018: bioinformatics towards translational applications

Identifying frequent drug combinations associated with delirium in older adults: Application of association rules method to a case‐time‐control design

Contact Info

Product

Resources

About