Columbia Open Health Data, clinical concept prevalence and co-occurrence from electronic health records

Abstract

Columbia Open Health Data (COHD) is a publicly accessible database of electronic health record (EHR) prevalence and co-occurrence frequencies between conditions, drugs, procedures, and demographics. COHD was derived from Columbia University Irving Medical Center’s Observational Health Data Sciences and Informatics (OHDSI) database. The lifetime dataset, derived from all records, contains 36,578 single concepts (11,952 conditions, 12,334 drugs, and 10,816 procedures) and 32,788,901 concept pairs from 5,364,781 patients. The 5-year dataset, derived from records from 2013–2017, contains 29,964 single concepts (10,159 conditions, 10,264 drugs, and 8,270 procedures) and 15,927,195 concept pairs from 1,790,431 patients. Exclusion of rare concepts (count ≤ 10) and Poisson randomization enable data sharing by eliminating risks to patient privacy. EHR prevalences are informative of healthcare consumption rates. Analysis of co-occurrence frequencies via relative frequency analysis and observed-expected frequency ratio are informative of associations between clinical concepts, useful for biomedical research tasks such as drug repurposing and pharmacovigilance. COHD is publicly accessible through a web application-programming interface (API) and downloadable from the Figshare repository. The code is available on GitHub.

Leveraging Distributed Biomedical Knowledge Sources to Discover Novel Uses for Known Drugs

“…Among these, the drug dexamethasone is predicted to treat posterior uveitis (a type of inflammation in the eye) with a probability of 0.838129. Using an additional knowledge source, Colombia Open Health Data (COHD) [86] which provides anonymized key word search over 1.7 million health records, we find that dexamethasone co-occurs with posterior uveitis at a rate 2.789 times more frequently than would be expected in a general population. This may indicate that dexamethasone is being prescribed as an off-label treatment for this disease.…”

“…The blue and yellow lines indicate the performance of the node2vec and DWPC approaches respectively when restricting the training set to only 147 diseases to facilitate a direct comparison due to efficiency constraints experienced by the DWPC method. such as when we used the plot as in Figure 3 to find a candidate threshold that filters out all but the most likely drug repurposing candidates or leveraging additional data sources such as Columbia Open Health Data [86] as in Section 3.1.…”

SurfCon

“…For the sake of patient privacy and security, it is usually quite difficult, if not impossible, for medical institutes to grant public access to large-scale raw or even de-identified clinical texts [2]. Consequently, medical terms 1 and their aggregated co-occurrence counts extracted from raw clinical texts are becoming a popular (although not perfect) substitute for raw clinical texts for the research community to study EMR data [2,8,33]. For example, Finlayson et al [8] released millions of medical terms extracted from the clinical texts in Stanford Hospitals and Clinics as well as their global co-occurrence counts, rather than releasing raw sentences/paragraphs/documents from the clinical text corpus.…”

“…For example, Finlayson et al [8] prune the edges between two terms co-occurring less than 100 times, which can lead to missing edges between two related terms in the co-occurrence graph. Ta et al [33] remove all concepts with singleton frequency counts below 10. Hence, the noisy nature of the co-occurrence graph makes it less accurate to embed a term based on their original contexts.…”

“…Moreover, there also exists the risk that de-identified data can be attacked and recovered by the re-identification in some cases [9]. Thus, to facilitate research on EMRs, an increasingly popular substitute strategy for releasing raw clinical texts is to extract medical terms and their aggregated co-occurrence counts from the corpus [2,8,33]. We refer to such data as privacy-aware clinical data in this paper.…”