Back

rdrugtrajectory: An R Package for the Analysis of Drug Prescriptions in Electronic Health Care Records

Nash, A.; Chang, T. E.; Wan, B.; Cader, M. Z.

2021-01-09 bioinformatics
10.1101/2021.01.08.425952 bioRxiv
Show abstract

Primary care electronic health care records are rich with patient and clinical information. Studying electronic health care records has resulted in marked improvements to national health care processes and patient-care decision making, and is a powerful supplementary source of data for drug discovery effort. We present the R package rdrugtrajectory, designed to yield demographic and patient-level characteristics of drug prescriptions in the UK Clinical Practice Research Datalink dataset. The package operates over Clinical Practice Research Datalink Gold clinical, referral and therapy datasets and includes features such as first drug prescriptions analysis, cohort-wide prescription information, cumulative drug prescription events, the longitudinal trajectory of drug prescriptions, and a survival analysis timeline builder to identify risks related to drug prescription switching. The rdrugtrajectory package has been made freely available via the GitHub repository.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.