Back

Off-label drug database

Grosjean, J.; Letord, C.; Zana, I.; Advenier-Iakovlev, E.; Duclos, C.; Krebs, M.-O.; Charlet, J.; Darmoni, S. J.

2021-11-30 health informatics
10.1101/2021.11.25.21266864 medRxiv
Show abstract

BackgroundMany drugs are still being prescribed in a "off-label mode" and especially in psychiatry. Off-label prescription situations may vary depending on several factors and such practice is not well identifiable in the literature. Methods: A new public academic drug database has been recently created and is able to contain off-label indications, especially in psychiatry in the context of the PSYHAMM French research project. For each situation, bibliographic references have been collected to make the scientific information available to all. Results: this new off-label drug database contains more than 18,154 lines. It is freely available at https://www.hetop.eu/hetop/medicaments. Several off-label usages have been formally described and the system is extensible to all drugs and all specialties. Conclusion: An off-label drug database can be a valuable tool for health professionals and students.

Matching journals

The top 12 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.