Tokenized product information for centrally approved medicines within EU (extracted May 3, 2022)
SND-ID: 2022-157-1. Version: 1. DOI: https://doi.org/10.57804/ggrw-hr06
Associated documentation
Download all files
Citation
Creator/Principal investigator(s)
Gabriel Westman
- Uppsala University
Research principal
Uppsala University
- Department of Medical Sciences
Description
The text corpus was compiled on May 3, 2022, by scripted downloading of all available English language product information files for all centrally approved medicinal products within the EU, from the European Medicines Agency website. Package Leaflet (PL) and Summary of product characteristics (SmPC) documents for each medicinal product, excluding multiplicate documents for medicinal products with more than one strength or pharmaceutical preparation, were used. The PDF files were scraped using the pdfplumber version 0.6.1 package in Python 3.8.10 to extract all text except page numbering, headers, and footers.
Line breaks and special characters (excluding punctuation characters) were removed, and punctuation was added to sentences where this was missing (such as headings) to avoid false aggregation. All paragraphs were tokenized on a sentence level using the Natural Language Toolkit (NLTK) version 3.7 tokenizer
This database contains sentence-level tokenized product infomation from all centrally approved medicinal products within the EU (May 3, 2022) including Summary of product characterist
Line breaks and special characters (excluding punctuation characters) were removed, and punctuation was added to sentences where this was missing (such as headings) to avoid false aggregation. All paragraphs were tokenized on a sentence level using the Natural Language Toolkit (NLTK) version 3.7 tokenizer
This database contains sentence-level tokenized product infomation from all centrally approved medicinal products within the EU (May 3, 2022) including Summary of product characteristics (SmPC) and Package leaflet (PL) documents.
A total of 1258 medicinal products were initially included, of which 5 were subsequently excluded due to document compatibility issues. From these, a total of 783 K sentences were extracted from PL and SmPC documents. Show less..
Data contains personal data
No
Language
Population
All centrally approved medicinal products within EU
Study design
Observational study
Description of study design
Health informatics study on information about approved medicinal products.
Data format / data structure
Responsible department/unit
Department of Medical Sciences
Commissioning organisation
Swedish Medical Products Agency
Research area
Computer and information science (Standard för svensk indelning av forskningsämnen 2011)
Basic medicine (Standard för svensk indelning av forskningsämnen 2011)
Bergman E, Sherwood K, Forslund M, Arlett P, Westman G (2022) A natural language processing approach towards harmonisation of European medicinal product information. PLoS ONE 17(10): e0275386. https://doi.org/10.1371/journal.pone.0275386
DOI:
https://doi.org/10.1371/journal.pone.0275386
If you have published anything based on these data, please notify us with a reference to your publication(s). If you are responsible for the catalogue entry, you can update the metadata/data description in DORIS.
