Medscript Drug Dataset: Normalized Medicine Names for Prescription Processing

Cleaned and consolidated medicine names from multiple sources, including product datasets and drug lists. The dataset was created by author hashan-7 and last updated on April 14, 2026. It is designed for prescription OCR post-processing and drug name matching.

Use Cases

• Post-processing OCR output from scanned prescriptions based on normalized drug names.
• Matching drug entities in clinical text or databases based on cleaned medicine name strings.
• Deduplicating drug name entries in pharmacy or healthcare records based on the described cleaning process.

Strengths

• Data is cleaned and normalized, with steps including conversion to lowercase and whitespace trimming.
• Consolidated from multiple named sources, including product dataset and drug_database.csv.

Limitations

• Row count, column details beyond 'drug_name', and file formats are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• License information is unknown, which may restrict usage.

Provenance

Source

Multiple sources including product dataset, drug_database.csv, massive_drug_list.csv, and sl_drugs dataset.

Collection Method

Data was cleaned and consolidated, with processing steps including lowercase conversion, whitespace trimming, and duplicate removal.

Freshness

Last updated 2026-04-14 20:08:50; freshness should be verified.