MEDI (MEDication Indication) is an ensemble medication indication resource for primary and secondary uses of electronic medical record (EMR) data. MEDI was created based on multiple commonly used medication resources (RxNorm, MedlinePlus, SIDER 4.1, Mayo Clinic, WebMD, and Wikipedia ) and by leveraging both ontology and natural language processing (NLP) techniques.
The current release of MEDI (MEDI-2) contains 3,031 medications and 186,064 indications, including both ICD-9-CM and ICD-10-CM indications pairs. Based on clinician review of MEDI-2, the estimated precision was 0.67 and recall was 0.95. The MEDI-2 high precision subset (HPS) includes indications found within either RxNorm or at least three other resources. MEDI-2 HPS contains 2,000 medications and 34,488 indication pairs with an estimated precision of 0.94. For additional details, please see references below.
The download of MEDI is for free. Right click and select the download linked file or similar option in your browser to save the files on your computer.
MEDI Downloads:
MEDI-C (MEDI-1 and 2 combined 2020)
- MEDI-C.csv – contains all medication-indication pairs from MEDI-1 and MEDI-2.
MEDI-2 (2020)
- MEDI-2.csv – contains all medication-indication pairs mapped to ICD-9-CM and ICD-10-CM.
- MEDI-2_HPS.csv – contains MEDI-2 high precision subset mapped to ICD-9-CM and ICD-10-CM.
- MEDI-2_UMLS.csv – contains all medication-indication pairs mapped to UMLS CUIs (useful for natural language processing).
MEDI-1 (2013)
- MEDI.csv
- MEDI_HPS.csv (High Precision Set)
- MEDI_UMLS.csv (including RxCUI, UMLS, ATC, NDDF concepts and their indications)
- MEDI_wPrevalence_Published.csv
Key references:
-
Wei WQ, Cronin RM, Xu H, Lasko TA, Bastarache L, Denny JC. Development and evaluation of an ensemble resource linking medications to their indications. Journal of the American Medical Informatics Association. 2013;20:954-961. doi:10.1136/amiajnl-2012-001431
-
Wei WQ, Mosley JD, et al. Validation and Enhancement of a Computable Medication Indication Resource (MEDI) Using a Large Practice-based Dataset. AMIA Annual Symposium, 2013, Washington DC.
-
Zheng NS, Kerchberger VS, Borza VA, Eken HN, Smith JC, Wei WQ. MEDI – a computable medication-indication resource for biomedical research. (Under review).
Changelog:
MEDI-2 (10/18/20)
- Added Mayo Clinic and WebMD as additional resources and updated other four resources (e.g., SIDER 4.1) for indication extraction.
- Indications are represented as UMLS CUIs as well as ICD-9-CM and ICD-10-CM codes.
MEDI-1 (2013)
- First release of MEDI built from information from four publicly available resources: RxNorm, MedlinePlus, SIDER 2, and Wikipedia
- Please refer to original paper for more details.
MEDI by Dr. Wei-Qi Wei & Dr. Joshua Denny is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.