Diseases And Symptoms

Dataset created using https://people.dbmi.columbia.edu/~friedma/Projects/DiseaseSymptomKB/
Applied appropriate transformations and edits to make it more usable.

"This table below is a knowledge database of disease-symptom associations generated by an automated method based on information in textual discharge summaries of patients at New York Presbyterian Hospital admitted during 2004. The first column shows the disease, the second the number of discharge summaries containing a positive and current mention of the disease, and the associated symptom. Associations for the 150 most frequent diseases based on these notes were computed and the symptoms are shown ranked based on the strength of association. The method used the MedLEE natural language processing system to obtain UMLS codes for diseases and symptoms from the notes; then statistical methods based on frequencies and co-occurrences were used to obtain the associations. A more detailed description of the automated method can be found in Wang X, Chused A, Elhadad N, Friedman C, Markatou M. Automated knowledge acquisition from clinical reports. AMIA Annu Symp Proc. 2008. p. 783-7. PMCID: PMC2656103."

main.csv

• 408 columns depicting the symptoms + 1 of frequency of occurence
• 134 rows columns representing diseases
  Metadata for each symptom/column can be found from https://www.nlm.nih.gov/research/umls/index.html