Autoimmune Disease Classification Based on PubMed Text Mining

Hadas Samuels, Malki Malov, Trishna Saha Detroja, Karin Ben Zaken, Naamah Bloch, Meital Gal-Tanamy, Orly Avni, Baruh Polis, Abraham O. Samson

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Autoimmune diseases (AIDs) are often co-associated, and about 25% of patients with one AID tend to develop other comorbid AIDs. Here, we employ the power of datamining to predict the comorbidity of AIDs based on their normalized co-citation in PubMed. First, we validate our technique in a test dataset using earlier-reported comorbidities of seven knowns AIDs. Notably, the prediction correlates well with comorbidity (R = 0.91) and validates our methodology. Then, we predict the association of 100 AIDs and classify them using principal component analysis. Our results are helpful in classifying AIDs into one of the following systems: (1) gastrointestinal, (2) neuronal, (3) eye, (4) cutaneous, (5) musculoskeletal, (6) kidneys and lungs, (7) cardiovascular, (8) hematopoietic, (9) endocrine, and (10) multiple. Our classification agrees with experimentally based taxonomy and ranks AID according to affected systems and gender. Some AIDs are unclassified and do not associate well with other AIDs. Interestingly, Alzheimer’s disease correlates well with other AIDs such as multiple sclerosis. Finally, our results generate a network classification of autoimmune diseases based on PubMed text mining and help map this medical universe. Our results are expected to assist healthcare workers in diagnosing comorbidity in patients with an autoimmune disease, and to help researchers in identifying common genetic, environmental, and autoimmune mechanisms.

Original languageEnglish
Article number4345
JournalJournal of Clinical Medicine
Issue number15
StatePublished - Aug 2022

Bibliographical note

Publisher Copyright:
© 2022 by the authors.


  • Alzheimer’s disease
  • PubMed
  • autoimmune disease
  • classification
  • frequency analysis
  • list of autoimmune diseases
  • taxonomy
  • text mining


Dive into the research topics of 'Autoimmune Disease Classification Based on PubMed Text Mining'. Together they form a unique fingerprint.

Cite this