Discovering Disease Associations Using Electronic Health Records
Author Information
Author(s): Antony B. Holmes, Alexander Hawson, Feng Liu, Carol Friedman, Hossein Khiabanian, Raul Rabadan, Andrey Rzhetsky
Primary Institution: Columbia University College of Physicians and Surgeons
Hypothesis
Can integrating electronic clinical data with medical literature help identify disease associations?
Conclusion
The study successfully identified significant associations between Kawasaki disease and autistic disorder, among other findings.
Supporting Evidence
- ADAMS identified a statistically significant association between Kawasaki disease and autistic disorder.
- The study utilized a large dataset from electronic health records to find disease associations.
- Integration of multiple data sources improved the identification of rare disease co-morbidities.
Takeaway
The researchers used a computer program to look at patient records and medical articles to find connections between rare diseases and other health issues.
Methodology
The study used an application called ADAMS to analyze electronic health records and compare them with data from PubMed and Wikipedia.
Potential Biases
Data entry inconsistencies and the specific demographics of the NYPH patient population may affect the results.
Limitations
The study is limited by biases in the electronic health records and the specific patient population at NYPH.
Participant Demographics
Patients from New York-Presbyterian Hospital, primarily representing the population of New York City.
Statistical Information
P-Value
0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website