A study by researchers at the Massachusetts Institute of Technology (MIT) and New York's Beth Israel Deaconess Medical Center indicates that health knowledge graphs, which show relationships between symptoms and diseases to help with clinical diagnosis, performed poorly for diseases with high percentages of very old or young patients or high percentages of male or female patients.
The researchers studied automatically generated health knowledge graphs based on real datasets comprising more than 270,000 patients with close to 200 diseases and more than 770 symptoms and analyzed how various models used electronic health record data to automatically "learn" patterns of disease-symptom correlations.
They hope to provide guidance about the relationship between dataset size, model specification, and performance.
Said MIT's Irene Y. Chen, "It is essential that we closely examine these graphs, so that they can be used as the first steps of a diagnostic tool."
From MIT News
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found