Prevent hospitalization, stroke and coronary heart diseases

By knowing your risk you will be able to:

Description of image

Manage your health indicators


Description of image

Reach your goals


Description of image

Get better health



Risk prediction has been an important element in modern healthcare. It gives clinicians and patients insights that prompt actions, from giving preventative interventions to informing self-management. As a unique function, DiabeticLink provides two scientific approaches to profile patient’s risk. Both tools are based on results published in scientific journals. One predicts the 5-year risks of stroke and coronary heart disease (CHD) based on the U.K. Prospective Diabetes Study (UKPDS). The other predicts the risk of diabetes-induced hospitalization based on the research in the Artificial Intelligence (AI) Lab at the University of Arizona.
We identify a set of variables based on diabetes care guidelines. Run the experiment using about 2K patients. Get the estimated hazard ratio from the model. Use the variables with significant hazard ratio (that is, significantly greater than one) to calculate the risk. There are two types of risk engines we are demonstrating here:
  • Stroke and CHD Risk Prediction (UKPDS)
  • Diabetes-induced Hospitalization Risk Prediction (AI Lab at the University of Arizona)
All the information presented in our risk prediction tools are not intended to replace professional clinical judgment. Patients should consult with medical professionals for better interpretation and use of our risk predictions.
For more information about the UKPDS risk engine, see:
  • Stevens, R. J., Kothari, V., Adler, A. I., and Stratton, I. M. 2001. The UKPDS risk engine: a model for the risk of coronary heart disease in Type II diabetes (UKPDS 56). Clinical Science 101(6) 671–679.
  • Kothari, V., Stevens, R. J., Adler, A. I., Stratton, I. M., Manley, S. E., Neil, H. A., and Holman, R. R. 2002. UKPDS 60: risk of stroke in type 2 diabetes estimated by the UK Prospective Diabetes Study risk engine. Stroke; a journal of cerebral circulation 33(7) 1776–1781.
For more information about AI Lab’s hospitalization risk prediction, see:
  • Lin, Y.-K., Chen, H., Brown, R. A., Li, S.-H., and Yang, H.-J. 2014. Time-to-Event Predictive Modeling for Chronic Conditions using Electronic Health Records. IEEE Intelligent Systems Forthcoming.