Type II Diabetes Mellitus Predictor

Prediction Tool   Paper   About   Contact   References   Research Team

Abstract: The Type II Diabetes Mellitus Predictor is an online tool that can be used to calculate a user’s risk of developing Type II Diabetes Mellitus (T2DM). The risk prediction is based on the user’s input of medical lab information such as age, sex, body mass index, fasting blood sugar, triglycerides, and high-density lipoprotein levels. The calculator is modelled using a logistic regression model, and has been trained using the medical records of over ten thousand Canadian patients. This newly developed tool is intended to serve physicians and patients in predicting future diabetes risk and take early preventive measures.

• Xin Gao (PhD) is a professor at the Department of Mathematics and Statistics, York University, Toronto, Ontario, Canada.
  Email: xingao@yorku.ca
• Huaxiong Huang (PhD) is a professor at the Department of Mathematics and Statistics, York University and is the Deputy Director of the Fields Institute for Research in Mathematical Sciences, Toronto, Ontario, Canada.
  Email: hhuang@yorku.ca
• Aziz Guergachi (PhD) is a professor at Ted Rogers School of Management - Information Technology Management, Ryerson University and an adjunct professor at the Department of Mathematics and Statistics, York University, Toronto, Ontario, Canada.
  Email: a2guerga@ryerson.ca
• Karim Keshavjee (MD, MBA) is an adjunct professor and a practicing clinical IT architect at the Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.
  Email: karim.keshavjee@ryerson.ca
• Hang Lai (MSc, MA) is a PhD student at the Department of Mathematics and Statistics, York University, and a sessional lecturer at the University of Guelph Humber, Toronto, Ontario, Canada
  Email: hang68@yorku.ca
• Konstantinos Ntentes (MA) completed his Master's degree at the Department of Mathematics and Statistics, York University and is currently working as a data analyst at CitiIQ in Toronto, Ontario.
  Email: kntentes@yorku.ca
• Gian Alix (BSc) is an undergraduate BSc student at the Department of Electrical Engineering and Computer Science & Department of Mathematics and Statistics, York University, Toronto, Ontario, Canada.
  Email: gian.alix@gmail.com

Version 4.0 (Oct 27, 2020)

• Unit conversion to mg/dL bug fixes (for HDL/Triglycerides)
• Updated contacts (email addresses)
• Updated the about page (abstract)
• Updated reference format (according to CJD guidelines)
• Updated the disclaimer and warnings
• Updated ranges
• Updated the messages
• Changed to https://galix.me/t2dm/calc.html
• Cleaned code
• Removed password; ready for launch!

Version 3.3/3.4 (Oct 18, 2020)

• Small bug fixes

Version 3.2 (Oct 13, 2020)

• Minor fixes ("Professor Labs" to "Research Team" in the menu; also the message results were fixed up a little, title change)

Version 3.1 (Oct 11, 2020)

• Fixed minor typographical issues
• Consolidated all 4 professor's labs into one "Professor's Labs"

Version 3.0 (Oct 03, 2020)

• Updated the warning section
• Removed Confidence Interval and Onset Time boxes as these features will not materialize in future versions
• Updated the layout of the Checkbox and Submit button
• Moved the "Developer Notes" to the footer section
• Added the labs (websites) for the different professors involved in this study
• Added contacts
• Made some corrections on typographical errors

Version 2.0 (Aug 30, 2020)

• Reworked the layout of the site
• Included menu bar
• Reinforced data validation
• Linked the paper cited
• Added an "About" Section
• Added the "Contacts" Section
• Added a "References" page
• Link to the Gao Lab
• Added icons/steps
• Range of values considered in the input fields
• Units taken into account
• Text field for results changed to text area
• Checkbox options added that allows the user what can be displayed (risk, confidence interval, etc.); note: onset time is still not available in v2.0

Version 1.0 (Aug 23, 2020)

• Draft of Website

Lai H, Huang H, Keshavjee K, Guergachi A, Gao X. Predictive models for diabetes mellitus using machine learning techniques. BMC Endocrine Disorders 2019; 19:101. https://doi.org/10.1186/s12902-019-0436-6 [accessed: 20.08.05].