This page contains supplementary material for the article:
G.I. Choudhary, P. Fränti, Predicting Onset of Disease Progression Using Temporal
Disease Occurrence Networks, International Journal of Medical Informatics (2023), doi: https://doi.org/10.1016/
j.ijmedinf.2023.105068
Disease Prediction
How Relative Risk is calculated:
- N
- Total number of patients
- p(A) = num(A)/N
- probability that a patient has a diagnosis A
- p(B) = num(B)/N
- probability that a patient has a diagnosis B
- observed
- Number of patients that have both diagnosis A and B. Where A happened before B.
- expected = p(A)⋅p(B)⋅N
- Relative Risk = observed/expected
Conditional probability:
p(B|A): If patient has diagnosis A, what is the probability that they also have diagnosis B. This takes
temporal occurrence account that A happened before B.