We want to be fully transparent regarding the underlying calculations for the standard algorithm types that Evidencio supports. This page lists our standard algorithm types and the associated calculations
Linear regression algorithms are used to predict continuous outcomes. The prediction is estimated by:
predicted result P=β0+Xβ
Logistic regression algorithms are used to predict probabilities. The prediction is estimated by:
predicted probability P=eXβ1+eXβ
Cox proportional-hazards algorithms are used to predict the probability S(t) that the patient will be free from an event (e.g. biochemical recurrence) at some time point (e.g. 5 years after surgery). For survival analysis the prediction is estimated by: S(t)=S0(t)exp(Xβ)
Users can define Custom calculations based on custom mathematical formulas expressed in terms of algorithm
variables. Evidencio supports both single and conditional custom formulas. The custom formula(s) used by an
Evidencio algorithm can always be viewed in the details section of the respective algorithm, so that algorithm users can exactly
identify the underlying algorithm logic.
Example of conditional formulas:
Evidencio supports the use of R-Script code to define the calculation logic for prediction algorithms and calculators. R-Script algorithms may contain complex and nested functions as long as they produce a single value outcome.
Evidencio lets you define variable/parameter transformations for each continuous algorithm variable, for instance to accommodate non linear behaviour. We support both simple transformations as well as conditional (range based) transformations (e.g. cubic splines) to tackle a broad spectrum of non-linear behaviour.
You can attribute confidence interval data to your algorithms on Evidencio. Your confidence interval data can be specified in terms of a bootstrap data-set or as covariance matrix. You can simply copy paste your bootstrap or matrix data from e.g. excel or another data-sheet.
β0 | Intercept term, denoted by "Intercept" |
βvarN | Coefficient estimate, associated with a covariate/variable |
γ | Scaling parameter in survival regression algorithms, denoted by "Scaling Parameter" |
Xβ | Algorithm linear predictor, estimated by summation of the intercept term and all β values multiplied by that variable. E.g.: β0+βvar1⋅var1+βvar2⋅var2+βvarN⋅varN |
S0(t) | The baseline survival function, the survival proportion when all covariates are equal to zero (Xβ=0). |
Please enter a password
A password has to be at least 8 characters.
A password cannot be longer then 64 characters.
Choose a password with at least one capital letter.
Choose a password with at least one special character (@$!%*#?&)
Please agree to the Terms & Conditions and the Disclaimer
Please provide your e-mail address and we'll send you a link to reset your password.
Email Address
Please enter a valid email
If an account was registered with this email address you will receive a recovery link in your mail.
Please use the reset password link in it to set your new password.
Didn't receive the email yet? Please check your spam folder, or resend the email.