Our post hoc analysis of the discrimination performance of risk prediction models using disease-specific age and sex coefficients supports the importance of having more tailored risk algorithms.
Furthermore, models using laboratory data, vital signs, and other clinical findings provided better predictions of mortality [ 12– 15], and models using disease-specific diagnostic tests and treatments have been introduced for some diseases [ 16– 16].
An interesting pattern emerged in that analyses better supported mediation models involving physical functioning (in part due to the more consistent association of physical functioning with pain frequency) and models using disease-related parenting stress as mediator.
Quite unexpectedly, generating mouse models using conditional approaches as well as GAA-based mouse models (Puccio et al., 2001; Miranda et al., 2002; Al-Mahdawi et al., 2006) was more successful than the design of stable cellular models using disease-relevant cell types.
Also the analysis and development of risk stratification models – for example, using disease severity scores [ 17, 18] – could be a productive next step.
The resulting impacts on mortality in the UK have been modelled using disease-specific time lag curves.
Therefore, we constructed a theoretical decision analytic model using disease-specific information for COPD, to begin to assist COPD patients and their health care providers in the discussion of AD.
In the arthritis model used, disease develops in most mice strains, avoiding multiple breeding into arthritis susceptible strains.
These observations indicated that the statistical models trained using disease nsSNVs (e.g., EvoD, PolyPhen-2, and SIFT) are not suitable for diagnosing DR-affecting nsSNVs.
Indeed, in later work (unpublished) in which we built classification models using later disease stages for the model development set, we did identify patterns strongly predictive of ovarian cancer.
