TreeAge Pro supports four types of Monte Carlo simulation.
- Patient Simulation (Microsimulation, "Trials" taking random walks)
- Probabilistic Sensitivity Analysis (PSA, Samples, parameter uncertainty)
- Probabilistic Sensitivity Analysis & Patient SImulation (1 & 2 together)
- Expected Value of Partial Perfect Information (EVPPI, PSA with distributions isolated)
Patient Simulation (aka Microsimulation, Trials)
Run individual patients through the model one-by-one rather than evaluating a homogeneous cohort of patients. Using individual patients expands your modeling capabilities to take advantage of data at the patient level. It allows you to use:
- Individual patient characteristics - for heterogeneity. Consider different ages, severity of illness etc.
- Patient events - for history of the patient which may impact future events, probabilities, costs etc.
Analysis can be examined at both the cohort and at the individual level.
Probabilistic Sensitivity Analysis (PSA, Samples)
Recalculate the model repeatedly using different input values to assess the impact of parameter uncertainty on models. Parameters of interest can be represented by distributions. Those distributions are resampled for each model calculation.
The resulting model analysis includes a large number of model recalculations, each based on a different set of parameter samples. It is common to look for the percentage of the iterations that confirm the base case results. The higher the percentage, the more confident we can be in our conclusions.
Probabilistic Sensitivity Analysis & Patients
This analysis technique combines the first two techniques described above. This generates Probabilistic Sensitivity Analysis (PSA) results for a model that depends on patient simulation.
Expected Value of Partial Perfect Information (EVPPI)
This is a special form of PSA that isolates the impact of one or more distributions from the remaining distributions being used for parameter uncertainty.
It is possible to run Patient Simulation with EVPPI resulting in three loops (outer PSA, inner PSA and patients).