Clinical trial demand forecasting
TrialSupply's demand forecasting turns patient enrollment projections, site activation timing, treatment arms, and dosing schedules into a monthly drug demand forecast — in a spreadsheet-style interface, with the calculation logic handled by the product instead of cell formulas.
From enrollment assumptions to drug demand
A clinical demand forecast is only as good as the assumptions underneath it, so TrialSupply makes those assumptions first-class, structured inputs rather than numbers buried in a workbook:
- Patient enrollment projections — how many patients each month, entered and revised in a familiar monthly grid.
- Site activation counts — when sites come online, which drives when regional demand starts.
- Treatment arm modeling — randomization ratios that split enrolled patients across arms.
- Dosing schedules — how each arm's patients convert into dispensing events, month by month, over their time on study.
From these inputs, TrialSupply calculates drug demand by product and by month. Because the model is structured, the same inputs also drive depot-level demand aggregation for supply planning — there is no separate reconciliation step between the clinical view and the supply view.
Forecasts that stay current
In an Excel-based process, re-forecasting is a project: copy the workbook, update the tabs, hope the formulas survive. In TrialSupply, the first forecast is generated deliberately, and after that any change to a forecast input — enrollment, arms, dosing — recalculates the demand forecast automatically. The plan you are looking at always reflects the assumptions you have entered.
Forecast accuracy, measured
Every forecast is snapshotted, so you can compare what you projected against actual enrollment as it comes in. Forecast-vs-actual tracking turns the monthly CD&OP review from a debate about whose spreadsheet is right into a discussion of why the assumptions moved — which is where planning teams actually improve.