Background Prothrombinex-VF is being increasingly used as an off-label therapy to correct non-warfarin-related elevations in international normalised ratio (INR) in the critically ill. Currently there are no dosing guidelines for such use. Aims To validate a prediction equation, embedded in a smartphone application (app), to guide dosing of Prothrombinex-VF in critically ill patients. Methods A prospective pilot cohort study of critically ill adult patients with elevated INRs who were treated with Prothrombinex-VF. The main outcome measured was INR following Prothrombinex-VF administration. Results Of the 31 patients included, five (16%) were taking warfarin prior to admission and 14 (45%) had chronic liver disease. There was a significant decrease in INR after Prothrombinex-VF treatment (P < 0.001) and a significant correlation between the app's predicted INRs and the measured INRs (r = 0.63 and P < 0.001). The app's predicted INRs were less accurate for patients with chronic liver disease than for those without. Overall, the app's recommendations achieved an INR either similar to (29.6%) or better than (55.6%) what would have been achieved had the warfarin reversal guidelines been applied to dose the Prothrombinex-VF. Conclusion The app appeared to be reasonably accurate at predicting normalisation of elevated INRs after administration of Prothrombinex-VF, especially among patients without liver disease. Its dosing recommendations were similar to or possibly better than preexisting warfarin reversal guidelines in over 85% of the situations analysed, if we assume a higher dose of Prothrombinex-VF would achieve a greater reduction in INR than a lower dose.