Computer aided warfarin dosing in the Swedish national quality registry AuriculA – Algorithmic suggestions are performing better than manually changed doses

Warfarin treatment quality and prognosis in patients with mechanical heart valve prosthesis

“…The current results support and extend the results from a previous study from our group where TTR influenced the risk of bleedings and death, but not thromboembolic events, in patients with MHV 8. One way to increase TTR is using a computer-aided warfarin dosing system 21 22. Other important factors for a high TTR are patient information and compliance, which in Sweden is achieved at least partly due to a good organisation with outpatient clinics based on specialised nurses.…”

Warfarin treatment quality is consistently high in both anticoagulation clinics and primary care setting in Sweden

“…There is no support in our data that centralization of warfarin monitoring would be beneficial for the patients. Using a computer based system with a dosing algorithm for monitoring these patients might have assisted in achieving an effective warfarin treatment with high TTR and a low rate of complications in a non specialized setting [15]. AuriculA has been shown to improve TTR compared to manual dosing, but has not yet been tested against other computerised systems [16].…”

“…Provided that the patients have not declined to participate, data from the everyday clinical practice in the anticoagulation centers is recorded and transferred to the quality register automatically once every 24 hours. AuriculA also provides a clinical decision tool, aiding in the dosage of warfarin using a dosing algorithm [15]. If certain criteria are met, the algorithm can give a dose suggestion that can be accepted or manually changed.…”

Personalized anticoagulant management using reinforcement learning.

“…The current standard of care for warfarin oral anticoagulant therapy, as dictated by the American Society of Hematology, is an expert-system type algorithm that provides no dosing personalization and also does not explicitly optimize the monitoring frequency of the efficacy of the therapy (Cushman, Lim, & Zakai, 2011). While there are many other warfarin dosing algorithms that seek to improve the efficacy of warfarin therapy, including pharmacogenetic algorithms (Carlquist & Anderson, 2011) and computerized algorithms (Grzymala-Lubanski, Själander, Renlund, Svensson, & Själander, 2013;Dimberg, et al, 2012), these algorithms do a poor job of accounting for intra-patient variability (Kangelaris, Bent, Nussbaum, Garcia, & Tice, 2009) and do not explicitly optimize the monitoring frequency, which would reduce the overall cost of the therapy. Intra-patient variability during maintenance dosing can occur due to a variety of factors such as diet, disease state, and drug interactions.…”

“…These algorithms operate according to 720 rules and patient history to make dose suggestions (Grzymala-Lubanski, Själander, Renlund, Svensson, & Själander, 2013). While these algorithms have been successful in clinical practice, they require massive databases of patient information, and also, in the presence of high intra-patient variability, still require manual (physician initiated) dose changes.…”