Blood clots often form in the veins of the legs or in the lungs. They are usually treated with “blood thinning” drugs called anticoagulants. Guidelines recommend treatment for 3-6 months for some patients and longer for others. The general recommendation is that all patients receive at least 3 months of anticoagulation. After stopping anticoagulants blood clots are more likely to recur, whilst taking anticoagulants patients are more likely to have bleeding complications. The balance between continuing or stopping anticoagulants is clear for some patients but not for others where the risks and benefits may be more closely balanced. Our aim is to be able to predict more accurately the risks and benefits of stopping anticoagulation after 3-6 months or continuing anticoagulation for a longer period of time.
Venous thromboembolism (VTE) which consists of deep vein thrombosis (DVT) and pulmonary embolism (PE) is a common cause of morbidity and mortality. Many guidelines divide the anticoagulation (AC) therapy of VTE into various phases of treatment following the initial diagnosis, the acute phase for the first 1-2 weeks, the long-term treatment phase for 3-6 months, and the extended phase after the first 3-6months. Treatment duration is mainly based upon the risk of recurrence of VTE (R-VTE). The recommendation is that patients receive at least 3 months of anticoagulation. Patients at high risk of recurrence are offered extended anticoagulation. The risk of bleeding, unless very high, is not usually a major part of that calculation. Bleeding risks are considered separately and are loosely based on accumulating risks from data derived in both VTE and atrial fibrillation patients. Currently, insufficient data exist to support the integration of bleeding risk into duration of therapy planning and a combination of clinical insight, patient prothrombotic factors and patient choice informs anticoagulation duration.
An approach that allows clinicians to determine the duration of therapy right from the outset, and updates as new risks appear, as opposed to making the decision at a second consultation at 3 or 6 months, could render better treatment planning and patient education, as well as freeing up the clinic appointment time slots for other cases and be cost effective at the same time.
We aim to use baseline and time variable data in undertaking standard and machine learning methodology to develop and evaluate a novel risk prediction algorithm. Our algorithm will estimate risks of R-VTE and Clinically Significant Bleeding (CSB) in two scenarios: with AC continuation and with AC discontinuation, and thus may help clinicians in their decisions to determine which DVT & PE patients to place on extended AC.
VTE recurrences (R-VTE); major bleeding and clinically-relevant non-major bleeding requiring hospitalization (CRNMB-H).
Kevin Pollock - Chief Investigator - Bristol-Myers Squibb Pharmaceuticals Limited - UK ( BMS )
Carlos Martinez - Corresponding Applicant - Institute for Epidemiology, Statistics and Informatics GmbH (Pharma Epi)
Alexander Cohen - Collaborator - King's College London (KCL)
Amaia Irizar - Collaborator - Forecom Bioscience Ltd
Christopher Wallenhorst - Collaborator - Institute for Epidemiology, Statistics and Informatics GmbH (Pharma Epi)
Hanna Kew - Collaborator - Bristol-Myers Squibb Pharmaceuticals Limited - UK ( BMS )
Imran Khan - Collaborator - Pfizer Ltd - UK
Mikel Bober - Collaborator - Forecom Bioscience Ltd
Miroslaw Bober - Collaborator - University of Surrey
Satarupa Choudhuri - Collaborator - NHS England
Stephan Rietbrock - Collaborator - Institute for Epidemiology, Statistics and Informatics GmbH (Pharma Epi)
Susan Miller - Collaborator - Pfizer Ltd - UK
Zbigniew Galias - Collaborator - Forecom Bioscience Ltd
Amaia Irizar - Collaborator - Forecom Bioscience Ltd
Alexander Cohen - Collaborator - King's College London (KCL)
Christopher Wallenhorst - Collaborator - Institute for Epidemiology, Statistics and Informatics GmbH (Pharma Epi)
Hanna Kew - Collaborator - Bristol-Myers Squibb Pharmaceuticals Limited - UK ( BMS )
Imran Khan - Collaborator - Pfizer Ltd - UK
Kevin Pollock - Collaborator - Bristol-Myers Squibb Pharmaceuticals Limited - UK ( BMS )
Miroslaw Bober - Collaborator - University of Surrey
Mikel Bober - Collaborator - Forecom Bioscience Ltd
Stephan Rietbrock - Collaborator - Institute for Epidemiology, Statistics and Informatics GmbH (Pharma Epi)
Susan Miller - Collaborator - Pfizer Ltd - UK
Zbigniew Galias - Collaborator - Forecom Bioscience Ltd
HES Admitted Patient Care;HES Diagnostic Imaging Dataset;HES Outpatient;ONS Death Registration Data;Patient Level Index of Multiple Deprivation