Optimizing the dynamic treatment regime of in-hospital warfarin anticoagulation in patients after surgical valve replacement using reinforcement learning.
Juntong ZengJianzhun ShaoShen LinHongchang ZhangXiaoting SuXiaocong LianYan ZhaoXiangyang JiZhe ZhengPublished in: Journal of the American Medical Informatics Association : JAMIA (2022)
An RL algorithm significantly optimized the post-operation warfarin anticoagulation quality compared with clinicians' actual practice, suggesting its potential for challenging sequential decision-making tasks.
Keyphrases
- atrial fibrillation
- venous thromboembolism
- end stage renal disease
- decision making
- healthcare
- direct oral anticoagulants
- ejection fraction
- chronic kidney disease
- newly diagnosed
- primary care
- machine learning
- aortic valve
- aortic stenosis
- quality improvement
- mitral valve
- oral anticoagulants
- peritoneal dialysis
- deep learning
- heart failure
- coronary artery disease