BACKGROUND: Oral anticoagulation with warfarin can lead to life-threatening events as a result of either over-anticoagulation or undertreatment. One of the main contributors to an undesirable warfarin effect is the need to adjust its daily dose for a specific patient. The dose is adjusted empirically based on the experience of the clinician, a method that is often imprecise. There is currently no other well-accepted method for predicting the maintenance dose of warfarin. OBJECTIVE: To describe the application of an artificial neural network to the problem of warfarin maintenance dose prediction. METHODS: We designed a neural network that predicts the maintenance dose of warfarin. Data on 148 patients attending a large anticoagulant clinic were collected by file review. Using correlational analysis of the patients' data we selected the best input variables. The network was trained by using the back-propagation algorithm on a subset of our data and the results were validated against the rest of the data. We used a multivariate linear regression to create a comparable model. RESULTS: The neural network generated reasonable predictions of the maintenance dose (r = 0.823). The results of the linear regression model were similar (r = 0.800). CONCLUSION: Neural networks can be applied successfully for warfarin maintenance dose prediction. The results are promising, but further investigation is needed.
BACKGROUND: Oral anticoagulation with warfarin can lead to life-threatening events as a result of either over-anticoagulation or undertreatment. One of the main contributors to an undesirable warfarin effect is the need to adjust its daily dose for a specific patient. The dose is adjusted empirically based on the experience of the clinician, a method that is often imprecise. There is currently no other well-accepted method for predicting the maintenance dose of warfarin. OBJECTIVE: To describe the application of an artificial neural network to the problem of warfarin maintenance dose prediction. METHODS: We designed a neural network that predicts the maintenance dose of warfarin. Data on 148 patients attending a large anticoagulant clinic were collected by file review. Using correlational analysis of the patients' data we selected the best input variables. The network was trained by using the back-propagation algorithm on a subset of our data and the results were validated against the rest of the data. We used a multivariate linear regression to create a comparable model. RESULTS: The neural network generated reasonable predictions of the maintenance dose (r = 0.823). The results of the linear regression model were similar (r = 0.800). CONCLUSION: Neural networks can be applied successfully for warfarin maintenance dose prediction. The results are promising, but further investigation is needed.