Qian Li1, Jing Wang2, Huan Tao3, Qin Zhou4, Jie Chen5, Bo Fu6, WenZhe Qin7, Dong Li8, JiangLong Hou8, Jin Chen9, Wei-Hong Zhang10,11. 1. Department of Evidence-Based Medicine and Clinical Epidemiology, West China Hospital, Sichuan University, Guo Xue Xiang 37#, Chengdu, 610041, Sichuan, China. 2. Department of Career Development Division, The Fourth Affiliated Hospital of Anhui Medical University, Hefei, China. 3. Department of Hematology, West China Hospital, Sichuan University, Chengdu, China. 4. Department of Nutrition, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, China. 5. Department of Anesthesiology, China Mianyang Central Hospital, Mianyang, China. 6. Department of Cardiovascular Surgery, Tianjin Central Hospital, Tianjin, China. 7. Department of Social Medicine and Health Management, Shandong University, Jinan, China. 8. Department of Cardiovascular Surgery, West China Hospital, Sichuan University, Chengdu, China. 9. Department of Evidence-Based Medicine and Clinical Epidemiology, West China Hospital, Sichuan University, Guo Xue Xiang 37#, Chengdu, 610041, Sichuan, China. ebm_chenjin@126.com. 10. Department of Research Laboratory for Human Reproduction, Faculty of Medicine and School of Public Health, Université Libre de Bruxelles (ULB), Brussels, Belgium. 11. International Centre for Reproductive Health (ICRH), Department of Public Health and Primary Care, Ghent University, Ghent, Belgium.
Abstract
BACKGROUND AND OBJECTIVE: Because of the narrow therapeutic window and huge inter-individual variation, the individual precision on anticoagulant therapy of warfarin is challenging. In our study, we aimed to construct a Back Propagation Neural Network (BPNN) model to predict the individual warfarin maintenance dose among Chinese patients who have undergone heart valve replacement, and validate its prediction accuracy. METHODS: In this study, we analyzed 13,639 eligible patients extracted from the Chinese Low Intensity Anticoagulant Therapy after Heart Valve Replacement database, which collected data on patients using warfarin after heart valve replacement from 15 centers all over China. Ten percent of patients who were finally enrolled in the database were used as the external validation, while the remaining were randomly divided into the training and internal validation groups at a ratio of 3:1. Input variables were selected by univariate analysis of the general linear model; 2.0, the mean value of the international normalized ratio (INR) range 1.5-2.5, was used as the mandatory variable. The BPNN model and the multiple linear regression (MLR) model were constructed by the training group and validated through comparisons of the mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and ideal predicted percentage. RESULTS: Finally, 10 input variables were selected and a three-layer BPNN model was constructed. In the BPNN model, the value of MAE (0.688 mg/day and 0.740 mg/day in internal and external validation, respectively), MSE (0.580 mg/day and 0.599 mg/day in internal and external validation, respectively), and RMSE (0.761 mg/day and 0.774 mg/day in internal and external validation, respectively) were achieved. Ideal predicted percentages were high in both internal (63.0%) and external validation (59.7%), respectively. Compared with the MLR model, the BPNN model showed a higher ideal prediction percentage in the external validation group (59.7% vs. 56.6%), and showed the best prediction accuracy in the intermediate-dose subgroup (internal validation group: 85.2%; external validation group: 84.7%) and a high predicted percentage in the high-dose subgroup (internal validation group: 36.2%; external validation group: 39.8%), but poor performance in the low-dose subgroup (internal validation group: 0%; external validation group: 0.3%). Meanwhile, the BPNN model showed better ideal prediction percentage in the high-dose group than the MLR model (internal validation: 36.2% vs. 31.6%; external validation: 42.8% vs. 37.8%). CONCLUSION: The BPNN model shows promise for predicting the warfarin maintenance dose after heart valve replacement.
RCT Entities:
BACKGROUND AND OBJECTIVE: Because of the narrow therapeutic window and huge inter-individual variation, the individual precision on anticoagulant therapy of warfarin is challenging. In our study, we aimed to construct a Back Propagation Neural Network (BPNN) model to predict the individual warfarin maintenance dose among Chinese patients who have undergone heart valve replacement, and validate its prediction accuracy. METHODS: In this study, we analyzed 13,639 eligible patients extracted from the Chinese Low Intensity Anticoagulant Therapy after Heart Valve Replacement database, which collected data on patients using warfarin after heart valve replacement from 15 centers all over China. Ten percent of patients who were finally enrolled in the database were used as the external validation, while the remaining were randomly divided into the training and internal validation groups at a ratio of 3:1. Input variables were selected by univariate analysis of the general linear model; 2.0, the mean value of the international normalized ratio (INR) range 1.5-2.5, was used as the mandatory variable. The BPNN model and the multiple linear regression (MLR) model were constructed by the training group and validated through comparisons of the mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and ideal predicted percentage. RESULTS: Finally, 10 input variables were selected and a three-layer BPNN model was constructed. In the BPNN model, the value of MAE (0.688 mg/day and 0.740 mg/day in internal and external validation, respectively), MSE (0.580 mg/day and 0.599 mg/day in internal and external validation, respectively), and RMSE (0.761 mg/day and 0.774 mg/day in internal and external validation, respectively) were achieved. Ideal predicted percentages were high in both internal (63.0%) and external validation (59.7%), respectively. Compared with the MLR model, the BPNN model showed a higher ideal prediction percentage in the external validation group (59.7% vs. 56.6%), and showed the best prediction accuracy in the intermediate-dose subgroup (internal validation group: 85.2%; external validation group: 84.7%) and a high predicted percentage in the high-dose subgroup (internal validation group: 36.2%; external validation group: 39.8%), but poor performance in the low-dose subgroup (internal validation group: 0%; external validation group: 0.3%). Meanwhile, the BPNN model showed better ideal prediction percentage in the high-dose group than the MLR model (internal validation: 36.2% vs. 31.6%; external validation: 42.8% vs. 37.8%). CONCLUSION: The BPNN model shows promise for predicting the warfarin maintenance dose after heart valve replacement.
Authors: Karel G M Moons; Andre Pascal Kengne; Diederick E Grobbee; Patrick Royston; Yvonne Vergouwe; Douglas G Altman; Mark Woodward Journal: Heart Date: 2012-03-07 Impact factor: 5.994
Authors: P Lenzini; M Wadelius; S Kimmel; J L Anderson; A L Jorgensen; M Pirmohamed; M D Caldwell; N Limdi; J K Burmester; M B Dowd; P Angchaisuksiri; A R Bass; J Chen; N Eriksson; A Rane; J D Lindh; J F Carlquist; B D Horne; G Grice; P E Milligan; C Eby; J Shin; H Kim; D Kurnik; C M Stein; G McMillin; R C Pendleton; R L Berg; P Deloukas; B F Gage Journal: Clin Pharmacol Ther Date: 2010-04-07 Impact factor: 6.875
Authors: Nita A Limdi; T Mark Beasley; Melissa F Baird; Joyce A Goldstein; Gerald McGwin; Donna K Arnett; Ronald T Acton; Michael Allon Journal: J Am Soc Nephrol Date: 2009-02-18 Impact factor: 10.121
Authors: Giovanni Di Minno; Anna Russolillo; Carminio Gambacorta; Alessandro Di Minno; Domenico Prisco Journal: Eur J Intern Med Date: 2013-04-08 Impact factor: 4.487