Warfarin, a classic oral anticoagulant, is characterized by a narrow therapeutic window and considerable interindividual variability in dosing requirements. This makes precise dose adjustment challenging in clinical practice and increases the risk of bleeding or thrombosis. To improve dose prediction, this study developed a streamlined multilayer perceptron (MLP) model using real-world data from the International Warfarin Pharmacogenomics Consortium (IWPC) database. The LASSO-proj algorithm was applied for high-precision feature selection prior to model construction. The resulting model demonstrated strong predictive performance on the test set, achieving a coefficient of determination (R2) of 0.456, a mean absolute error (MAE) of 8.92 mg/week, and 48.522% of its predictions falling within ±20% of the actual stable therapeutic dose. Through SHAP-based interpretation using DeepExplainer, key features influencing warfarin dosing were identified, including the VKORC1 genotype, body weight, age, and ethnicity. The interpretable MLP framework incorporating LASSO-proj not only maintains high predictive accuracy, but also significantly enhances model transparency, providing a valuable tool for guiding warfarin therapy.
ObjectiveTo investigate the influence of high activity of CYP2C9 (Cytochrome P450 proteins 2C9)and VKORC (Vitamin K epoxide reductase C)on warfarin anticoagulation of patients after heart valve replacement (HVR).
MethodsFrom February 2010 to May 2013, 40 patients with high activity of CYP2C9 and VKORC underwent HVR in the Department of Cardiac Surgery, the First Affiliated Hospital of Zhengzhou University. There were 18 male and 22 female patients with their age of 40-51 (45.18±2.93)years. There were18 patients receiving mitral valve replacement (MVR), 14 patients receiving MVR and tricuspid valvuloplasty (TVP), and 8 patients receiving double valve replacement (DVR). Depen-ding on whether they received preoperative genetic polymorphism detection of CYP2C9 and VKORC1, all the patients were divided into 2 groups with 20 patients in each group. Patients in group A didn't receive preoperative genetic polymorphism detection of CYP2C9 and VKORC1, while patients in group B received preoperative genetic polymorphism detection of CYP2C9 and VKORC1. Postoperatively, periodic examination of international normalized ratio (INR)was performed to adjust warfarin dosage. Time to reach expected INR value and morbidity were collected. All the patients were followed up for 3-12 months after discharge. Monthly telephone follow-up was performed to record INR values, morbidity and general recovery.
ResultsPostoperatively, in group A, 2 patients had cerebral infarction, 2 patients had popliteal artery throm-bosis, 1 patient had pulmonary embolism, and 1 patient had thrombosis in the annulus. Expected INR was achieved 15-20 days after warfarin treatment among the other 14 patients without thromboembolism. Three months after surgery, CYP2C9 and VKORC1 gene polymorphism was examined to find 17 patients with positive CYP2C9*1/*1 (*2CC/*3AA)and positive VKORC1-1639 GA, and 3 patients with positive CYP2C9*1/*1 (*2CC/*3AA)and positive VKORC1-1639 GG. In Group B, patients received aspirin (100 mg/d)and low molecular heparin (0.4 ml/d)in addition to warfarin since the second posto-perative day. Expected INR was achieved 5-9 days after warfarin treatment, and then aspirin and low molecular heparin were discontinued. During the 6 months follow-up period, no obvious thromboembolism was found, and only 1 patient had epistaxis who was cured with nasal tamponade.
ConclusionPreoperative detection of genetic polymorphisms of CYP2C9 and VKORC1 can provide important guidance for warfarin anticoagulation after HVR.
Objective
To investigate the diagnosis and treatment of pulmonary thromboembolism (PTE) after thoracotomy.
Methods
We analyzed the clinical data of 10 patients with PTE after thoracotomy treated from January 2011 to March 2015. Among them were 8 males and 2 females, with their age ranging from 51 to 73 years old, averaging 61. Six patients had lung cancer lobectomy, and 4 had esophagus carcinoma resection. All the 10 patients suffered sudden shortness of breath, chest pain and palpitation within the first 40 hours to 128 hours after surgery, and the physical examinations revealed tachypnea, drop of blood pressure and tachycardia. The PTE diagnosis was confirmed after using echocardiography, three-dimensional imaging of CT pulmonary angiography. All the patients accepted the treatment combination of low molecular weight heparin and warfarin.
Results
All the patients were cured without complications like chest or wound bleeding. Follow-up checks 3 months after the surgery showed no relapses.
Conclusions
Thoracotomy patients are of high risks of PTE. The diagnosis should be based on imaging examinations. Treatment combination of low molecular weight heparin and warfarin has a remarkable effect in treating PTE patients after thoracotomy, which also has a low rate of bleeding complications.
ObjectiveTo investigate the effect of CYP2C9 and APOE on the dose of stable warfarin and model prediction in Hainan population.MethodsFrom August 2016 to July 2018, 368 patients who required heart valve replacement and agreed to take warfarin anticoagulation at the second department of cardiothoracic surgery in our hospital were enrolled, including 152 males aged 48.5–70.5 (60.03±10.18) years and 216 females aged 43.5–65.6 (54.24±11.35) years. CYP2C9 and APOE were amplified by polymerase chain reaction. The gene fragment was sequenced by the Single Nucleotide Polymorphisms (SNP) site. The patients' age, sex, weight, history of smoking and drinking, and the dose of stable warfarin were recorded. Regression analysis of these clinical data was made to construct a dose prediction model.ResultsAmong 368 patients, CYP2C9 genotype test results showed 301 patients (81.8%) with *1*1 genotype, and 67 patients (18.2%) with *1*3 type. For different CYP2C9 genotype patients, the difference was statistically significant in the dose of stable warfarin (P<0.05). The results of APOE genotype showed 93 patients (25.3%) with E2 genotype, 221 patients (60.1%) with E3 genotype, and 54 patients (14.7%) with E4 genotype; the dose of stable warfarin in patients with different APOE genotypes was statistically significant (P<0.05). Multiple regression analysis showed that patients' age, body weight, and CYP2C9 and APOE genotypes were correlated with the dose of stable warfarin. The correlation coefficient R2 was 0.572, and the prediction model was statistically significant (P<0.05).ConclusionCYP2C9 and APOE gene polymorphisms exist in Hainan population. There is significant difference in the dose of stable warfarin among different genotypes of patients. The model to predict stable warfarin can partly explain the difference of warfarin among different patients.
ObjectivesTo compare different formula calculated dosages with the actual doses of warfarin from patients in Beijing Hospital so as to investigate suitable warfarin dosing models for Chinese patients.MethodsOne hundred and three Chinese patients with long-term prescription of warfarin were randomly selected from Beijing Hospital from July 2012 to May 2013. The CYP2C9 and VKROC1 genotypes and basic statistical information were collected. SPSS 18.0 software was used to compare the differences between different formula calculated dosages and the actual dosages of warfarin.ResultsFive genotypes were found in 103 patients, including: CYP2C9 AA genotype + VKORC1 AA genotype (n=72, 69.9%), CYP2C9 AA genotype + VKORC1 AG genotype (n=17, 16.5%), CYP2C9 AC genotype + VKORC1 AA genotype (n=10, 9.7%), CYP2C9 AC genotype + VKORC1 AG genotype (n=3, 2.9%) and CYP2C9 AA genotype + VKORC1 GG genotype (n=1, 1%). Compared with the actual dosages of warfarin, the degree of coincidence was highest for dosages calculated by Jeffrey’s formula.Conclusions Using Jeffrey’s formula to calculate warfarin dosages may be more suitable for Chinese patients with using long-term warfarin. Due to limited sample size, prospective and large sample size studies are required to verify the above conclusion.
Abstract: Objective To investigate the anticoagulation effect of warfarin on pregnant women with prosthetic mechanical heart valves during the whole course of pregnancy and their fetuses. Methods Followup survey was carried out on 103 pregnant women with prosthetic mechanical heart valves treated in the Second Xiangya Hospital of Central South University from April 1998 to June 2010. Their age ranged from 19 and 38 years (26.4±3.8 years). All the 103 pregnant women were given oral administration of warfarin during the whole course of pregnancy. The average dose of domestic warfarin was 3.30±0.43 mg/d (87 cases), while the average dose of imported warfarin was 2.90±1.05 mg/d (16 cases). Results None of the patients suffered from serious embolic events. One patient suffered from spontaneous peritoneal hemorrhage. There were 4 cases of intrauterine deaths, and 5 cases of fetal malformation including 1 case of Down’s syndrome and 4 cases of hydrocephalus. Six cases of low birth weight infants and 1 case of ABO hemolytic disease were also found. All the other neonates were healthy with normal weight. No pregnant women suffered from postpartum hemorrhage. Conclusion Oral administration of low dose warfarin (lt;5 mg/d) during the whole course of pregnancy is a relative safe and effective anticoagulation protocol.
ObjectivesTo investigate the correlation of warfarin dose genetic and polymorphism of Han-patients after heart valve replacement, to forecast the anticoagulation therapy with warfarin reasonable dosage, and to realize individualized management of anticoagulation monitoring.
MethodsWe selected 103 patients between January 1, 2011 and December 31, 2012 in West China Hospital of Sichuan University who were treated by oral warfarin after heart valve replacement with monitoring anticoagulation by international normalized ratio (INR) in Anticoagulation Therapy Database of Chinese Patients after Heart Valve Replacement. There were 32 males and 71 female at age of 21-85 (48.64± 11.66) years. All the patients' CYP2C9 and VKORC1 genetic polymorphisms were detected by using polymerase chain reaction-restriction fragment length polymorphism (PCR-RELP) method and gene sequencing technology. Warfarin concentration in plasma was determined by high performance liquid chromatography (HPLC) method. The activity of coagulation factorⅡ, Ⅶ, Ⅸ, Ⅹwas determined by Sysmex CA7000 analyzer.
ResultsThe multivariate linear regression analysis showed that age, body surface area, and coagulation factor activity had no significant effect on warfarin dosage. While the gene polymor-phisms of CYP2C9 and VKORC1, warfarin concentration, and age had significant contributions to the overall variability in warfarin dose with decisive coefficients at 1.2%, 26.5%, 43.4%, and 5.0% respectively. The final equation was:Y=1.963-0.986× (CYP2C9* 3) +0.893× (VKORC1-1639) +0.002× (warfarin concentration)-0.019× (age).
ConclusionMultiple regression equation including gene polymorphisms of CYP2C9 and VKORC1, non-genetic factors of coagulation factor activity, warfarin concentration, age, and body surface area can predict reasonable dosage of warfarin for anticoagulation to achieve individualized management of anticoagulation monitoring and reduce the anticoagulation complications.
Warfarin is one of the most frequently prescribed oral anticoagulant. Many researches have shown that the genotypes have been strongly associated with warfarin maintenance doses. Especially, it has been accepted in academia that cytochrome P450 2C9 (CYP2C9) and vitamin K epoxide reductase complex 1 subunit (VKORC1) could affect the warfarin maintenance doses. There are also many other genotypes that were reported to be related to warfarin doses, but the results have been in controversial so far. The studies found that the dose formula which contained the genetic factors and clinical information could accurately predict the maintenance dose of warfarin, however, its usefulness is suspected due to the inconsistent results of clinical trials. Large-sample and multi-center studies are necessary to verify the specific effects of gene and non-gene factors to warfarin dose; at the same time, testing constructed models or building new models help to improve the explained percentages of individual differences.
ObjectiveTo verify the reliability of Anticlot Assistant, a patient self-management system for warfarin therapy assisted by artificial intelligence.MethodsIt was a single-center, prospective cohort study. The eligible 34 participants were recruited consecutively between November 29, 2017 to September 27, 2018 and managed by warfarin therapy via Anticlot Assistant. The recommendations of Anticlot Assistant were examined and verified by the doctors to ensure the security. Medical records were exported from the the background management system. An univariate analysis compared the outcomes between accepted and overridden records and a logistic regression model was built to determine independent predictors of the outcomes. The research team analyzed 153 medical records, which were from 18 participants and were input by 19 doctors. There were 97 records with doctor accepting the suggestion and 56 records with doctor rejecting the suggestion .ResultsWhen the doctors accepted the recommendations, the percentage of the next-test international normalized ratio (INR) in the therapeutic range was higher (64.95% vs. 44.64%, RR=2.298, 95%CI 1.173 to 4.499, P=0.014). The logistic regression analysis revealed that accepting the recommendations was an independent predictor for the next-test INR being in the therapeutic range after controlling potentially confounding factors (OR=2.446, 95%CI 1.103 to 5.423, P=0.028).ConclusionThe algorithm of Anticlot Assistant is reasonable and reliable.
Objective
To investigate the role of clinical pharmacists in warfarin therapy.
Methods
A total of 134 patients underwent prosthetic heart valve replacement and had warfarin for life from March 2013 to October 2013 in Fujian Medical University Union Hospital. All patients were equally divided into two groups (an intervention and a non-intervention group) crosswise by sequence. There were 67 patients in each group. The anticoagulant effects of the two groups were compared.
Results
There was no statistical difference in the patients' demographic information between the two groups. However, the time for the patients to reach the target international normalized ratio(INR) values for the first time (7.1±3.3 dvs. 10.5±5.0 d,P=0.000) and time of INR in the therapy range (46.3%±18.8%vs.19.0%±16.2%,P=0.000) during their hospitalization, proportion of time of under anticoagulation (47.5%±19.5%vs. 71.2%±22.9%,P=0.000), proportion of time of anticoagulation overdose (5.3%±8.2%vs. 9.9%±16.7%,P=0.002) were significantly different. While there was no statistical difference in postoperative hospitalization time between the two groups (19.9±6.6 dvs. 18.1±7.0 d,P=0.137). There were 4 patients (6.0%) with minor hemorrhage and no severe complication was found in the intervention group. There were seven patients (10.4%) with mild hemorrhage, two patients with stroke, one patient with mild pulmonary embolism, and severe complication rate of 4.5% in the non-intervention group.
Conclusion
With clinical pharmacists involved in the whole anticoagulation therapy progress of patients after mechanical heart valve replacement, the time to achieve the therapeutic window for the first time is effectively shorten, and the time of the INR value controlled in therapeutic range is highly improved during hospitalization time. Moreover, the patients' risk of thrombosis and bleeding is eventually reduced.
