Machine learning guided prediction of warfarin blood levels for personalized medicine based on clinical longitudinal data from cardiac surgery patients: a prospective observational study.

BACKGROUND: Warfarin is a common oral anticoagulant, and its effects vary widely among individuals. Numerous dose-prediction algorithms have been reported based on cross-sectional data generated via multiple linear regression or machine learning. This study aimed to construct an information fusion perturbation theory and machine learning prediction model of warfarin blood levels based on clinical longitudinal data from cardiac surgery patients. METHODS AND MATERIAL: The data of 246 patients were obtained from electronic medical records. Continuous variables were processed by calculating the distance of the raw data with the moving average (MA ∆vki(sj)), and categorical variables in different attribute groups were processed using Euclidean distance (ED ǁ∆vk(sj)ǁ). Regression and classification analyses were performed on the raw data, MA ∆vki(sj), and ED ǁ∆vk(sj)ǁ. Different machine-learning algorithms were chosen for the STATISTICA and WEKA software. RESULTS: The random forest (RF) algorithm was the best for predicting continuous outputs using the raw data. The correlation coefficients of the RF algorithm were 0.978 and 0.595 for the training and validation sets, respectively, and the mean absolute errors were 0.135 and 0.362 for the training and validation sets, respectively. The proportion of ideal predictions of the RF algorithm was 59.0%. General discriminant analysis (GDA) was the best algorithm for predicting the categorical outputs using the MA ∆vki(sj) data. The GDA algorithm's total true positive rate (TPR) was 95.4% and 95.6% for the training and validation sets, respectively, with MA ∆vki(sj) data. CONCLUSIONS: An information fusion perturbation theory and machine learning model for predicting warfarin blood levels was established. A model based on the RF algorithm could be used to predict the target international normalized ratio (INR), and a model based on the GDA algorithm could be used to predict the probability of being within the target INR range under different clinical scenarios.

A Randomized Trial Comparing Standard of Care to Bayesian Warfarin Dose Individualization.

The quality of warfarin treatment may be improved if management is guided by the use of models based upon pharmacokinetic-pharmacodynamic theory. A prospective, two-armed, single-blind, randomized controlled trial compared management aided by a web-based dose calculator (NextDose) with standard clinical care. Participants were 240 adults receiving warfarin therapy following cardiac surgery, followed up until the first outpatient appointment at least 3 months after warfarin initiation. We compared the percentage of time spent in the international normalized ratio acceptable range (%TIR) during the first 28 days following warfarin initiation, and %TIR and count of bleeding events over the entire follow-up period. Two hundred thirty-four participants were followed up to day 28 (NextDose: 116 and standard of care: 118), and 228 participants (114 per arm) were followed up to the final study visit. Median %TIR tended to be higher for participants receiving NextDose guided warfarin management during the first 28 days (63 vs. 56%, P = 0.13) and over the entire follow-up period (74 vs. 71%, P = 0.04). The hazard of clinically relevant minor bleeding events was lower for participants in the NextDose arm (hazard ratio: 0.21, P = 0.041). In NextDose, there were 89.3% of proposed doses accepted by prescribers. NextDose guided dose management in cardiac surgery patients requiring warfarin was associated with an increase in %TIR across the full follow-up period and fewer hemorrhagic events. A theory-based, pharmacologically guided approach facilitates higher quality warfarin anticoagulation. An important practical benefit is a reduced requirement for clinical experience of warfarin management.

Assessment of risk factors for acute graft-versus-host disease post-hematopoietic stem cell transplantation: a retrospective study based on a proportional odds model using a nonlinear mixed-effects model.

Background: Acute graft-versus-host disease (aGVHD) is a major complication following hematopoietic stem cell transplantation (HSCT). Objective: This study aimed to explore the risk factors for the incidence of aGVHD in patients post-HSCT. Design: This was a retrospective study. Methods: A total of 407 patients were enrolled. The patients' data were recorded from the medical records. The exposure of cyclosporine was estimated based on a population pharmacokinetics model. The occurrence of aGVHD was clinically graded and staged in severity from grades I to IV. A proportional odds model that estimated the cumulative probabilities of aGVHD was used to analyze the data using a nonlinear mixed-effects model. Then, the model parameters and plausibility were evaluated by bootstrap and visual predictive checks. Results: The typical probabilities were 18.9% and 17.9% for grade II and grades III-IV, respectively. The incidence of grade II and grade III-IV aGVHD for human leukocyte antigen (HLA) haplo sibling donor patients was higher than that for HLA-matched donor patients. The incidence of grade II and grade III-IV aGVHD decreased with increasing early cyclosporine trough concentration; however, cyclosporine exposure was not associated with the incidence of aGVHD. Conclusion: HLA matching and early cyclosporine trough concentration were important factors for the occurrence of aGVHD.

Exploring the complex relationship between vitamin K, gut microbiota, and warfarin variability in cardiac surgery patients.

BACKGROUND AND OBJECTIVES: Due to the high individual variability of anticoagulant warfarin, this study aimed to investigate the effects of vitamin K concentration and gut microbiota on individual variability of warfarin in 246 cardiac surgery patients. METHODS: The pharmacokinetics and pharmacodynamics (PKPD) model predicted international normalized ratio (INR) and warfarin concentration. Serum and fecal samples were collected to detect warfarin and vitamin K [VK1 and menaquinone-4 (MK4)] concentrations and gut microbiota diversity, respectively. In addition, the patient's medical records were reviewed for demographic characteristics, drug history, and CYP2C9, VKORC1, and CYP4F2 genotypes. RESULTS: The PKPD model predicted ideal values of 62.7% for S-warfarin, 70.4% for R-warfarin, and 76.4% for INR. The normal VK1 level was 1.34±1.12 nmol/ml (95% CI: 0.33-4.08 nmol/ml), and the normal MK4 level was 0.22±0.18 nmol/ml (95% CI: 0.07-0.63 nmol/ml). The MK4 to total vitamin K ratio was 16.5±9.8% (95% CI: 4.3-41.5%). The S-warfarin concentration of producing 50% of maximum anticoagulation and the half-life of prothrombin complex activity tended to increase with vitamin K. Further, Prevotella and Eubacterium of gut microbiota identified as the main bacteria associated with individual variability of warfarin. The results suggest that an increase in vitamin K concentration can decrease anticoagulation, and gut microbiota may influence warfarin anticoagulation through vitamin K2 synthesis. CONCLUSION: This study highlights the importance of considering vitamin K concentration and gut microbiota when prescribing warfarin. The findings may have significant implications for the personalized use of warfarin. Further research is needed to understand better the role of vitamin K and gut microbiota in warfarin anticoagulation.

A fully validated flow cytometry method to quantitatively analyze active rATG in human serum and its application in pharmacokinetic study for therapeutic drug monitoring.

Rabbit anti-thymocyte globulin (rATG) has been widely used to prevent graft-versus-host disease (GvHD) after allogeneic hematopoietic stem cell transplantation (allo-HSCT). The therapeutic window of rATG is narrow, and it may increase the risk of relapse, viral reactivation, delayed immune reconstitution and GvHD when overexposed or underexposed. Therefore, a reliable method for detecting the rATG concentration in human serum by flow cytometry was established and fully validated for therapeutic drug monitoring. In this method, Jurkat T cells were used to capture active rATG in human serum, and PE-labeled donkey anti-rabbit IgG was used as a secondary antibody. The method showed good specificity, selectivity and excellent linearity at concentration of 0.00300-20.0 AU/mL. The intra- and interday precision values were all within 20% at four concentration levels for the analyte. The stock solutions of rATG showed no significant degradation after storage at ambient temperature for 8 h and at - 80 °C for 481 days. No significant degradation of rATG in serum was observed at ambient temperature for 6 h, during six freezethaw cycles and at - 80 °C for at least 373 days. This method was fully validated and successfully applied to monitor active rATG concentration in serum of patients with haploid-identical hematopoietic stem cell transplantation.

Assessment of the impact of intravenous antibiotics treatment on gut microbiota in patients: Clinical data from pre-and post-cardiac surgery.

Background and aims: Surgical site infection is a common complication after surgery. Periprocedural antibiotics are necessary to prescribe for preventing or treating infections. The present study aimed to explore the effect of intravenous antibiotics on gut microbiota and menaquinone biosynthesis in patients, especially in elderly patients undergoing cardiac surgery. Methods: A total of 388 fecal samples were collected from 154 cardiac surgery patients. The V3-V4 hypervariable region of the bacterial 16S rRNA gene was amplified and sequenced on a MiSeq PE300. The gut microbiota diversity of samples was analyzed in terms of α- and ß-diversity at the OTU level. The different groups were classified according to antibiotics in combinations and single antibiotics. PICRUSt2 was used for preliminary prediction of the gut microbiota function for menaquinone biosynthesis. Results: The intravenously administered antibiotics which are excreted via bile represents the main antibiotics that could disturb the gut microbiota's composition in cardiac surgery patients, especially for elderly patients. The effect of antibiotics on gut microbiota is produced after antibiotics treatments over one week. The recovery of gut microbiota to the state of pre-antibiotics may require over two weeks of antibiotics withdrawal. Sex factor doesn't represent as an influencer in gut microbiota composition. Long-term use of cefoperazone-sulbactam may affect coagulation function. Conclusions: The composition of the gut microbiota had a significant change post-intravenous antibiotics treatment in cardiac surgery patients. The richness and diversity of gut microbiota are increased in elderly patients.

Long noncoding RNA SNHG6 promotes oesophageal squamous cell carcinoma by downregulating the miR-101-3p/EZH2 pathway.

Long noncoding RNAs (LncRNAs) have been reported to play a vital role in the development of oesophageal squamous cell carcinoma (OSCC). Our previous study revealed that the significant upregulation of the LncRNA small nucleolar RNA host gene 6 (SNHG6) in OSCC promotes OSCC tumourigenesis. However, the mechanisms underlying the dynamics of SNHG6 expression in OSCC have rarely been studied. In this study, we verified the tumour-promoting effect of SNHG6 through sponging miR-101-3p, and their levels were negatively correlated in human samples of OSCC. In addition, miR-101-3p overexpression reversed the effect of SNHG6. Moreover, we confirmed that SNHG6/miR-101-3p affects OSCC by regulating the expression of the enhancer of zeste 2 (EZH2). The effect of EZH2 silencing resembled closely that of SNHG6 knockdown. EZH2 silencing inhibited the expression of protein cyclin D1 and ß-catenin, but in contrast, it enhanced the expression of E-cadherin. These findings demonstrated the oncogenic role of SNHG6, which promotes OSCC progression by regulating the expression of EZH2 through its interaction with miR-101-3p. These findings may help in improving the diagnosis and treatment methods of OSCC.

Multicenter-Based Population Pharmacokinetic Analysis of Ciclosporin in Hematopoietic Stem Cell Transplantation Patients.

PURPOSE: To explore the contribution of physiological characteristics to variability in ciclosporin pharmacokinetics in hematopoietic stem cell transplantation patients. METHODS: Clinical data from 563 patients were collected from centers in three regions. Ciclosporin concentrations were measured using immunoassays. The patients' demographics, hematological and biological indicators, coadministered drugs, region, and disease diagnosis were recorded from medical records. Data analysis was performed using NONMEM based on a one-compartment model to describe the pharmacokinetics of ciclosporin. The reliability and stability of the final model were evaluated using bootstrap resampling, goodness-of-fit plots, and prediction-corrected visual predictive checks. RESULTS: The population estimate of the clearance (CL) was 30.4 L/h, the volume of distribution (V) was 874.0 L and the bioavailability (F) was 81.1%. The between-subject variability in these parameters was 26.3, 68.0, and 110.8%, respectively. Coadministration of fluconazole, itraconazole, or voriconazole decreased CL by 17.6%, 28.4%, and 29.2%, respectively. Females' CL increased by approximately 12.0%. In addition, CL and V decreased with hematocrit, total protein, and uric acid increase, and CL also decreased with age and aspartate aminotransferase increase. However, CL increased with creatinine clearance increase. CONCLUSIONS: A multicenter-based population pharmacokinetic model of ciclosporin was established. The pharmacokinetics of ciclosporin exhibited discrepancies among different regions.

Upregulation of long non-coding RNA SNHG6 promote esophageal squamous cell carcinoma cell malignancy and its diagnostic value.

AIM: To investigate the expression of lncRNA SNHG6 in esophageal squamous cell carcinoma (ESCC), the biological function of SNHG6 in ESCCs, and evaluate its diagnostic value in ESCC. METHODS: SNHG6 expression in tissues and cells was detected by quantitative real-time polymerase chain reaction (qRT-PCR). The effect of SNHG6 on the cell proliferation, migration and invasion was detected by CCK-8 assay and transwell assay, respectively. RESULTS: SNHG6 expression was upregulated in ESCC tissues and ESCCs. Upregulated SNHG6 expression was correlated with prognosis, lymph node metastasis, distant metastasis and TNM stage of ESCC patients. SNHG6 promoted the abilities of cell proliferation, migration and invasion in ESCCs, knockdown of SNHG6 reversed these effects. SNHG6 might serve as an independently diagnostic biomarker for lymph node metastasis, distant metastasis and TNM stage. CONCLUSION: SNHG6 may exert oncogenic function in ESCC and may be a potential diagnostic marker for this cancer.

Metabolism and disposition of pyrotinib in healthy male volunteers: covalent binding with human plasma protein.

Pyrotinib is a novel irreversible EGFR/HER2 dual tyrosine kinase inhibitor that is used to treat HER2-positive breast cancer. In this study we investigated the metabolism and disposition of pyrotinib in six healthy Chinese men after a single oral dose of 402 mg of [14C]pyrotinib. At 240 h postdose, the mean cumulative excretion of the dose radioactivity was 92.6%, including 1.7% in urine and 90.9% in feces. In feces, oxidative metabolites were detected as major drug-related materials and the primary metabolic pathways were O-depicoline (M1), oxidation of pyrrolidine (M5), and oxidation of pyridine (M6-1, M6-2, M6-3, and M6-4). In plasma, the major circulating entities identified were pyrotinib, SHR150980 (M1), SHR151468 (M2), and SHR151136 (M5), accounting for 10.9%, 1.9%, 1.0%, and 3.0%, respectively, of the total plasma radioactivity based on the AUC0-∞ ratios. Approximately 58.3% of the total plasma radioactivity AUC0-∞ was attributed to covalently bound materials. After incubation of human plasma with [14C]pyrotinib at 37 °C for 2, 5, 8, and 24 h, the recovery of radioactivity by extraction was 97.4%, 91.8%, 69.6%, and 46.7%, respectively, revealing covalent binding occurred independently of enzymes. A group of pyrotinib adducts, including pyrotinib-lysine and pyrotinib adducts of the peptides Gly-Lys, Lys-Ala, Gly-Lys-Ala, and Lys-Ala-Ser, was identified after HCl hydrolysis of the incubated plasma. Therefore, the amino acid residue Lys190 of human serum albumin was proposed to covalently bind to pyrotinib via Michael addition. Finally, the covalently bound pyrotinib could dissociate from the human plasma protein and be metabolized by oxidation and excreted via feces.

Theory-based pharmacokinetics and pharmacodynamics of S- and R-warfarin and effects on international normalized ratio: influence of body size, composition and genotype in cardiac surgery patients.

AIMS: The aims of this study are to apply a theory-based mechanistic model to describe the pharmacokinetics (PK) and pharmacodynamics (PD) of S- and R-warfarin. METHODS: Clinical data were obtained from 264 patients. Total concentrations for S- and R-warfarin were measured by ultra-high performance liquid tandem mass spectrometry. Genotypes were measured using pyrosequencing. A sequential population PK parameter with data method was used to describe the international normalized ratio (INR) time course. Data were analyzed with NONMEM. Model evaluation was based on parameter plausibility and prediction-corrected visual predictive checks. RESULTS: Warfarin PK was described using a one-compartment model. CYP2C9 *1/*3 genotype had reduced clearance for S-warfarin, but increased clearance for R-warfarin. The in vitro parameters for the relationship between prothrombin complex activity (PCA) and INR were markedly different (A = 0.560, B = 0.386) from the theory-based values (A = 1, B = 0). There was a small difference between healthy subjects and patients. A sigmoid Emax PD model inhibiting PCA synthesis as a function of S-warfarin concentration predicted INR. Small R-warfarin effects was described by competitive antagonism of S-warfarin inhibition. Patients with VKORC1 AA and CYP4F2 CC or CT genotypes had lower C50 for S-warfarin. CONCLUSION: A theory-based PKPD model describes warfarin concentrations and clinical response. Expected PK and PD genotype effects were confirmed. The role of predicted fat free mass with theory-based allometric scaling of PK parameters was identified. R-warfarin had a minor effect compared with S-warfarin on PCA synthesis. INR is predictable from 1/PCA in vivo.

Population pharmacokinetics and individualized dosage prediction of cyclosporine in allogeneic hematopoietic stem cell transplant patients.

BACKGROUND: Cyclosporine (CsA), a potent immunosuppressive agent used to prevent rejection, is characterized by large individual variability. The purpose of this study was to explore the pharmacokinetic characteristics of CsA and establish a CsA population pharmacokinetic model that could be used for personalized therapy in allogeneic hematopoietic stem cell transplant (allo-HSCT) patients. METHODS: Clinical data were obtained from 117 allo-HSCT patients. The data analysis was performed using NONMEM software. A first-order conditional estimation with interaction (FOCE-I) method within NONMEM was used to estimate the parameters. The covariates, including demographics, hematological indices, biochemical levels, concurrent drugs, and genetic polymorphisms of CYP3A4, CYP3A5, and ABCB1, were evaluated quantitatively. The stability of the final model was validated by a nonparametric bootstrap procedure. RESULTS: A total of 1,571 observed concentrations were collected. A 1-compartment model with first-order absorption and elimination adequately described the pharmacokinetics of CsA. The typical values for clearance (CL), volume of distribution (V), and bioavailability were 29.6 L/hr, 605 L, and 0.619, respectively. The interindividual variability of these parameters was 20.4, 66.1, and 30.4%, respectively. The residual error was 31.4% and 23.7 ng/mL. The duration of CsA therapy, hematocrit, antifungal agent administration, triglycerides, and weight were identified as the main covariates that influenced CL, and hematocrit had a significant effect on V. The internal validation showed that the final model was stable and accurate. CONCLUSIONS: This study established a population pharmacokinetic model of CsA in allo-HSCT patients that could provide the foundation for personalized use of CsA in the clinic.