Genetic Variants Associated with Biological Treatment Response in Inflammatory Bowel Disease: A Systematic Review.

Inflammatory bowel disease (IBD) is a chronic inflammatory disorder of the digestive tract usually characterized by diarrhea, rectal bleeding, and abdominal pain. IBD includes Crohn's disease and ulcerative colitis as the main entities. IBD is a debilitating condition that can lead to life-threatening complications, involving possible malignancy and surgery. The available therapies aim to achieve long-term remission and prevent disease progression. Biologics are bioengineered therapeutic drugs that mainly target proteins. Although they have revolutionized the treatment of IBD, their potential therapeutic benefits are limited due to large interindividual variability in clinical response in terms of efficacy and toxicity, resulting in high rates of long-term therapeutic failure. It is therefore important to find biomarkers that provide tailor-made treatment strategies that allow for patient stratification to maximize treatment benefits and minimize adverse events. Pharmacogenetics has the potential to optimize biologics selection in IBD by identifying genetic variants, specifically single nucleotide polymorphisms (SNPs), which are the underlying factors associated with an individual's drug response. This review analyzes the current knowledge of genetic variants associated with biological agent response (infliximab, adalimumab, ustekinumab, and vedolizumab) in IBD. An online literature search in various databases was conducted. After applying the inclusion and exclusion criteria, 28 reports from the 1685 results were employed for the review. The most significant SNPs potentially useful as predictive biomarkers of treatment response are linked to immunity, cytokine production, and immunorecognition.

Use of Machine Learning for Dosage Individualization of Vancomycin in Neonates.

BACKGROUND AND OBJECTIVE: High variability in vancomycin exposure in neonates requires advanced individualized dosing regimens. Achieving steady-state trough concentration (C0) and steady-state area-under-curve (AUC0-24) targets is important to optimize treatment. The objective was to evaluate whether machine learning (ML) can be used to predict these treatment targets to calculate optimal individual dosing regimens under intermittent administration conditions. METHODS: C0 were retrieved from a large neonatal vancomycin dataset. Individual estimates of AUC0-24 were obtained from Bayesian post hoc estimation. Various ML algorithms were used for model building to C0 and AUC0-24. An external dataset was used for predictive performance evaluation. RESULTS: Before starting treatment, C0 can be predicted a priori using the Catboost-based C0-ML model combined with dosing regimen and nine covariates. External validation results showed a 42.5% improvement in prediction accuracy by using the ML model compared with the population pharmacokinetic model. The virtual trial showed that using the ML optimized dose; 80.3% of the virtual neonates achieved the pharmacodynamic target (C0 in the range of 10-20 mg/L), much higher than the international standard dose (37.7-61.5%). Once therapeutic drug monitoring (TDM) measurements (C0) in patients have been obtained, AUC0-24 can be further predicted using the Catboost-based AUC-ML model combined with C0 and nine covariates. External validation results showed that the AUC-ML model can achieve an prediction accuracy of 80.3%. CONCLUSION: C0-based and AUC0-24-based ML models were developed accurately and precisely. These can be used for individual dose recommendations of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively.

Drug Clearance in Neonates: A Combination of Population Pharmacokinetic Modelling and Machine Learning Approaches to Improve Individual Prediction.

BACKGROUND: Population pharmacokinetic evaluations have been widely used in neonatal pharmacokinetic studies, while machine learning has become a popular approach to solving complex problems in the current era of big data. OBJECTIVE: The aim of this proof-of-concept study was to evaluate whether combining population pharmacokinetic and machine learning approaches could provide a more accurate prediction of the clearance of renally eliminated drugs in individual neonates. METHODS: Six drugs that are primarily eliminated by the kidneys were selected (vancomycin, latamoxef, cefepime, azlocillin, ceftazidime, and amoxicillin) as 'proof of concept' compounds. Individual estimates of clearance obtained from population pharmacokinetic models were used as reference clearances, and diverse machine learning methods and nested cross-validation were adopted and evaluated against these reference clearances. The predictive performance of these combined methods was compared with the performance of two other predictive methods: a covariate-based maturation model and a postmenstrual age and body weight scaling model. Relative error was used to evaluate the different methods. RESULTS: The extra tree regressor was selected as the best-fit machine learning method. Using the combined method, more than 95% of predictions for all six drugs had a relative error of < 50% and the mean relative error was reduced by an average of 44.3% and 71.3% compared with the other two predictive methods. CONCLUSION: A combined population pharmacokinetic and machine learning approach provided improved predictions of individual clearances of renally cleared drugs in neonates. For a new patient treated in clinical practice, individual clearance can be predicted a priori using our model code combined with demographic data.

Population pharmacokinetic meta-analysis of individual data to design the first randomized efficacy trial of vancomycin in neonates and young infants.

OBJECTIVES: In the absence of consensus, the present meta-analysis was performed to determine an optimal dosing regimen of vancomycin for neonates. METHODS: A 'meta-model' with 4894 concentrations from 1631 neonates was built using NONMEM, and Monte Carlo simulations were performed to design an optimal intermittent infusion, aiming to reach a target AUC0-24 of 400 mg·h/L at steady-state in at least 80% of neonates. RESULTS: A two-compartment model best fitted the data. Current weight, postmenstrual age (PMA) and serum creatinine were the significant covariates for CL. After model validation, simulations showed that a loading dose (25 mg/kg) and a maintenance dose (15 mg/kg q12h if <35 weeks PMA and 15 mg/kg q8h if ≥35 weeks PMA) achieved the AUC0-24 target earlier than a standard 'Blue Book' dosage regimen in >89% of the treated patients. CONCLUSIONS: The results of a population meta-analysis of vancomycin data have been used to develop a new dosing regimen for neonatal use and to assist in the design of the model-based, multinational European trial, NeoVanc.

Topiramate plus Cooling for Hypoxic-Ischemic Encephalopathy: A Randomized, Controlled, Multicenter, Double-Blinded Trial.

BACKGROUND AND OBJECTIVES: Therapeutic interventions to improve the efficacy of whole-body cooling for hypoxic-ischemic encephalopathy (HIE) are desirable. Topiramate has been effective in reducing brain damage in experimental studies. However, in the clinical setting information is limited to a small number of feasibility trials. We launched a randomized controlled double-blinded topiramate/placebo multicenter trial with the primary objective being to reduce the antiepileptic activity in cooled neonates with HIE and assess if brain damage would be reduced as a consequence. STUDY DESIGN: Neonates were randomly assigned to topiramate or placebo at the initiation of hypothermia. Topiramate was administered via a nasogastric tube. Brain electric activity was continuously monitored. Topiramate pharmacokinetics, energy-related and Krebs' cycle intermediates, and lipid peroxidation biomarkers were determined using liquid chromatography-mass spectrometry and MRI for assessing brain damage. RESULTS: Out of 180 eligible patients 110 were randomized, 57 (51.8%) to topiramate and 53 (48.2%) to placebo. No differences in the perinatal or postnatal variables were found. The topiramate group exhibited less seizure burden in the first 24 h of hypothermia (topiramate, n = 14 [25.9%] vs. placebo, n = 22 [42%]); needed less additional medication, and had lower mortality (topiramate, n = 5 [9.2%] vs. placebo, n = 10 [19.2%]); however, these results did not achieve statistical significance. Topiramate achieved a therapeutic range in 37.5 and 75.5% of the patients at 24 and 48 h, respectively. A significant association between serum topiramate levels and seizure activity (p < 0.016) was established. No differences for oxidative stress, energy-related metabolites, or MRI were found. CONCLUSIONS: Topiramate reduced seizures in patients achieving therapeutic levels in the first hours after treatment initiation; however, they represented only a part of the study population. Our results warrant further studies with higher loading and maintenance dosing of topiramate.