Search

In population pharmacokinetic (PK) models, interindividual variability is explained by implementation of covariates in the model. The widely used forward stepwise selection method is sensitive to bias, which may lead to an incorrect inclusion of covariates. Alternatives, such as the full fixed effects model, reduce this bias but are dependent on the chosen implementation of each covariate. As the correct functional forms are unknown, this may still lead to an inaccurate selection of covariates. Machine learning (ML) techniques can potentially be used to learn the optimal functional forms for implementing covariates directly from data. A recent study suggested that using ML resulted in an improved selection of influential covariates. However, how do we select the appropriate functional form for including these covariates? In this work, we use SHapley Additive exPlanations (SHAP) to infer the relationship between covariates and PK parameters from ML models. As a case‐study, we use data from 119 patients with hemophilia A receiving clotting factor VIII concentrate peri‐operatively. We fit both a random forest and a XGBoost model to predict empirical Bayes estimated clearance and central volume from a base nonlinear mixed effects model. Next, we show that SHAP reveals covariate relationships which match previous findings. In addition, we can reveal subtle effects arising from combinations of covariates difficult to obtain using other methods of covariate analysis. We conclude that the proposed method can be used to extend ML‐based covariate selection, and holds potential as a complete full model alternative to classical covariate analyses. [ABSTRACT FROM AUTHOR]

Nonlinear mixed effect (NLME) models are the gold standard for the analysis of patient response following drug exposure. However, these types of models are complex and time‐consuming to develop. There is great interest in the adoption of machine‐learning methods, but most implementations cannot be reliably extrapolated to treatment strategies outside of the training data. In order to solve this problem, we propose the deep compartment model (DCM), a combination of neural networks and ordinary differential equations. Using simulated datasets of different sizes, we show that our model remains accurate when training on small data sets. Furthermore, using a real‐world data set of patients with hemophilia A receiving factor VIII concentrate while undergoing surgery, we show that our model more accurately predicts a priori drug concentrations compared to a previous NLME model. In addition, we show that our model correctly describes the changing drug concentration over time. By adopting pharmacokinetic principles, the DCM allows for simulation of different treatment strategies and enables therapeutic drug monitoring. [ABSTRACT FROM AUTHOR]

Summary: Congenital platelet disorders (CPDs) are rare bleeding disorders that are associated with mucocutaneous bleeds. However, data on vaginal bleeding in women with CPDs are scarce. A set of generic and bleeding‐specific questionnaires were used to evaluate the prevalence of vaginal bleeding, its impact on quality of life (QoL) and sexual functioning and the consequences for pregnancy, miscarriage and delivery in a cohort of women who were referred for diagnostic evaluation for CPDs. A total of 78 women included in the study were either diagnosed with a CPD (n = 35) or were clinically suspected of a CPD (n = 43). Heavy menstrual bleeding (HMB) was reported by a large proportion of women, which mainly started at menarche. In all, 76% of women received any kind of HMB treatment, often leading to surgical prodecures. HMB was shown to have a high impact on QoL, which improved upon treatment. Even though women reported that vaginal bleeding affects sexuality, this topic is not frequently discussed with physicians. Heavy blood loss frequently occurred after miscarriage/delivery, often requiring treatment. Women with (suspected) CPDs frequently encounter HMB, negatively impacting daily life and sexual functioning. Together with peripartum bleeding, these data highlight the burden of vaginal bleeding in CPDs and importance of adequate treatment. [ABSTRACT FROM AUTHOR]

Sickle cell disease is an autosomal recessive, multisystem disorder, characterised by chronic haemolytic anaemia, painful episodes of vaso-occlusion, progressive organ failure and a reduced life expectancy. Sickle cell disease is the most common monogenetic disease, with millions affected worldwide. In well-resourced countries, comprehensive care programs have increased life expectancy of sickle cell disease patients, with almost all infants surviving into adulthood. Therapeutic options for sickle cell disease patients are however, still scarce. Predictors of sickle cell disease severity and a better understanding of pathophysiology and (epi)genetic modifiers are warranted and could lead to more precise management and treatment. This review provides an extensive summary of the pathophysiology and management of sickle cell disease and encompasses the characteristics, complications and current and future treatment options of the disease., (Copyright © 2019. Published by Elsevier Ltd.)

Essentials A pediatric pharmacogenetic dosing algorithm for acenocoumarol has not yet been developed. We conducted a multicenter retrospective follow-up study in children in the Netherlands. Body surface area and indication explained 45.0% of the variability in dose requirement. Adding the genotypes of VKORC1, CYP2C9 and CYP2C18 to the algorithm increased this to 61.8%., Summary: Background The large variability in dose requirement of vitamin K antagonists is well known. For warfarin, pediatric dosing algorithms have been developed to predict the correct dose for a patient; however, this is not the case for acenocoumarol. Objectives To develop dosing algorithms for pediatric patients receiving acenocoumarol with and without genetic information. Methods The Children Anticoagulation and Pharmacogenetics Study was designed as a multicenter retrospective follow-up study in Dutch anticoagulation clinics and children's hospitals. Pediatric patients who used acenocoumarol between 1995 and 2014 were selected for inclusion. Clinical information and saliva samples for genotyping of the genes encoding cytochrome P450 (CYP) 2C9, vitamin K epoxide reductase complex subunit 1 (VKORC1), CYP4F2, CYP2C18 and CYP3A4 were collected. Linear regression was used to analyze their association with the log mean stable dose. A stable period was defined as three or more consecutive International Normalized Ratio measurements within the therapeutic range over a period of ≥ 3 weeks. Results In total, 175 patients were included in the study, of whom 86 had a stable period and no missing clinical information (clinical cohort; median age 8.9 years, and 49% female). For 80 of these 86 patients, genetic information was also available (genetic cohort). The clinical algorithm, containing body surface area and indication, explained 45.0% of the variability in dose requirement of acenocoumarol. After addition of the VKORC1, CYP2C9, and CYP2C18 genotypes to the algorithm, this increased to 61.8%. Conclusions These findings show that clinical factors had the largest impact on the required dose of acenocoumarol in pediatric patients. Nevertheless, genetic factors, and especially VKORC1, also explained a significant part of the variability., (© 2018 The Authors. Journal of Thrombosis and Haemostasis published by Wiley Periodicals, Inc. on behalf of International Society on Thrombosis and Haemostasis.)

3 pregnant women, aged 27, 33 and 31 years respectively, were carriers of haemophilia A. The first patient had a caesarean section without prior measurement or substitution of factor VIII. She gave birth to a healthy boy, but developed severe diffuse abdominal bleeding after a few hours. The second patient had a normal level of factor VIII, and lived 100 km away from the nearest haemophilia treatment centre. Ultrasound investigation revealed a female foetus. She gave birth in the local hospital. The third patient was pregnant with a male foetus, but refused further prenatal investigation. Contrary to medical advice she gave birth at home. For carriers of haemophilia, there are several options for prenatal diagnosis and managing labour and delivery. Early referral is advised and the need for adequate counselling is explained. It is important to have an experienced haemophilia treatment centre nearby, where haematologists, gynaecologists, geneticists and paediatricians cooperate in caring for pregnant carriers of haemophilia.

A 5-year-old boy presented with fever and fatigue after a holiday in northern Italy. On physical examination a marked splenomegaly was found. Laboratory investigations showed a pancytopenia as well as several markers suggesting an autoimmune disease. The splenomegaly and pancytopenia continued to progress despite treatment with prednisolone and intravenous immunoglobulins. One and a half years after presentation, the spleen had grown to such an extent that it was causing mechanical problems. Splenectomy was performed for diagnostic and therapeutic purposes. Histological investigation of the spleen showed amastigotes of Leishmania. PCR confirmed the diagnosis visceral leishmaniasis. Leishmaniasis is too often considered to be a tropical disease only. In recent years it has frequently been seen in southern European countries around the Mediterranean Sea.

Anaemia was diagnosed in four adopted children during a standard screening examination 1-4 weeks after arrival. Further investigation revealed a number of causes which could then be specifically treated. The children were a girl aged 14 months from China with iron-deficiency anaemia, a boy aged 16 months from Nigeria with sickle cell anaemia, a girl aged 5 from Haiti who had alpha-thalassaemia, and a boy aged 7 from Brazil with spherocytosis. Iron deficiency is the most common cause of anaemia in childhood. However, in adopted children from sub-tropical areas other causes of anaemia like haemoglobinopathies or erythrocyte membrane defects should be borne in mind, particularly as a history of disease and family history are often lacking. Additional investigations may be necessary. An incorrect diagnosis of iron deficiency may result in ongoing and unjustified iron supplementation leading to harmful iron accumulation in thalassaemia and a delay in the correct treatment in sickle cell anemia or spherocytosis which could carry considerable risk.

4 children, a boy aged 10 years and 3 girls aged 3, 3, and 16 years, suffering from chronic or refractory autoimmune haemolytic anaemia (AIHA), who were dependent on high doses of steroids and were refractory to immunosuppressants, were treated with rituximab at a dose of 375 mg/m2 once a week for 3 or 4 weeks as an alternative to splenectomy. Rituximab is a monoclonal anti-CD20 antibody that prevents the production ofautoantibodies by selective destruction of B-lymphocytes. Haemoglobin levels increased and the parameters of chronic haemolysis (reticulocyte count, lactate dehydrogenase activity, bilirubin concentration) decreased to normal values. 3 patients were taken off corticosteroids completely; 1 of these was also no longer dependent on blood transfusions. Circulating B-lymphocytes were absent for 6 to 15 months after the treatment and the rituximab was well-tolerated. During the treatment, immunoglobulins were substituted and infectious complications were not seen. Rituximab was valuable in the treatment of chronic or refractory AIHA and eliminated the need for splenectomy. 1 patient did not respond to rituximab.