Applying Neural ODEs to Derive a Mechanism-Based Model for Characterizing Maturation-Related Serum Creatinine Dynamics in Preterm Newborns.

Serum creatinine in neonates follows complex dynamics due to maturation processes, most pronounced in the first few weeks of life. The development of a mechanism-based model describing complex dynamics requires high expertise in pharmacometric (PMX) modeling and substantial model development time. A recently published machine learning (ML) approach of low-dimensional neural ordinary differential equations (NODEs) is capable of modeling such data from newborns automatically. However, this efficient data-driven approach in itself does not result in a clinically interpretable model. In this work, an approach to deriving an interpretable model with reasonable PMX-type functions is presented. This "translation" was applied to derive a PMX model for serum creatinine in neonates considering maturation processes and covariates. The developed model was compared to a previously published mechanism-based PMX model whereas both models had similar mechanistic structures. The developed model was then utilized to simulate serum creatinine concentrations in the first few weeks of life considering different covariate values for gestational age and birth weight. The reference serum creatinine values derived from these simulations are consistent with observed serum creatinine values and previously published reference values. Thus, the presented NODE-based ML approach to model complex serum creatinine dynamics in newborns and derive interpretable, mathematical-statistical components similar to those in a conventional PMX model demonstrates a novel, viable approach to facilitate the modeling of complex dynamics in clinical settings and pediatric drug development.

Systems pharmacodynamic model of combined gemcitabine and trabectedin in pancreatic cancer cells. Part I.Çô Effects on signal transduction pathways related to tumor growth.

Pancreatic ductal adenocarcinoma (PDAC) is often chemotherapy-resistant, and novel drug combinations would fill an unmet clinical need. Previously we reported synergistic cytotoxic effects of gemcitabine and trabectedin on pancreatic cancer cells, but underlying protein-level interaction mechanisms remained unclear. We employed a reliable, sensitive, comprehensive, quantitative, high-throughput IonStar proteomic workflow to investigate the time course of gemcitabine and trabectedin effects, alone and combined, upon pancreatic cancer cells. MiaPaCa-2 cells were incubated with vehicle (controls), gemcitabine, trabectedin, and their combinations over 72 hours. Samples were collected at intervals and analyzed using the label-free IonStar liquid chromatography-mass spectrometry (LC-MS/MS) workflow to provide temporal quantification of protein expression for 4,829 proteins in four experimental groups. To characterize diverse signal transduction pathways, a comprehensive systems pharmacodynamic (SPD) model was developed. The analysis is presented in two parts. Here, Part I describes drug responses in cancer cell growth and migration pathways included in the full model: receptor tyrosine kinase- (RTK), integrin-, G-protein coupled receptor- (GPCR), and calcium-signaling pathways. The developed model revealed multiple underlying mechanisms of drug actions, provides insight into the basis of drug interaction synergism, and offers a scientific rationale for potential drug combination strategies.

Prospective study to characterize adalimumab exposure in pediatric patients with rheumatic diseases.

BACKGROUND: In pediatric rheumatic diseases (PRD), adalimumab is dosed using fixed weight-based bands irrespective of methotrexate co-treatment, disease activity (DA) or other factors that might influence adalimumab pharmacokinetics (PK). In rheumatoid arthritis (RA) adalimumab exposure between 2-8 mg/L is associated with clinical response. PRD data on adalimumab is scarce. Therefore, this study aimed to analyze adalimumab PK and its variability in PRD treated with/without methotrexate. METHODS: A two-center prospective study in PRD patients aged 2-18 years treated with adalimumab and methotrexate (GA-M) or adalimumab alone (GA) for ≥ 12 weeks was performed. Adalimumab concentrations were collected 1-9 (maximum concentration; Cmax), and 10-14 days (minimum concentration; Cmin) during ≥ 12 weeks following adalimumab start. Concentrations were analyzed with enzyme-linked immunosorbent assay (lower limit of quantification: 0.5 mg/L). Log-normalized Cmin were compared between GA-M and GA using a standard t-test. RESULTS: Twenty-eight patients (14 per group), diagnosed with juvenile idiopathic arthritis (71.4%), non-infectious uveitis (25%) or chronic recurrent multifocal osteomyelitis (3.6%) completed the study. GA-M included more females (71.4%; GA 35.7%, p = 0.13). At first study visit, children in GA-M had a slightly longer exposure to adalimumab (17.8 months [IQR 9.6, 21.6]) compared to GA (15.8 months [IQR 8.5, 30.8], p = 0.8). Adalimumab dosing was similar between both groups (median dose 40 mg every 14 days) and observed DA was low. Children in GA-M had a 27% higher median overall exposure compared to GA, although median Cmin adalimumab values were statistically not different (p = 0.3). Cmin values ≥ 8 mg/L (upper limit RA) were more frequently observed in GA-M versus GA (79% versus 64%). Overall, a wide range of Cmin values was observed in PRD (0.5 to 26 mg/L). CONCLUSION: This study revealed a high heterogeneity in adalimumab exposure in PRD. Adalimumab exposure tended to be higher with methotrexate co-treatment compared to adalimumab monotherapy although differences were not statistically significant. Most children showed adalimumab exposure exceeding those reported for RA with clinical response, particularly with methotrexate co-treatment. This highlights the need of further investigations to establish model-based personalized treatment strategies in PRD to avoid under- and overexposure. TRIAL REGISTRATION: NCT04042792 , registered 02.08.2019.

Low-dimensional neural ODEs and their application in pharmacokinetics.

Machine Learning (ML) is a fast-evolving field, integrated in many of today's scientific disciplines. With the recent development of neural ordinary differential equations (NODEs), ML provides a new tool to model dynamical systems in the field of pharmacology and pharmacometrics, such as pharmacokinetics (PK) or pharmacodynamics. The novel and conceptionally different approach of NODEs compared to classical PK modeling creates challenges but also provides opportunities for its application. In this manuscript, we introduce the functionality of NODEs and develop specific low-dimensional NODE structures based on PK principles. We discuss two challenges of NODEs, overfitting and extrapolation to unseen data, and provide practical solutions to these problems. We illustrate concept and application of our proposed low-dimensional NODE approach with several PK modeling examples, including multi-compartmental, target-mediated drug disposition, and delayed absorption behavior. In all investigated scenarios, the NODEs were able to describe the data well and simulate data for new subjects within the observed dosing range. Finally, we briefly demonstrate how NODEs can be combined with mechanistic models. This research work enhances understanding of how NODEs can be applied in PK analyses and illustrates the potential for NODEs in the field of pharmacology and pharmacometrics.

Systems Pharmacodynamic Model of Combined Gemcitabine and Trabectedin in Pancreatic Cancer Cells. Part II: Cell Cycle, DNA Damage Response, and Apoptosis Pathways.

Despite decades of research efforts, pancreatic adenocarcinoma (PDAC) continues to present a formidable clinical challenge, demanding innovative therapeutic approaches. In a prior study, we reported the synergistic cytotoxic effects of gemcitabine and trabectedin on pancreatic cancer cells. To investigate potential mechanisms underlying this synergistic pharmacodynamic interaction, liquid chromatography-mass spectrometry-based proteomic analysis was performed, and a systems pharmacodynamics model (SPD) was developed to capture pancreatic cancer cell responses to gemcitabine and trabectedin, alone and combined, at the proteome level. Companion report Part I describes the proteomic workflow and drug effects on the upstream portion of the SPD model related to cell growth and migration, specifically the RTK-, integrin-, GPCR-, and calcium-signaling pathways. This report presents Part II of the SPD model. Here we describe drug effects on pathways associated with cell cycle, DNA damage response (DDR), and apoptosis, and provide insights into underlying mechanisms. Drug combination effects on protein changes in the cell cycle- and apoptosis pathways contribute to the synergistic effects observed between gemcitabine and trabectedin. The SPD model was subsequently incorporated into our previously-established cell cycle model, forming a comprehensive, multi-scale quantification platform for evaluating drug effects across multiple scales, spanning the proteomic-, cellular-, and subcellular levels. This approach provides a quantitative mechanistic framework for evaluating drug-drug interactions in combination chemotherapy, and could potentially serve as a tool to predict combinatorial efficacy and assist in target selection.

Clinically practical pharmacometrics computer model to evaluate and personalize pharmacotherapy in pediatric rare diseases: application to Graves' disease.

Objectives: Graves' disease (GD) with onset in childhood or adolescence is a rare disease (ORPHA:525731). Current pharmacotherapeutic approaches use antithyroid drugs, such as carbimazole, as monotherapy or in combination with thyroxine hormone substitutes, such as levothyroxine, as block-and-replace therapy to normalize thyroid function and improve patients' quality of life. However, in the context of fluctuating disease activity, especially during puberty, a considerable proportion of pediatric patients with GD is suffering from thyroid hormone concentrations outside the therapeutic reference ranges. Our main goal was to develop a clinically practical pharmacometrics computer model that characterizes and predicts individual disease activity in children with various severity of GD under pharmacotherapy. Methods: Retrospectively collected clinical data from children and adolescents with GD under up to two years of treatment at four different pediatric hospitals in Switzerland were analyzed. Development of the pharmacometrics computer model is based on the non-linear mixed effects approach accounting for inter-individual variability and incorporating individual patient characteristics. Disease severity groups were defined based on free thyroxine (FT4) measurements at diagnosis. Results: Data from 44 children with GD (75% female, median age 11 years, 62% receiving monotherapy) were analyzed. FT4 measurements were collected in 13, 15, and 16 pediatric patients with mild, moderate, or severe GD, with a median FT4 at diagnosis of 59.9 pmol/l (IQR 48.4, 76.8), and a total of 494 FT4 measurements during a median follow-up of 1.89 years (IQR 1.69, 1.97). We observed no notable difference between severity groups in terms of patient characteristics, daily carbimazole starting doses, and patient years. The final pharmacometrics computer model was developed based on FT4 measurements and on carbimazole or on carbimazole and levothyroxine doses involving two clinically relevant covariate effects: age at diagnosis and disease severity. Discussion: We present a tailored pharmacometrics computer model that is able to describe individual FT4 dynamics under both, carbimazole monotherapy and carbimazole/levothyroxine block-and-replace therapy accounting for inter-individual disease progression and treatment response in children and adolescents with GD. Such clinically practical and predictive computer model has the potential to facilitate and enhance personalized pharmacotherapy in pediatric GD, reducing over- and underdosing and avoiding negative short- and long-term consequences. Prospective randomized validation trials are warranted to further validate and fine-tune computer-supported personalized dosing in pediatric GD and other rare pediatric diseases.

Computing optimal drug dosing with OptiDose: implementation in NONMEM.

Determining a drug dosing recommendation with a PKPD model can be a laborious and complex task. Recently, an optimal dosing algorithm (OptiDose) was developed to compute the optimal doses for any pharmacometrics/PKPD model for a given dosing scenario. In the present work, we reformulate the underlying optimal control problem and elaborate how to solve it with standard commands in the software NONMEM. To demonstrate the potential of the OptiDose implementation in NONMEM, four relevant but substantially different optimal dosing tasks are solved. In addition, the impact of different dosing scenarios as well as the choice of the therapeutic goal on the computed optimal doses are discussed.

Evaluation of machine learning methods for covariate data imputation in pharmacometrics.

Missing data create challenges in clinical research because they lead to loss of statistical power and potentially to biased results. Missing covariate data must be handled with suitable approaches to prepare datasets for pharmacometric analyses, such as population pharmacokinetic and pharmacodynamic analyses. To this end, various statistical methods have been widely adopted. Here, we introduce two machine-learning (ML) methods capable of imputing missing covariate data in a pharmacometric setting. Based on a previously published pharmacometric analysis, we simulated multiple missing data scenarios. We compared the performance of four established statistical methods, listwise deletion, mean imputation, standard multiple imputation (hereafter "Norm"), and predictive mean matching (PMM) and two ML based methods, random forest (RF) and artificial neural networks (ANNs), to handle missing covariate data in a statistically plausible manner. The investigated ML-based methods can be used to impute missing covariate data in a pharmacometric setting. Both traditional imputation approaches and ML-based methods perform well in the scenarios studied, with some restrictions for individual methods. The three methods exhibiting the best performance in terms of least bias for the investigated scenarios are the statistical method PMM and the two ML-based methods RF and ANN. ML-based approaches had comparable good results to the best performing established method PMM. Furthermore, ML methods provide added flexibility when encountering more complex nonlinear relationships, especially when associated parameters are suitably tuned to enhance predictive performance.

Leveraging Predictive Pharmacometrics-Based Algorithms to Enhance Perinatal Care-Application to Neonatal Jaundice.

The field of medicine is undergoing a fundamental change, transforming towards a modern data-driven patient-oriented approach. This paradigm shift also affects perinatal medicine as predictive algorithms and artificial intelligence are applied to enhance and individualize maternal, neonatal and perinatal care. Here, we introduce a pharmacometrics-based mathematical-statistical computer program (PMX-based algorithm) focusing on hyperbilirubinemia, a medical condition affecting half of all newborns. Independent datasets from two different centers consisting of total serum bilirubin measurements were utilized for model development (342 neonates, 1,478 bilirubin measurements) and validation (1,101 neonates, 3,081 bilirubin measurements), respectively. The mathematical-statistical structure of the PMX-based algorithm is a differential equation in the context of non-linear mixed effects modeling, together with Empirical Bayesian Estimation to predict bilirubin kinetics for a new patient. Several clinically relevant prediction scenarios were validated, i.e., prediction up to 24 h based on one bilirubin measurement, and prediction up to 48 h based on two bilirubin measurements. The PMX-based algorithm can be applied in two different clinical scenarios. First, bilirubin kinetics can be predicted up to 24 h based on one single bilirubin measurement with a median relative (absolute) prediction difference of 8.5% (median absolute prediction difference 17.4 µmol/l), and sensitivity and specificity of 95.7 and 96.3%, respectively. Second, bilirubin kinetics can be predicted up to 48 h based on two bilirubin measurements with a median relative (absolute) prediction difference of 9.2% (median absolute prediction difference 21.5 µmol/l), and sensitivity and specificity of 93.0 and 92.1%, respectively. In contrast to currently available nomogram-based static bilirubin stratification, the PMX-based algorithm presented here is a dynamic approach predicting individual bilirubin kinetics up to 48 h, an intelligent, predictive algorithm that can be incorporated in a clinical decision support tool. Such clinical decision support tools have the potential to benefit perinatal medicine facilitating personalized care of mothers and their born and unborn infants.

Infliximab Treatment Does Not Lead to Full TNF-α Inhibition: A Target-Mediated Drug Disposition Model.

BACKGROUND AND OBJECTIVE: Infliximab, an anti-tumour necrosis factor (TNF)-α monoclonal antibody, has been approved in chronic inflammatory disease, including rheumatoid arthritis, Crohn's disease and ankylosing spondylitis. This study aimed to investigate and characterise target-mediated drug disposition of infliximab and antigen mass turnover during infliximab treatment. METHODS: In this retrospective cohort of 186 patients treated with infliximab for rheumatoid arthritis, Crohn's disease or ankylosing spondylitis, trough infliximab concentrations were determined from samples collected between weeks 0 and 22 after treatment initiation. Target-mediated pharmacokinetics of infliximab was described using target-mediated drug disposition modelling. Target-mediated elimination parameters were determined for rheumatoid arthritis and Crohn's disease, assuming ankylosing spondylitis with no target-mediated elimination. RESULTS: The quasi-equilibrium approximation of a target-mediated drug disposition model allowed a satisfactory description of infliximab concentration-time data. Estimated baseline TNF-α amounts were similar in Crohn's disease and rheumatoid arthritis (R0 = 0.39 vs 0.46 nM, respectively), but infliximab-TNF complex elimination was slower in Crohn's disease than in rheumatoid arthritis (kint = 0.024 vs 0.061 day-1, respectively). Terminal elimination half-lives were 13.5, 21.5 and 16.5 days for rheumatoid arthritis, Crohn's disease and ankylosing spondylitis, respectively. Estimated amounts of free target were close to baseline values before the next infusion suggesting that TNF-α inhibition may not be sustained over the entire dose interval. CONCLUSIONS: The present study is the first to quantify the influence of target antigen dynamics on infliximab pharmacokinetics. Target-mediated elimination of infliximab may be complex, involving a multi-scale turnover of TNF-α, especially in patients with Crohn's disease. Additional clinical studies are warranted to further evaluate and fine-tune dosing approaches to ensure sustained TNF-α inhibition.

OptiDose: Computing the Individualized Optimal Drug Dosing Regimen Using Optimal Control.

Providing the optimal dosing strategy of a drug for an individual patient is an important task in pharmaceutical sciences and daily clinical application. We developed and validated an optimal dosing algorithm (OptiDose) that computes the optimal individualized dosing regimen for pharmacokinetic-pharmacodynamic models in substantially different scenarios with various routes of administration by solving an optimal control problem. The aim is to compute a control that brings the underlying system as closely as possible to a desired reference function by minimizing a cost functional. In pharmacokinetic-pharmacodynamic modeling, the controls are the administered doses and the reference function can be the disease progression. Drug administration at certain time points provides a finite number of discrete controls, the drug doses, determining the drug concentration and its effect on the disease progression. Consequently, rewriting the cost functional gives a finite-dimensional optimal control problem depending only on the doses. Adjoint techniques allow to compute the gradient of the cost functional efficiently. This admits to solve the optimal control problem with robust algorithms such as quasi-Newton methods from finite-dimensional optimization. OptiDose is applied to three relevant but substantially different pharmacokinetic-pharmacodynamic examples.

Delay differential equations based models in NONMEM.

Delay differential equations (DDEs) are commonly used in pharmacometric models to describe delays present in pharmacokinetic and pharmacodynamic data analysis. Several DDE solvers have been implemented in NONMEM 7.5 for the first time. Two of them are based on algorithms already applied elsewhere, while others are extensions of existing ordinary differential equations (ODEs) solvers. The purpose of this tutorial is to introduce basic concepts underlying DDE based models and to show how they can be developed using NONMEM. The examples include previously published DDE models such as logistic growth, tumor growth inhibition, indirect response with precursor pool, rheumatoid arthritis, and erythropoiesis-stimulating agents. We evaluated the accuracy of NONMEM DDE solvers, their ability to handle stiff problems, and their performance in parameter estimation using both first-order conditional estimation (FOCE) and the expectation-maximization (EM) method. NONMEM control streams and excerpts from datasets are provided for all discussed examples. All DDE solvers provide accurate and precise solutions with the number of significant digits controlled by the error tolerance parameters. For estimation of population parameters, the EM method is more stable than FOCE regardless of the DDE solver.

Modeling of levothyroxine in newborns and infants with congenital hypothyroidism: challenges and opportunities of a rare disease multi-center study.

Modeling of retrospectively collected multi-center data of a rare disease in pediatrics is challenging because laboratory data can stem from several decades measured with different assays. Here we present a retrospective pharmacometrics (PMX) based data analysis of the rare disease congenital hypothyroidism (CH) in newborns and infants. Our overall aim is to develop a model that can be applied to optimize dosing in this pediatric patient population since suboptimal treatment of CH during the first 2 years of life is associated with a reduced intelligence quotient between 10 and 14 years. The first goal is to describe a retrospectively collected dataset consisting of 61 newborns and infants with CH up to 2 years of age. Overall, 505 measurements of free thyroxine (FT4) and 510 measurements of thyrotropin or thyroid-stimulating hormone were available from patients receiving substitution treatment with levothyroxine (LT4). The second goal is to introduce a scale/location-scale normalization method to merge available FT4 measurements since 34 different postnatal age- and assay-specific laboratory reference ranges were applied. This method takes into account the change of the distribution of FT4 values over time, i.e. a transformation from right-skewed towards normality during LT4 treatment. The third goal is to develop a practical and useful PMX model for LT4 treatment to characterize FT4 measurements, which is applicable within a clinical setting. In summary, a time-dependent normalization method and a practical PMX model are presented. Since there is no on-going or planned development of new pharmacological approaches for CH, PMX based modeling and simulation can be leveraged to personalize dosing with the goal to enhance longer-term neurological outcome in children with the rare disease CH.

The rhythm of a preterm neonate's life: ultradian oscillations of heart rate, body temperature and sleep cycles.

The objectives are to characterize oscillations of physiological functions such as heart rate and body temperature, as well as the sleep cycle from behavioral states in generally stable preterm neonates during the first 5 days of life. Heart rate, body temperature as well as behavioral states were collected during a daily 3-h observation interval in 65 preterm neonates within the first 5 days of life. Participants were born before 32 weeks of gestational age or had a birth weight below 1500 g; neonates with asphyxia, proven sepsis or malformation were excluded. In total 263 observation intervals were available. Heart rate and body temperature were analyzed with mathematical models in the context of non-linear mixed effects modeling, and the sleep cycles were characterized with signal processing methods. The average period length of an oscillation in this preterm neonate population was 159 min for heart rate, 290 min for body temperature, and the average sleep cycle duration was 19 min. Oscillation of physiological functions as well as sleep cycles can be characterized in very preterm neonates within the first few days of life. The observed parameters heart rate, body temperature and sleep are running in a seemingly uncorrelated pace at that stage of development. Knowledge about such oscillations may help to guide nursing and medical care in these neonates as they do not yet follow a circadian rhythm.

Copeptin Kinetics and Its Relationship to Osmolality During Rehydration for Diabetic Ketoacidosis in Children.

CONTEXT: Copeptin is a surrogate marker for arginine vasopressin (AVP) release in response to hyperosmolal stimuli such as diabetic ketoacidosis (DKA). OBJECTIVE: The objective of this work is to characterize kinetics of copeptin and osmolality, and their dynamic relationship during rehydration and insulin therapy in children with type 1 diabetes (T1D) and DKA. DESIGN AND SETTING: A prospective, observational, multicenter study was conducted. PATIENTS AND INTERVENTION: Children with T1D admitted for DKA underwent serial serum copeptin and osmolality measurements from start of rehydration at 14 time points during 72 hours. MAIN OUTCOME MEASURES: Measurements included temporal course of copeptin and osmolality (kinetics), relationship between both (dynamics), and association between-subject variability (BSV) (coefficient of variation, CV%). RESULTS: Twenty-eight children (20 newly diagnosed T1D) aged 1 to 16 years were included. Copeptin decreased from 95 pmol/L (95% CI, 55-136 pmol/L) (CV%, 158%) to 9.7 pmol/L (95% CI, 8.1-11.4 pmol/L) (CV%, 31%) with a 50% recovery time (t1/2) of 7.1 hours (range, 5.1-11.5 hours) (114%). Serum osmolality decreased from 321 mOsm/kg (range, 315-327 mOsm/kg) (4%) to 294 mOsm/kg (range, 292-296 mOsm/kg) (1%) with a t1/2 of 4.3 hours (range, 3.0-5.6 hours) (64%). Copeptin levels doubled with each osmolality increase by 15 mOsm/kg (range, 10-21 mOsm/kg) (59%), from 9.8 pmol/L (range, 7.3-12.3 pmol/L) (48%) to 280 mOsm/kg. Copeptin kinetics differed between newly diagnosed and known T1D patients (P = .001), and less between mild vs moderate-severe DKA (P = .04). CONCLUSIONS: First, this study characterized for the first time copeptin kinetics and dynamics in the high hyperosmolar range in children with DKA. Second, it revealed significant differences in copeptin kinetics between newly diagnosed and known T1D patients that may be explained by changes at the osmoreceptor and renal AVP receptor level due to longstanding osmotic diuresis and DKA.

Caffeine preserves quiet sleep in preterm neonates.

Caffeine is widely used in preterm neonates suffering from apnea of prematurity (AOP), and it has become one of the most frequently prescribed medications in neonatal intensive care units. Goal of this study is to investigate how caffeine citrate treatment affects sleep-wake behavior in preterm neonates. The observational study consists of 64 preterm neonates during their first 5 days of life with gestational age (GA) <32 weeks or very low birthweight of < 1500 g. A total of 52 patients treated with caffeine citrate and 12 patients without caffeine citrate were included. Sleep-wake behavior was scored in three stages: active sleep, quiet sleep, and wakefulness. Individual caffeine concentration of every neonate was simulated with a pharmacokinetic model. In neonates with GA ≥ 28 weeks, wakefulness increased and active sleep decreased with increasing caffeine concentrations, whereas quiet sleep remained unchanged. In neonates with GA < 28 weeks, no clear caffeine effects on sleep-wake behavior could be demonstrated. Caffeine increases fraction of wakefulness, alertness, and most probably also arousability at cost of active but not quiet sleep in preterm neonates. As such, caffeine should therefore not affect time for physical and cerebral regeneration during sleep in preterm neonates.

Pharmacometrics and Machine Learning Partner to Advance Clinical Data Analysis.

Clinical pharmacology is a multidisciplinary data sciences field that utilizes mathematical and statistical methods to generate maximal knowledge from data. Pharmacometrics (PMX) is a well-recognized tool to characterize disease progression, pharmacokinetics, and risk factors. Because the amount of data produced keeps growing with increasing pace, the computational effort necessary for PMX models is also increasing. Additionally, computationally efficient methods, such as machine learning (ML) are becoming increasingly important in medicine. However, ML is currently not an integrated part of PMX, for various reasons. The goals of this article are to (i) provide an introduction to ML classification methods, (ii) provide examples for a ML classification analysis to identify covariates based on specific research questions, (iii) examine a clinically relevant example to investigate possible relationships of ML and PMX, and (iv) present a summary of ML and PMX tasks to develop clinical decision support tools.

Clinical Pharmacology and Pharmacometrics to Better Understand Physiological Changes During Pregnancy and Neonatal Life.

Pregnant women, fetuses, and newborns are particularly vulnerable patient populations. During pregnancy, the body is subject to physiological changes that influence the pharmacokinetics and pharmacodynamics of drugs. Inappropriate dosing in pregnant women can result in sub-therapeutic or toxic effects, putting not only the pregnant woman but also her fetus at risk. During neonatal life, maturation processes also affect pharmacokinetics and pharmacodynamics of drugs. Inappropriate dosing in newborns leads not only to short-term complications but can also have a negative impact on the long-term development of infants and children. For these reasons, it is crucial to characterize physiological changes in pregnant women, describe placental transfer kinetics of drugs, and describe physiological changes related to the transition from intrauterine to extrauterine life and maturation processes in preterm and term neonates. Quantitative pharmacological approaches such as pharmacometric and physiologically-based modeling and model-based simulations can be useful to better understand and predict such physiological changes and their effects on drug exposure and response. This review article (1) gives an overview of physiological changes in pregnant women, their fetuses, and (pre)term neonates, (2) presents case studies to illustrate applications of new modeling and simulation approaches, and (3) discusses challenges and opportunities in optimizing and personalizing treatments during pregnancy and neonatal life.