Learning pharmacokinetic models for in vivo glucocorticoid activation

Abstract

In vivo glucocorticoid activation Probabilistic models Gaussian mixture model Expectation maximization Clustering Partially observed time series analysis a b s t r a c tTo understand trends in individual responses to medication, one can take a purely data-driven machine learning approach, or alternatively apply pharmacokinetics combined with mixed-effects statistical modelling. To take advantage of the predictive power of machine learning and the explanatory power of pharmacokinetics, we propose a latent variable mixture model for learning clusters of pharmacokinetic models demonstrated on a clinical data set investigating 11 β-hydroxysteroid dehydrogenase enzymes (11 β-HSD) activity in healthy adults. The proposed strategy automatically constructs different population models that are not based on prior knowledge or experimental design, but result naturally as mixture component models of the global latent variable mixture model. We study the parameter of the underlying multi-compartment ordinary differential equation model via identifiability analysis on the observable measurements, which reveals the model is structurally locally identifiable. Further approximation with a perturbation technique enables efficient training of the proposed probabilistic latent variable mixture clustering technique using Estimation Maximization. The training on the clinical data results in 4 clusters reflecting the prednisone conversion rate over a period of 4 h based on venous blood samples taken at 20-min intervals. The learned clusters differ in prednisone absorption as well as prednisone/prednisolone conversion. In the discussion section we include a detailed investigation of the relationship of the pharmacokinetic parameters of the trained cluster models for possible or plausible physiological explanation and correlations analysis using additional phenotypic participant measurements.

Artificial intelligence methods for a Bayesian epistemology‐powered evidence evaluation

“…Machine learning could play a fundamental role also in modelling mechanisms within E‐Synthesis . There is already an abundant literature on its use in pharmacokinetics and pharmacodynamics 44,45 to figure out possible and impossible biochemical mechanisms, bypassing in vitro and in vivo checks by fast and efficient deployment of in silico analyses. Likewise, a better understanding of absorption, distribution, metabolization mechanisms—which prove critical for dose‐response and drug concentration estimation in drug delivery processes—has been highly accelerated by computer simulations 46 and machine learning 47,48 .…”

Machine learning in pharmacometrics: Opportunities and challenges

“…Bunte et al evaluated combined parameter estimation and clustering approach for population PK modelling of prednisolone 153 . The parameters for a 2‐compartment model of prednisolone were obtained using MLE and combined with Gaussian mixture modelling for clustering with the EM algorithm.…”

Impact of Cannabidiol oil and prednisolone on liver enzymes, oxidative stress markers and liver histology in cadmium induced toxicity in male Wistar rats

“…Prednisone is a delayedrelease corticosteroid indicated as an antiinflammatory or immunosuppressive agent to treat a broad range of disorders such as immunosuppression, rheumatism, collagen, dermatologic, allergic, ophthalmic, respiratory, hematologic, neoplastic, edematous, gastrointestinal, acute exacerbations of multiple sclerosis, and as an anti-inflammatory and an antineoplastic agent (Renner et al, 1986). It works on the immune system to help relieve swelling, redness, itching, and allergic reactions (Bunte et al, 2018). Prednisone decreases inflammation via suppression in the migration of polymorphonuclear leukocytes and reversing increased capillary permeability.…”

“…Prednisone decreases inflammation via suppression in the migration of polymorphonuclear leukocytes and reversing increased capillary permeability. It also suppresses the immune system by reducing the activity and volume of the immune system (Bunte et al, 2018). Cadmium is one of the toxic heavy metals in the environment that induces oxidative stress, dyslipidemia, and membrane disturbances in the heart.…”