The adenosine monophosphate activated protein kinase (AMPK) is critical in the regulation of important cellular functions such as lipid, glucose, and protein metabolism; mitochondrial biogenesis and autophagy; and cellular growth. In many diseases—such as metabolic syndrome, obesity, diabetes, and also cancer—activation of AMPK is beneficial. Therefore, there is growing interest in AMPK activators that act either by direct action on the enzyme itself or by indirect activation of upstream regulators. Many natural compounds have been described that activate AMPK indirectly. These compounds are usually contained in mixtures with a variety of structurally different other compounds, which in turn can also alter the activity of AMPK via one or more pathways. For these compounds, experiments are complicated, since the required pure substances are often not yet isolated and/or therefore not sufficiently available. Therefore, our goal was to develop a screening tool that could handle the profound heterogeneity in activation pathways of the AMPK. Since machine learning algorithms can model complex (unknown) relationships and patterns, some of these methods (random forest, support vector machines, stochastic gradient boosting, logistic regression, and deep neural network) were applied and validated using a database, comprising of 904 activating and 799 neutral or inhibiting compounds identified by extensive PubMed literature search and PubChem Bioassay database. All models showed unexpectedly high classification accuracy in training, but more importantly in predicting the unseen test data. These models are therefore suitable tools for rapid in silico screening of established substances or multicomponent mixtures and can be used to identify compounds of interest for further testing.

This study aimed to determine cefazolin target attainment in patients with invasive Staphylococcus aureus (S. aureus) infections and to develop a population pharmacokinetic (PK) model. Adult patients with invasive S. aureus infections treated with cefazolin bolus infusions were included. Unbound and total trough and mid-dose cefazolin concentrations were measured, and strain-specific MICs were determined. The primary outcome was the proportion of patients attaining 100% fT_>MIC at all time points evaluated. A population PK model was developed, using non-linear mixed-effects modelling. Overall, 51 patients were included, with a total of 226 unbound and total cefazolin concentrations measured (mean: 4.4 per patient). The median daily dosage in patients with an estimated glomerular filtration rate of >60 mL/min/m² was 8 g. The median age was 74 years (interquartile range (IQR) 57–82) and 26% were female. A history of chronic kidney disease and acute kidney injury were present in 10/51 (19.6%) and 6/51 (11.7%), respectively. Achievement of 100% fT_>MIC occurred in 86% of the patients and decreased to 45% when a target of 100% fT_>4xMIC was evaluated. The mean unbound cefazolin fraction was 27.0% (standard deviation (SD) 13.4). Measured and estimated mean cefazolin trough concentrations differed significantly [13.1 mg/L (SD 23.5) vs. 7.4 mg/L (SD 7.9), p < 0.001]. In the population PK model, elevated estimated creatinine clearance and bolus instead of continuous application were covariates for target non-attainment. In conclusion, cefazolin target achievement was high, and the measurement of the unbound cefazolin concentration may be favored. The Monte Carlo simulations indicated that target attainment was significantly improved with continuous infusion.

Cimicifuga racemosa (CR) extracts contain diverse constituents such as saponins. These saponins, which act as a defense against herbivores and pathogens also show promise in treating human conditions such as heart failure, pain, hypercholesterolemia, cancer, and inflammation. Some of these effects are mediated by activating AMP-dependent protein kinase (AMPK). Therefore, comprehensive screening for activating constituents in a CR extract is highly desirable. Employing machine learning (ML) techniques such as Deep Neural Networks (DNN), Logistic Regression Classification (LRC), and Random Forest Classification (RFC) with molecular fingerprint MACCS descriptors, 95 CR constituents were classified. Calibration involved 50 randomly chosen positive and negative controls. LRC achieved the highest overall test accuracy (90.2%), but DNN and RFC surpassed it in precision, sensitivity, specificity, and ROC AUC. All CR constituents were predicted as activators, except for three non-triterpene compounds. The validity of these classifications was supported by good calibration, with misclassifications ranging from 3% to 17% across the various models. High sensitivity (84.5–87.2%) and specificity (84.1–91.4%) suggest suitability for screening. The results demonstrate the potential of triterpene saponins and aglycones in activating AMP-dependent protein kinase (AMPK), providing the rationale for further clinical exploration of CR extracts in metabolic pathway-related conditions.

Objectives: Several risk factors have been identified for severe clinical outcomes of COVID-19 caused by SARS-CoV-2. Some can be found in structured data of patients’ Electronic Health Records. Others are included as unstructured free-text, and thus cannot be easily detected automatically. We propose an automated real-time detection of risk factors using a combination of data mining and Natural Language Processing (NLP). Material and methods: Patients were categorized as negative or positive for SARS-CoV-2, and according to disease severity (severe or non-severe COVID-19). Comorbidities were identified in the unstructured free-text using NLP. Further risk factors were taken from the structured data. Results: 6250 patients were analysed (5664 negative and 586 positive; 461 non-severe and 125 severe). Using NLP, comorbidities, i.e. cardiovascular and pulmonary conditions, diabetes, dementia and cancer, were automatically detected (error rate ≤2%). Old age, male sex, higher BMI, arterial hypertension, chronic heart failure, coronary heart disease, COPD, diabetes, insulin only treatment of diabetic patients, reduced kidney and liver function were risk factors for severe COVID-19. Interestingly, the proportion of diabetic patients using metformin but not insulin was significantly higher in the non-severe COVID-19 cohort (p<0.05). Discussion and conclusion: Our findings were in line with previously reported risk factors for severe COVID-19. NLP in combination with other data mining approaches appears to be a suitable tool for the automated real-time detection of risk factors, which can be a time saving support for risk assessment and triage, especially in patients with long medical histories and multiple comorbidities.

Background: Optimal antibiotic dosing for Staphylococcus aureus bloodstream infections (BSI) is still controversial. One reason is inter-individual variation in pharmacokinetics, which may be influenced by various patient-related factors, particularly in critically ill patients. Objectives: To describe the population pharmacokinetics (PopPK) of the antibiotic flucloxacillin in patients with S. aureus BSI. Subsequently, we sought to translate the model into a user-friendly app for generating a priori and a posteriori time–concentration curves and dose recommendations to optimize dosing regimens. Methods: Total and unbound flucloxacillin concentrations were included from 49 patients from a prospective cohort study conducted during clinical routine, including non-critically ill and critically ill individuals who received intermittent bolus applications. These data were analysed using non-linear mixed-effects modelling. Results: Most patients (98%) were treated with 2 g of flucloxacillin every 4 h. We developed a joint model that simultaneously described total and unbound concentrations. The model included an allometric effect of glomerular filtration rate on clearance and albumin on the albumin dissociation constant. The latter was especially important, as in our population the unbound fraction was higher at 11.5% (16.7% for critically ill patients) compared with reported values of approximately 5%. Based on our joint model, we developed a web-based app for optimizing dosing regimens of flucloxacillin. Conclusions: By utilizing data from clinical routine, we were able to create a predictive PopPK model of flucloxacillin and identify influential covariates. The web-based app is currently being validated in a clinical trial.