Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.

We are overwhelmed by a deluge of data and, although its interpretation is challenging, fortunately, information technology comes to the rescue. One of the tools is artificial intelligence, allowing the identification of relationships between variables and their arbitrary classification. We focused on the assessment of both the remission of proteinuria and the deterioration of kidney function in patients with IgA nephropathy, comparing several methods of machine learning. It is of utmost importance to respond to subtle changes in kidney function, which will lead to a deceleration of the disease. This goal has been achieved by analyzing regression techniques, predicting the difference in serum creatinine concentration. We obtained the performance of the tested models which classified patients with high accuracy (Random Forest Classifier showed an accuracy of 0.8–1.0, Multi-Layer Perceptron an Area Under Curve of 0.8842–0.9035 and an accuracy of 0.7527–1.0) and regressors with a low estimation error (Decision Tree Regressor showed MAE 0.2059, RMSE 0.2645). We have demonstrated the impact of both model selection and input features on performance. Application of machine learning methods requires careful selection of models and assessed parameters. The computing power of modern computers allows searching for the models most effective in terms of accuracy.

Pathogenic viral factors pose a serious epidemiological threat and challenge to the world population, as proven by the scale and rapidity of COVID-19 pandemic outbreak. Polymer macromolecules can be an alternative to the accepted forms of treatment. Polymeric substances can be used as drugs or as adjuvants in vaccines. The most important feature of polymers is their advanced structure and the ability to construct the molecule from scratch, giving it the desired properties. Antiviral properties are influenced by, among other things, electrical charge, form and structure, and composition with other polymers or heavy metals. Depending on the expected properties, molecules can be built from scratch to be capable of transporting drugs or improve the effectiveness of the right drug. They can also be antiviral drugs in themselves. Polymeric compounds allow to reduce the frequency of adverse effects and improve the effect of the drug. They can have a direct antiviral effect by upsetting the lipid membrane of the surrounding viruses. Antiviral action of polymers occurs because of the properties of the polymers alone or in combination with other molecules. Viral epidemics are a motivation for research that can help stop a global pandemic in the future.

Viruses that are pathogenic to humans and livestock pose a serious epidemiological threat and challenge the world's population. The SARS-CoV-2/COVID-19 pandemic has made the world aware of the scale of the threat. The surfaces of various materials can be a source of viruses that remain temporarily contagious in the environment. Few polymers have antiviral effects that reduce infectivity or the presence of a virus in the human environment. Some of the effects are due to certain physical properties, e.g., high hydrophobicity. Other materials owe their antiviral activity to a modified physicochemical structure favoring the action on specific virus receptors or on their biochemistry. Current research areas include: gluten, polyvinylidene fluoride, polyimide, polylactic acid, graphene oxide, and polyurethane bound to copper oxide. The future belongs to multi-component mixtures or very thin multilayer systems. The rational direction of research work is the search for materials with a balanced specificity in relation to the most dangerous viruses and universality in relation to other viruses.

Background: Although acute kidney injury (AKI) is a common complication in patients undergoing hematopoietic stem cell transplantation (HSCT), its prophylaxis remains a clinical challenge. Attempts at prevention or early diagnosis focus on various methods for the identification of factors influencing the incidence of AKI. Our aim was to test the artificial intelligence (AI) potential in the construction of a model defining parameters predicting AKI development. Methods: The analysis covered the clinical data of children followed up for 6 months after HSCT. Kidney function was assessed before conditioning therapy, 24 h after HSCT, 1, 2, 3, 4, and 8 weeks after transplantation, and, finally, 3 and 6 months post-transplant. The type of donor, conditioning protocol, and complications were incorporated into the model. Results: A random forest classifier (RFC) labeled the 93 patients according to presence or absence of AKI. The RFC model revealed that the values of the estimated glomerular filtration rate (eGFR) before and just after HSCT, as well as methotrexate use, acute graft versus host disease (GvHD), and viral infection occurrence, were the major determinants of AKI incidence within the 6-month post-transplant observation period. Conclusions: Artificial intelligence seems a promising tool in predicting the potential risk of developing AKI, even before HSCT or just after the procedure.

Background: Normal-anion-gap metabolic acidosis (AGMA) and high-anion-gap metabolic acidosis (HAGMA) are two forms of metabolic acidosis, which is a common complication in patients with chronic kidney disease (CKD). The aim of this study is to identify the prevalence of various acid–base disorders in patients with advanced CKD using point-of-care testing (POCT) and to determine the relationship between POCT parameters. Methods: In a group of 116 patients with CKD in stages G4 and G5, with a mean age of 62.5 ± 17 years, a sample of arterial blood was taken during the arteriovenous fistula procedure for POCT, which enables an assessment of the most important parameters of acid–base balance, including: pH, base excess (BE), bicarbonate (HCO₃⁻), chloride(Cl⁻), anion gap (AG), creatinine and urea concentration. Based on this test, patients were categorized according to the type of acidosis-base disorder. Results: Decompensate acidosis with a pH < 7.35 was found in 68 (59%) patients. Metabolic acidosis (MA), defined as the concentration of HCO₃⁻ ≤ 22 mmol/L, was found in 92 (79%) patients. In this group, significantly lower pH, BE, HCO₃⁻ and Cl⁻ concentrations were found. In group of MA patients, AGMA and HAGMA was observed in 48 (52%) and 44 (48%) of patients, respectively. The mean creatinine was significantly lower in the AGMA group compared to the HAGMA group (4.91 vs. 5.87 mg/dL, p < 0.05). The AG correlated positively with creatinine (r = 0.44, p < 0.01) and urea (r = 0.53, p < 0.01), but there was no correlation between HCO₃⁻ and both creatinine (r = −0.015, p > 0.05) and urea (r = −0.07, p > 0.05). The Cl⁻ concentrations correlated negatively with HCO₃⁻ (r = −0.8, p < 0.01). Conclusions: The most common type of acid–base disturbance in CKD patients in stages 4 and 5 is AGMA, which is observed in patients with better kidney function and is associated with compensatory hyperchloremia. The initiation of renal replacement therapy was significantly earlier for patients diagnosed with HAGMA compared to those diagnosed with AGMA. The more advanced the CKD, the higher the AG.