Antimicrobial Activity Classification of Imidazolium Derivatives Predicted by Artificial Neural Networks.

PURPOSE: This study assesses the Multilayer Perceptron (MLP) neural network, complemented by other Machine Learning techniques (CART, PCA), in predicting the antimicrobial activity of 140 newly designed imidazolium chlorides against Klebsiella pneumoniae before synthesis. Emphasis is on leveraging molecular properties for predictive analysis. METHODS: Classification and regression decision trees (CART) identified the top 200 predictive molecular descriptors. Principal Component Analysis (PCA) reduced these descriptors to 5 components, retaining 99.57% of raw data information. Antimicrobial activity, categorized as high or low, was based on experimentally proven minimal inhibitory concentration (MIC), with a cut-point at MIC = 0.856 mol/L. A 12-fold cross-validation trained the MLP (architecture 5-12-2 with 5 Principal Components). RESULTS: The MLP exhibited commendable performance, achieving almost 90% correct classifications across learning, validation, and test sets, outperforming models without PCA dimension reduction. Key metrics, including accuracy (0.907), sensitivity (0.905), specificity (0.909), and precision (0.891), were notably high. These results highlight the MLP model's efficacy with PCA as a high-quality classifier for determining antimicrobial activity. CONCLUSIONS: The study concludes that the MLP neural network, along with CART and PCA, is a robust tool for predicting the antimicrobial activity class of imidazolium chlorides against Klebsiella pneumoniae. CART and PCA, used in this study, allowed input variable reduction without significant information loss. High classification accuracy and associated metrics affirm the method's potential utility in pre-synthesis assessments, offering valuable insights for antimicrobial compound design.

Quantitative anatomy of the extensor digiti minimi muscle in the growing human fetus.

Introduction Age-specific reference intervals for the extensor digiti minimi muscle (EDMM) in the human fetus may be relevant in the detailed evaluation of the musculoskeletal systems with potential relevant aspects for surgical treatment. The aim of the study was to examine the age-specific reference intervals and growth dynamics of the EDMM in relation to its length, width, projection surface area and volume. Material and methods The examined material included 70 human formalin-fixed fetuses of both sexes (37♀, 33♂) aged from 17 to 29 weeks. With the use of anatomical dissection every EDMM was visualized, recorded in a form of JPG formats and analyzed by the digital image analysis system and statistical methods. Results No variability of the EDMM was found. All the morphometric parameters of the EDMM revealed neither sex nor laterality differences. With fetal age most linear parameters of the EDMM concerning its examined lengths and widths increased in accordance with natural logarithmic functions. The only two exceptions to this referred to the belly width of EDMM measured at its mid-length and the tendon width of EDMM measured proximal to the extensor retinaculum of wrist, which both followed square root functions. The projection surface areas of the EDMM followed natural logarithmic functions, while the volumetric growth of the EDMM was proportionate to fetal age. Conclusions The variability of the EDMM in the human fetus is minimal. The morphometric data of the EDMM represents age-specific reference intervals of clinical significance. Morphometric parameters of the EDMM reveal neither sex nor laterality differences. The EDMM displays three different growth dynamics: from gradual growth deceleration according to both natural logarithmic functions (total length of the muscle and its tendons, belly length, tendon lengths, belly width at its origin, tendon width at its insertion, and projection surface areas) and square root functions (belly width at its mid-length and tendon width in the pre-retinacular segment) to a proportionate growth (total volume).

Application of artificial neural networks to evaluate femur development in the human fetus.

The present article concentrates on an innovative analysis that was performed to assess the development of the femur in human fetuses using artificial intelligence. As a prerequisite, linear dimensions, cross-sectional surface areas and volumes of the femoral shaft primary ossification center in 47 human fetuses aged 17-30 weeks, originating from spontaneous miscarriages and preterm deliveries, were evaluated with the use of advanced imaging techniques such as computed tomography and digital image analysis. In order to ensure the data representativeness and to avoid introducing any hidden structures that may exist in the data, the entire dataset was randomized and separated into three subsets: training (50% of cases), testing (25% of cases), and validation (25% of cases). Based on the collected numerical data, an artificial neural network was devised, trained, and subject to testing in order to synchronously estimate five parameters of the femoral shaft primary ossification center, thus leveraging fundamental information such as gestational age and femur length. The findings reveal the formulated multi-layer perceptron model denoted as MLP 2-3-2-5 to exhibit robust predictive efficacy, as evidenced by the linear correlation coefficient between actual values and network outputs: R = 0.955 for the training dataset, R = 0.942 for validation, and R = 0.953 for the testing dataset. The authors have cogently demonstrated that the use of an artificial neural network to assess the growing femur in the human fetus may be a valuable tool in prenatal tests, enabling medical doctors to quickly and precisely assess the development of the fetal femur and detect potential anatomical abnormalities.

Quantitative study of the popliteal fossa in the human fetus.

The popliteal fossa presents an extensive diamond-shaped topographical element on the posterior aspect of the knee. With the use of classical anatomical dissection, digital image analysis of NIS Elements AR 3.0 and statistics we morphometrically analyzed the size of the popliteal fossa in human fetuses aged 17-29 weeks of gestation. Morphometric parameters of the popliteal fossa increased logarithmically with fetal age: y = -44.421 + 24.301 × ln (Age) for length of superomedial boundary, y = -41.379 + 22.777 × ln (Age) for length of superolateral boundary, y = -39.019 + 20.981 × ln (Age) for inferomedial boundary, y = -37.547 + 20.319 × ln (Age), for length of inferolateral boundary, y = -28.915 + 15.822 × ln (Age) for transverse diameter, y = -69.790 + 38.73 × ln (Age) for vertical diameter and y = -485.631 + 240.844 × ln (Age) for projection surface area. Out of the four angles of the popliteal fossa the medial one was greatest, the inferior one the smallest, while the lateral one was somewhat smaller than the medial one and approximately three times greater than the superior one, with no difference with fetal age. In terms of morphometric parameters the popliteal fossa in the human fetus displays neither male-female nor right-left differences. In the popliteal fossa, growth patterns of its four boundaries, vertical and transverse diameters, and projection surface area all follow natural logarithmic functions. All the morphometric data is considered age-specific reference intervals, which may be conducive in the diagnostics of congenital abnormalities in the human fetus.

Stem cell-based interventions for the treatment of stroke in newborn infants.

BACKGROUND: Perinatal stroke refers to a diverse but specific group of cerebrovascular diseases that occur between 20 weeks of fetal life and 28 days of postnatal life. Acute treatment options for perinatal stroke are limited supportive care, such as controlling hypoglycemia and seizures. Stem cell-based therapies offer a potential therapeutic approach to repair, restore, or regenerate injured brain tissue. Preclinical findings have culminated in ongoing human neonatal studies. OBJECTIVES: To evaluate the benefits and harms of stem cell-based interventions for the treatment of stroke in newborn infants compared to control (placebo or no treatment) or stem-cell based interventions of a different type or source. SEARCH METHODS: We searched CENTRAL, PubMed, Embase, and three trials registries in February 2023. We planned to search the reference lists of included studies and relevant systematic reviews for studies not identified by the database searches. SELECTION CRITERIA: We attempted to include randomized controlled trials, quasi-randomized controlled trials, and cluster trials that evaluated any of the following comparisons. • Stem cell-based interventions (any type) versus control (placebo or no treatment) • Mesenchymal stem/stromal cells (MSCs) of a specifictype (e.g. number of doses or passages) or source (e.g. autologous/allogeneic or bone marrow/cord) versus MSCs of another type or source • Stem cell-based interventions (other than MSCs) of a specific type (e.g. mononuclear cells, oligodendrocyte progenitor cells, neural stem cells, hematopoietic stem cells, or induced pluripotent stem cell-derived cells) or source (e.g. autologous/allogeneic or bone marrow/cord) versus stem cell-based interventions (other than MSCs) of another type or source • MSCs versus stem cell-based interventions other than MSCs We planned to include all types of transplantation regardless of cell source (bone marrow, cord blood, Wharton's jelly, placenta, adipose tissue, peripheral blood), type of graft (autologous or allogeneic), and dose. DATA COLLECTION AND ANALYSIS: We used standard Cochrane methods. Our primary outcomes were all-cause neonatal mortality, major neurodevelopmental disability, and immune rejection or any serious adverse event. Our secondary outcomes included all-cause mortality prior to first hospital discharge, seizures, adverse effects, and death or major neurodevelopmental disability at 18 to 24 months of age. We planned to use GRADE to assess the certainty of evidence for each outcome. MAIN RESULTS: We identified no completed or ongoing randomized trials that met our inclusion criteria. We excluded three studies: two were phase 1 trials, and one included newborn infants with conditions other than stroke (i.e. cerebral ischemia and anemia). Among the three excluded studies, we identified the first phase 1 trial on the use of stem cells for neonatal stroke. It reported that a single intranasal application of bone marrow-derived MSCs in term neonates with a diagnosis of perinatal arterial ischemic stroke (PAIS) was feasible and apparently not associated with severe adverse events. However, the trial included only 10 infants, and follow-up was limited to three months. AUTHORS' CONCLUSIONS: No evidence is currently available to evaluate the benefits and harms of stem cell-based interventions for treatment of stroke in newborn infants. We identified no ongoing studies. Future clinical trials should focus on standardizing the timing and method of cell delivery and cell processing to optimize the therapeutic potential of stem cell-based interventions and safety profiles. Phase 1 and large animal studies might provide the groundwork for future randomized trials. Outcome measures should include all-cause mortality, major neurodevelopmental disability and immune rejection, and any other serious adverse events.

Validating the early phototherapy prediction tool across cohorts.

Background: Hyperbilirubinemia of the newborn infant is a common disease worldwide. However, recognized early and treated appropriately, it typically remains innocuous. We recently developed an early phototherapy prediction tool (EPPT) by means of machine learning (ML) utilizing just one bilirubin measurement and few clinical variables. The aim of this study is to test applicability and performance of the EPPT on a new patient cohort from a different population. Materials and methods: This work is a retrospective study of prospectively recorded neonatal data from infants born in 2018 in an academic hospital, Regensburg, Germany, meeting the following inclusion criteria: born with 34 completed weeks of gestation or more, at least two total serum bilirubin (TSB) measurement prior to phototherapy. First, the original EPPT-an ensemble of a logistic regression and a random forest-was used in its freely accessible version and evaluated in terms of the area under the receiver operating characteristic curve (AUROC). Second, a new version of the EPPT model was re-trained on the data from the new cohort. Third, the predictive performance, variable importance, sensitivity and specificity were analyzed and compared across the original and re-trained models. Results: In total, 1,109 neonates were included with a median (IQR) gestational age of 38.4 (36.6-39.9) and a total of 3,940 bilirubin measurements prior to any phototherapy treatment, which was required in 154 neonates (13.9%). For the phototherapy treatment prediction, the original EPPT achieved a predictive performance of 84.6% AUROC on the new cohort. After re-training the model on a subset of the new dataset, 88.8% AUROC was achieved as evaluated by cross validation. The same five variables as for the original model were found to be most important for the prediction on the new cohort, namely gestational age at birth, birth weight, bilirubin to weight ratio, hours since birth, bilirubin value. Discussion: The individual risk for treatment requirement in neonatal hyperbilirubinemia is robustly predictable in different patient cohorts with a previously developed ML tool (EPPT) demanding just one TSB value and only four clinical parameters. Further prospective validation studies are needed to develop an effective and safe clinical decision support system.

Prediction of semen quality using artificial neural network.

Examination of semen characteristics is routinely performed for fertility status investigation of the male partner of an infertile couple as well as for evaluation of the sperm donor candidate. A useful tool for preliminary assessment of semen characteristics might be an artificial neural network. Thus, the aim of the present study was to construct an artificial neural network, which could be used for predicting the result of semen analysis based on the basic questionnaire data. On the basis of eleven survey questions two models of artificial neural networks to predict semen parameters were developed. The first model aims to predict the overall performance and profile of semen. The second network was developed to predict the concentration of sperm. The network to evaluate sperm concentration proved to be the most efficient. 92.93% of the patients in the learning process were properly qualified for the group with a correct or incorrect result, while the result for the test set was 85.71%. This study suggests that an artificial neural network based on eleven survey questions might be a valuable tool for preliminary evaluation and prediction of the semen profile.

Does consumption of red grapefruit juice alter naringenin concentrations in milk produced by breastfeeding mothers?

The content of certain ingredients of human milk, such as flavonoids, depend on the types and amounts of plant products consumed and may vary from woman to woman. The aim of the study was to determine to what extent consumption of an average amount of grapefruit juice (250 ml) affected naringenin content in human milk. A total of 14 breastfeeding mothers were included in the study. The subjects remained on a diet with restricted intake of naringenin for a total of five days except on the third day, when they drank a single serving of 250 ml of grapefruit juice. A considerable subject-to-subject variability in naringenin content was observed in both initial and subsequent determinations. Baseline concentration values, which may reflect naringenin content in the milk produced by the breastfeeding mother who eat an everyday (unmodified) diet, ranged from 420.86 nmol/l to 1568.89 nmol/l, with a mean of 823.24 nmol/l. Switching to the modified diet resulted in a decrease in naringenin concentrations to the mean value of 673.89 nmol/l measured 48 hours after the switch. The highest mean values were observed four and 12 hours after consumption of the juice, equalling 908.25 nmol/l (SD ± 676.84 nmol/l) and 868.96 nmol/l (SD ± 665.54 nmol/l), respectively. Naringenin is commonly found in human milk in quantities expressed in nmol/l, and its concentrations vary from woman to woman. Consumption of 250 ml of red grapefruit juice by breastfeeding mothers does not significantly alter naringenin concentrations in their milk.

Isoflavone production in Cyclopia subternata Vogel (honeybush) suspension cultures grown in shake flasks and stirred-tank bioreactor.

Suspension cultures of the endemic South-African plant Cyclopia subternata were established for the first time and evaluated for the presence of isoflavones. The influence of light, as well as medium supplementation strategies with phenylalanine, casein hydrolysate and coconut water on biomass growth and isoflavone production were examined. The highest levels of 7-O-ß-glucosides of calycosin, pseudobaptigenin and formononetin (275.57, 125.37 and 147.28 mg/100 g DW, respectively) were recorded for cultures grown in the absence of light, whereas coconut water substantially promoted biomass growth. Cell suspensions were subsequently grown in the 2-l stirred-tank bioreactor. Maximum productivity of 7-O-ß-glucosides of calycosin, pseudobaptigenin and formononetin (0.96, 0.44 and 0.22 mg l(-1) day(-1), respectively) in bioreactor-cultivated cells was obtained for biomass grown in the dark and supplemented with coconut water. The results indicate that C. subternata suspension cultures can be utilised for the production of the specified isoflavone derivatives absent in the intact plant.