Search Results (17)

To support bearing capacity estimates, this study develops and tests a geoprocessing workflow for predicting soil properties using Empirical Bayesian Kriging 3D and a classification function. The model covers a 183 m × 185 m × 24 m site in Astana (Kazakhstan), based on 16 boreholes (15–24 m deep) and 77 samples. Eight geotechnical properties were mapped in 3D voxel models (812,520 voxels at 1 m × 1 m × 1 m resolution): cohesion (c), friction angle (φ), deformation modulus (E), plasticity index (PI), liquidity index (LI), porosity (e), particle size (PS), and particle size distribution (PSD). Stratification patterns were revealed with ~35% variability. Maximum φ (34.9°), E (36.6 MPa), and PS (1.29 mm) occurred at 8–16 m; c (33.1 kPa) and PSD peaked below 16 m, while PI and e were elevated in the upper and lower strata. Strong correlations emerged in pairs φ-E-PS (0.91) and PI-e (0.95). Classification identified 10 soil types, including one absent in borehole data, indicating the workflow’s capacity to detect hidden lithologies. Predicted fractions of loams (51.99%), sandy loams (22.24%), and sands (25.77%) matched borehole data (52%, 26%, 22%). Adjacency analysis of 2,394,873 voxel pairs showed homogeneous zones in gravel–sandy soils (28%) and stiff loams (21.75%). The workflow accounts for lateral and vertical heterogeneity, reduces subjectivity, and is recommended for digital subsurface 3D mapping and construction design optimization. Full article

Background: Classification trees (CTs) are widely used machine learning algorithms with growing applications in clinical research, especially for risk stratification. Their ability to generate interpretable decision rules makes them attractive to healthcare professionals. This review provides an accessible yet rigorous overview of CT methodology for clinicians, highlighting their utility through a case study addressing the “obesity paradox” in critically ill patients. Methods: We describe key methodological aspects of CTs, including model development, pruning, validation, and classification types (simple, ensemble, and hybrid). Using data from the ENPIC (Evaluation of Practical Nutrition Practices in the Critical Care Patient) study, which assessed artificial nutrition in ICU (intensive care unit) patients, we applied various CT approaches—CART (classification and regression trees), CHAID (chi-square automatic interaction detection), and XGBoost (extreme gradient boosting)—and compared them with logistic regression. SHAP (SHapley Additive exPlanation) values were used to interpret ensemble models. Results: CTs allowed for identification of optimal cut-off points in continuous variables and revealed complex, non-linear interactions among predictors. Although the obesity paradox was not confirmed in the full cohort, CTs uncovered a specific subgroup in which obesity was associated with reduced mortality. The ensemble model (XGBoost) achieved the best predictive performance (highest area under the ROC curve), though at the expense of interpretability. Conclusions: CTs are valuable tools in clinical epidemiology, complementing traditional models by uncovering hidden patterns and enhancing risk stratification. While ensemble models offer superior predictive accuracy, their complexity necessitates interpretability techniques such as SHAP. CT-based approaches can guide personalized medicine but require cautious interpretation and external validation. Full article

Due to the high variability in Hematoxylin and Eosin (H&E)-stained Whole Slide Images (WSIs), hidden stratification, and batch effects, generalizing beyond the training distribution is one of the main challenges in Deep Learning (DL) for Computational Pathology (CPath). But although DL depends on large volumes of diverse and annotated data, it is common to have a significant number of annotated samples from one or multiple source distributions, and another partially annotated or unlabeled dataset representing a target distribution for which we want to generalize, the so-called Domain Adaptation (DA). In this work, we focus on the task of generalizing from a single source distribution to a target domain. As it is still not clear which domain adaptation strategy is best suited for CPath, we evaluate three different DA strategies, namely FixMatch, CycleGAN, and a self-supervised feature extractor, and show that DA is still a challenge in CPath. Full article

Integrating Artificial Intelligence (AI) into Precision Medicine (PM) is redefining healthcare, enabling personalized treatments tailored to individual patients based on their genetic code, environment, and lifestyle. AI’s ability to analyze vast and complex datasets, including genomics and medical records, facilitates the identification of hidden patterns and correlations, which are critical for developing personalized treatment plans. Unsupervised Learning (UL) is particularly valuable in PM as it can analyze unstructured and unlabeled data to uncover novel disease subtypes, biomarkers, and patient stratifications. By revealing patterns that are not explicitly labeled, unsupervised algorithms enable the discovery of new insights into disease mechanisms and patient variability, advancing our understanding of individual responses to treatment. However, the integration of AI into PM presents some challenges, including concerns about data privacy and the rigorous validation of AI models in clinical practice. Despite these challenges, AI holds immense potential to revolutionize PM, offering a more personalized, efficient, and effective approach to healthcare. Collaboration among AI developers and clinicians is essential to fully realize this potential and ensure ethical and reliable implementation in medical practice. This review will explore the latest emerging UL technologies in the biomedical field with a particular focus on PM applications and their impact on human health and well-being. Full article

(1) Background: The identification of tumor subtypes is fundamental in precision medicine for accurate diagnoses and personalized therapies. Cancer development is often driven by the accumulation of somatic mutations that can cause alterations in tissue functions and morphologies. In this work, a method based on a deep neural network integrated into a network-based stratification framework (D3NS) is proposed to stratify tumors according to somatic mutations. (2) Methods: This approach leverages the power of deep neural networks to detect hidden information in the data by combining the knowledge contained in a network of gene interactions, as typical of network-based stratification methods. D3NS was applied using real-world data from The Cancer Genome Atlas for bladder, ovarian, and kidney cancers. (3) Results: This technique allows for the identification of tumor subtypes characterized by different survival rates and significant associations with several clinical outcomes (tumor stage, grade or response to therapy). (4) Conclusion: D3NS can provide a base model in cancer research and could be considered as a useful tool for tumor stratification, offering potential support in clinical settings. Full article

Poor diet is the top modifiable mortality risk factor globally, accounting for 11 million deaths annually with half being from diet-linked atherosclerotic cardiovascular disease (ASCVD). Yet, most of the world cannot afford a healthy diet—as the hidden costs of the inadequate global food system total over USD 13 trillion annually—let alone the much more clinically, financially, and ecologically costly and resource-intensive medical interventions required to address the disease progression and acute complications of ASCVD. Yet, AI is increasingly understood as a force multiplying revolutionary technology which may catalyze multi-sector efforts in medicine and public health to better address these significant health challenges. This novel narrative review seeks to provide the first known overview of the state-of-the-art in clinical interventions and public health policies in healthy diets for ASCVD, accelerated by health equity-focused AI. It is written from the first-hand practitioner perspective to provide greater relevance and applicability for health professionals and data scientists. The review summarizes the emerging trends and leading use cases in population health risk stratification and precision public health, AI democratizing clinical diagnosis, digital twins in precision nutrition, and AI-enabled culinary medicine as medical education and treatment. This review may, therefore, help inform and advance the evidence-based foundation for more clinically effective, financially efficient, and societally equitable dietary and nutrition interventions for ASCVD. Full article

Artificial intelligence (AI) is rapidly being applied to the medical field, especially in the cardiovascular domain. AI approaches have demonstrated their applicability in the detection, diagnosis, and management of several cardiovascular diseases, enhancing disease stratification and typing. Cardiomyopathies are a leading cause of heart failure and life-threatening ventricular arrhythmias. Identifying the etiologies is fundamental for the management and diagnostic pathway of these heart muscle diseases, requiring the integration of various data, including personal and family history, clinical examination, electrocardiography, and laboratory investigations, as well as multimodality imaging, making the clinical diagnosis challenging. In this scenario, AI has demonstrated its capability to capture subtle connections from a multitude of multiparametric datasets, enabling the discovery of hidden relationships in data and handling more complex tasks than traditional methods. This review aims to present a comprehensive overview of the main concepts related to AI and its subset. Additionally, we review the existing literature on AI-based models in the differential diagnosis of cardiomyopathy phenotypes, and we finally examine the advantages and limitations of these AI approaches. Full article

This retrospective case-control study evaluated the diagnostic performance of a commercially available chest radiography deep convolutional neural network (DCNN) in identifying the presence and position of central venous catheters, enteric tubes, and endotracheal tubes, in addition to a subgroup analysis of different types of lines/tubes. A held-out test dataset of 2568 studies was sourced from community radiology clinics and hospitals in Australia and the USA, and was then ground-truth labelled for the presence, position, and type of line or tube from the consensus of a thoracic specialist radiologist and an intensive care clinician. DCNN model performance for identifying and assessing the positioning of central venous catheters, enteric tubes, and endotracheal tubes over the entire dataset, as well as within each subgroup, was evaluated. The area under the receiver operating characteristic curve (AUC) was assessed. The DCNN algorithm displayed high performance in detecting the presence of lines and tubes in the test dataset with AUCs > 0.99, and good position classification performance over a subpopulation of ground truth positive cases with AUCs of 0.86–0.91. The subgroup analysis showed that model performance was robust across the various subtypes of lines or tubes, although position classification performance of peripherally inserted central catheters was relatively lower. Our findings indicated that the DCNN algorithm performed well in the detection and position classification of lines and tubes, supporting its use as an assistant for clinicians. Further work is required to evaluate performance in rarer scenarios, as well as in less common subgroups. Full article

Wilms’ tumors are pediatric malignancies that are thought to arise from faulty kidney development. They contain a wide range of poorly differentiated cell states resembling various distorted developmental stages of the fetal kidney, and as a result, differ between patients in a continuous manner that is not well understood. Here, we used three computational approaches to characterize this continuous heterogeneity in high-risk blastemal-type Wilms’ tumors. Using Pareto task inference, we show that the tumors form a triangle-shaped continuum in latent space that is bounded by three tumor archetypes with “stromal”, “blastemal”, and “epithelial” characteristics, which resemble the un-induced mesenchyme, the cap mesenchyme, and early epithelial structures of the fetal kidney. By fitting a generative probabilistic “grade of membership” model, we show that each tumor can be represented as a unique mixture of three hidden “topics” with blastemal, stromal, and epithelial characteristics. Likewise, cellular deconvolution allows us to represent each tumor in the continuum as a unique combination of fetal kidney-like cell states. These results highlight the relationship between Wilms’ tumors and kidney development, and we anticipate that they will pave the way for more quantitative strategies for tumor stratification and classification. Full article

Lake Kislo-Sladkoe is a stratified water body partly isolated from the White Sea. Perennial meromixis in the lake irregularly alternates with mixing events. Taking into account that the protists of Arctic coastal stratified water bodies are understudied, we evaluated for the first time the vertical structure, species richness, and diversity of protists assigned to different taxonomic groups in Lake Kislo-Sladkoe using light, luminescent, and scanning electron microscopy. To test the research hypothesis that a mixing event affects the vertical stratification and species composition of protists in a stratified lake, we compared the protist communities of Lake Kislo-Sladkoe in two extremely different states: strong meromixis vs. full vertical mixing. A total of 97 morphologically distinct phototrophic, heterotrophic, and mixotrophic protists were revealed with the most diverse supertaxa SAR (59), Obazoa (9), and Excavates (14). The hidden diversity of protists (43 species) was a bit less than the active diversity (54 species). A taxonomic list and micrographs of cells for the observed protists are provided. The majority of species revealed are cosmopolitan or widespread in the northern sea waters. The vertical patterns of protist communities were absolutely different in 2018 and 2021. In July 2018, clearly distinct protist communities inhabited different layers of the lake. Bloom of cryptophyte Rhodomonas cf. baltica was detected in chemocline, whereas the maximum density of its grazers was observed in adjacent layers, mainly dinoflagellates Gymnodinium sp. and Scrippsiella trochoidea, as well as a ciliate Prorodon sp. In 2021 due to the recent mixing of lake and seawater, there were no distinct communities in the water column except the superficial 0–1 m layer of fresh water. Full article

The use of high-throughput omics technologies is becoming increasingly popular in all facets of biomedical science. The mRNA sequencing (RNA-seq) method reports quantitative measures of more than tens of thousands of biological features. It provides a more comprehensive molecular perspective of studied cancer mechanisms compared to traditional approaches. Graph-based learning models have been proposed to learn important hidden representations from gene expression data and network structure to improve cancer outcome prediction, patient stratification, and cell clustering. However, these graph-based methods cannot rank the importance of the different neighbors for a particular sample in the downstream cancer subtype analyses. In this study, we introduce omicsGAT, a graph attention network (GAT) model to integrate graph-based learning with an attention mechanism for RNA-seq data analysis. The multi-head attention mechanism in omicsGAT can more effectively secure information of a particular sample by assigning different attention coefficients to its neighbors. Comprehensive experiments on The Cancer Genome Atlas (TCGA) breast cancer and bladder cancer bulk RNA-seq data and two single-cell RNA-seq datasets validate that (1) the proposed model can effectively integrate neighborhood information of a sample and learn an embedding vector to improve disease phenotype prediction, cancer patient stratification, and cell clustering of the sample and (2) the attention matrix generated from the multi-head attention coefficients provides more useful information compared to the sample correlation-based adjacency matrix. From the results, we can conclude that some neighbors play a more important role than others in cancer subtype analyses of a particular sample based on the attention coefficient. Full article

Pediatric tuberculosis is a serious infectious disease and a hidden global epidemic. The objective of this study was to describe the epidemiological situation of tuberculosis mortality in children under 15 years of age in Colombia in the period 2010–2018. A longitudinal descriptive study was conducted. The variables sex, age groups, and origin were studied. This study had 260 cases for analysis and was carried out in three phases. The first phase was the determination of the sociodemographic and clinical characteristics. The second phase was the construction of indicators by territorial entities. The third phase was stratification into four epidemiological situations according to the mortality rate and years of life lost. The median age was 7 years (range 0–14), 66.5% of cases were pulmonary tuberculosis (97.7% without bacteriological confirmation), 14.3781 years of life lost were recorded (95% CI: 142.811–168.333), and in children under 10–14 years, the loss was 110,057. Amazonas had the highest adjusted YLL rate (3979.7). In total, 36.4% of the territories had a high mortality, and 30.3% adjusted to the situation designated as 1. This is the first study that has used composite indicators to address the problem of premature mortality from childhood tuberculosis in Colombia. Our results allow us to specify that this disease remains a challenge for public health. It requires models of care and differential strategies by region. It also requires ensuring opportunities in diagnosis with sensitive methods, as well as intersectoral work for the optimal approach. Full article

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization. Full article

Detailed mineralogical analyses in areas with surface hydrothermal alteration zones associated with recent volcanism (<1 Ma) in the Central Andean Volcanic Zone could provide key information to unravel the presence of hidden geothermal systems. In the Cordón de Inacaliri Volcanic Complex, a geothermal field with an estimated potential of ~1.08 MWe·km⁻² has been recently discovered. In this work, we focus on the hydrothermal alteration zones and discharge products of this area, with the aim to reconstruct the geological processes responsible for the space-time evolution leading to the geothermal records. We identified (1) discharge products associated with acid fluids that could be related to: (i) acid-sulfate alteration with alunite + kaolinite + opal CT + anatase, indicating the presence of a steam-heated blanket with massive fine-grained silica (opal-CT), likely accumulated in mud pots where the intersection of the paleowater table with the surface occurred; (ii) argillic alteration with kaolinite + hematite + halloysite + smectite + I/S + illite in the surrounding of the acid-sulfate alteration; and (2) discharge products associated with neutral-alkaline fluids such as: (i) discontinuous pinnacle-like silica and silica deposits with laterally developed coarse stratification which, together with remaining microorganisms, emphasize a sinter deposit associated with alkaline/freshwater/brackish alkaline-chlorine water bodies and laterally associated with (ii) calcite + aragonite deriving from bicarbonate waters. The scarce presence of relics of sinter deposits, with high degree crystallinity phases and diatom remnants, in addition to alunite + kaolinite + opal CT + anatase assemblages, is consistent with a superimposition of a steam-heated environment to a previous sinter deposit. These characters are also a distinguishing feature of paleosurface deposits associated with the geothermal system of the Cordón de Inacaliri Volcanic Complex. The presence of diatoms in heated freshwater bodies at 5100 m a.s.l. in the Atacama Desert environment could be related with the last documented deglaciation in the area (~20–10 ka), an important factor in the recharge of the hidden geothermal systems of the Pabelloncito graben. Full article

Studies of the spatial distribution and size of modern planktonic foraminifera are still lacking in the Mediterranean Sea. In this study, 17 core-top sediments collected from a north-south transect along the central Mediterranean have been analyzed for planktonic foraminiferal content, in terms of their distributional pattern and intraspecific size variability. Among the analyzed planktonic foraminiferal species, Globigerina bulloides and Globigerinoides ruber (w) were the most abundant, presenting an antagonistic behavior and an overall decreasing trend in their average size values from Adriatic to Ionian sub-basins. Intraspecific differences have been also documented for G. ruber (w), with the dominant sensu stricto morphotype to present generally higher frequencies and more constant shell sizes than sensu lato. The greater size variability of the latter is possibly related to its adaptation in particular hydrographic conditions based on its depth habitat preference and ecological characteristics to reach the (sub)optimum growth conditions. The rest of the species occur in minor percentages and show on average 11% increase with decreasing latitude characterized by distinct species-specific size variations along the transect. Our results show that the relationship between planktonic foraminifera shell size and abundance or sea surface temperature are either absent or weaker than previously reported for other regions and that in central Mediterranean assemblages’ size may be mainly related to nutrient availability. Besides the environmental parameters (sea surface temperature, primary productivity, water depth, stratification), the possible hidden cryptic diversity, still lingers to be consistently determined, could give a better understanding of the geographic and morphological differentiation within the Mediterranean planktonic populations. Full article