Forest Classifier Research Articles

Creating Sustainable Flood Maps Using Machine Learning and Free Remote Sensing Data in Unmapped Areas

This study leverages a Random Forest model to predict flood hazard in Arizona, New Mexico, Colorado, and Utah, focusing on enhancing sustainability in flood management. Utilizing the National Flood Hazard Layer (NFHL), an intricate flood map of Arizona was generated, with the Random Forest Classification algorithm assessing flood hazard for each grid cell. Weather variable predictions from TerraClimate were integrated with NFHL classifications and Digital Elevation Model (DEM) analyses, providing a comprehensive understanding of flood dynamics. The research highlights the model’s capability to predict flood hazard in areas lacking NFHL classifications, thereby supporting sustainable flood management by elucidating weather’s influence on flood hazard. This approach aligns with sustainable development goals by aiding in resilient infrastructure design and informed urban planning, reducing the impact of floods on communities. Despite recognizing constraints such as input data precision and the model’s potential limitations in capturing complex variable interactions, the methodology offers a robust framework for flood hazard evaluation in other regions. Integrating diverse data sources, this study presents a valuable tool for decision-makers, supporting sustainable practices, and enhancing the resilience of vulnerable regions against flood hazards. This integrated approach underscores the potential of advanced modeling techniques in promoting sustainability in environmental hazard management.

Development of an accelerometer-based wearable sensor approach for alcohol consumption detection.

Alcohol is a commonly used substance associated with significant public health consequences. Treatment is often stigmatized and limited with regard to both access and affordability, demonstrating the need for innovations in alcohol treatment. Accelerometer sensors can detect drinking without user input and are widely incorporated into wearable devices, increasing accessibility and affordability. We compared a distributional and random forest classification approach to detect and evaluate sensor-based drinking data. Data were collected at a local state fair (n = 194), where participants drank water at specified intervals interspersed with confounding behaviors (e.g., touching nose, rubbing forehead, or yawning) while wearing an Android-based smartwatch for 10 min. Participants were randomized to receive one of three drinking container shapes: pint, martini, or wine. The random forest model achieved an overall testing accuracy of 93% (sensitivity = 0.32; specificity = 0.99; positive predictive value = 0.74). The distributional algorithm achieved an overall accuracy of 95% (sensitivity = 0.76; specificity = 0.97; positive predictive value = 0.72). The distributional algorithm had a significantly greater accuracy (t(193) = 7.73, p < 0.001, d = 0.56) and sensitivity (t(193) = 24.5, p < 0.001, d = 1.76). Equivalency testing demonstrated significant equivalency to the ground truth for sip duration (tlower(193) = 16.92, p < 0.001; tupper(193) = -9.85, p < 0.001) and between-sip interval (tlower(193) = 1.72, p = 0.044; thigher(193) = -3.96, p < 0.001). However, the random forest did not have significant equivalency to the ground truth for between-sip interval (tlower(193) = 1.98, p = 0.025; thigher(193) = 0.160, p = 0.564). Overall, the results indicated that consumer-grade smartwatches can be utilized to detect and measure alcohol use behavior using machine learning and distributional algorithms. This work provides the methodological foundation for future research to analyze the behavioral pharmacology of alcohol use and develop accessible just-in-time clinical interventions.

Intergovernmental Panel on Climate Change (IPCC) Tier 1 forest biomass estimates from Earth Observation

Aboveground biomass density (AGBD) estimates from Earth Observation (EO) can be presented with the consistency standards mandated by United Nations Framework Convention on Climate Change (UNFCCC). This article delivers AGBD estimates, in the format of Intergovernmental Panel on Climate Change (IPCC) Tier 1 values for natural forests, sourced from National Aeronautics and Space Administration’s (NASA’s) Global Ecosystem Dynamics Investigation (GEDI) and Ice, Cloud and land Elevation Satellite (ICESat-2), and European Space Agency’s (ESA’s) Climate Change Initiative (CCI). It also provides the underlying classification used by the IPCC as geospatial layers, delineating global forests by ecozones, continents and status (primary, young (≤20 years) and old secondary (>20 years)). The approaches leverage complementary strengths of various EO-derived datasets that are compiled in an open-science framework through the Multi-mission Algorithm and Analysis Platform (MAAP). This transparency and flexibility enables the adoption of any new incoming datasets in the framework in the future. The EO-based AGBD estimates are expected to be an independent contribution to the IPCC Emission Factors Database in support of UNFCCC processes, and the forest classification expected to support the generation of other policy-relevant datasets while reflecting ongoing shifts in global forests with climate change.

Machine Learning Applications in Stock Price Prediction

With economic fluctuations, investors focus on the stock market where scientific investment strategies become increasingly crucial. This article utilizes linear regression to predict stock price trends, achieving an R value close to 1, indicating high accuracy in the model's predictions. Additionally, logistic regression and random forest classification models were employed to predict stock price movements, revealing a superior performance with the random forest model achieving an AUC value of 0.64. By employing a combination of regression and classification algorithms, this study offers a diverse perspective on stock price prediction, highlighting the importance of scientific forecasting in financial markets. The findings demonstrate that integrating multiple predictive models enhances the accuracy and reliability of stock price predictions, providing investors with precise market information to facilitate rational investment decisions. Furthermore, this research contributes valuable insights for future studies in stock market prediction, promoting continuous innovation and development in the theoretical and methodological aspects of this field. The results underscore the potential of advanced machine learning techniques in financial forecasting, offering a robust framework for understanding market dynamics and improving investment strategies. This study serves as a reference point for both academic research and practical applications, driving forward the evolution of predictive modeling in finance.

Preparation of Dysprosium(III)-Metal Organic Framework Nanofiber for Exosome Capture and Biomarker Discovery toward Liver Disease.

As an emerging source for liquid biopsy, exosomes hold significant promise for clinical diagnosis. However, commonly used exosome isolation methods (e.g., ultracentrifugation) suffer from low throughput for a large number of clinical samples. Herein, a dysprosium-metal organic framework was synthesized and doped with nanofibers by electrospinning for efficient capture of exosomes from body fluid. With the integration of multichannel of pipet or robot automatic workstation, high throughput exosome isolation can be achieved with clinical samples with high reproducibility. To evaluate the clinical value of the developed method, urinary exosomes were enriched from 34 liver disease samples of different stages for the profiling of metabolites by mass spectrometry. The results showed that HCC, cirrhosis, and healthy controls can be significantly differentiated by the Random Forest classification model. The dysprosium-metal organic framework has promising applications in exosome-based liquid biopsy for large-scale clinical disease diagnosis.

Land Cover Mapping in East China for Enhancing High-Resolution Weather Simulation Models

This study was designed to develop a 30 m resolution land cover dataset to improve the performance of regional weather forecasting models in East China. A 10-class land cover mapping scheme was established, reflecting East China’s diverse landscape characteristics and incorporating a new category for plastic greenhouses. Plastic greenhouses are key to understanding surface heterogeneity in agricultural regions, as they can significantly impact local climate conditions, such as heat flux and evapotranspiration, yet they are often not represented in conventional land cover classifications. This is mainly due to the lack of high-resolution datasets capable of detecting these small yet impactful features. For the six-province study area, we selected and processed Landsat 8 imagery from 2015–2018, filtering for cloud cover. Complementary datasets, such as digital elevation models (DEM) and nighttime lighting data, were integrated to enrich the inputs for the Random Forest classification. A comprehensive training dataset was compiled to support Random Forest training and classification accuracy. We developed an automated workflow to manage the data processing, including satellite image selection, preprocessing, classification, and image mosaicking, thereby ensuring the system’s practicality and facilitating future updates. We included three Weather Research and Forecasting (WRF) model experiments in this study to highlight the impact of our land cover maps on daytime and nighttime temperature predictions. The resulting regional land cover dataset achieved an overall accuracy of 83.2% and a Kappa coefficient of 0.81. These accuracy statistics are higher than existing national and global datasets. The model results suggest that the newly developed land cover, combined with a mosaic option in the Unified Noah scheme in WRF, provided the best overall performance for both daytime and nighttime temperature predictions. In addition to supporting the WRF model, our land cover map products, with a planned 3–5-year update schedule, could serve as a valuable data source for ecological assessments in the East China region, informing environmental policy and promoting sustainability.

Machine learning-assisted amidase-catalytic enantioselectivity prediction and rational design of variants for improving enantioselectivity

Biocatalysis is an attractive approach for the synthesis of chiral pharmaceuticals and fine chemicals, but assessing and/or improving the enantioselectivity of biocatalyst towards target substrates is often time and resource intensive. Although machine learning has been used to reveal the underlying relationship between protein sequences and biocatalytic enantioselectivity, the establishment of substrate fitness space is usually disregarded by chemists and is still a challenge. Using 240 datasets collected in our previous works, we adopt chemistry and geometry descriptors and build random forest classification models for predicting the enantioselectivity of amidase towards new substrates. We further propose a heuristic strategy based on these models, by which the rational protein engineering can be efficiently performed to synthesize chiral compounds with higher ee values, and the optimized variant results in a 53-fold higher E-value comparing to the wild-type amidase. This data-driven methodology is expected to broaden the application of machine learning in biocatalysis research.

Seasonal variation of antibiotic resistance genes in activated sludge of a full-scale municipal wastewater treatment plant: Contribution of activated sludge functional taxa and clinically relevant taxa

It has been demonstrated that antibiotic resistance genes (ARGs) exhibit seasonal variations in municipal wastewater treatment plants (MWTPs), but their relationship to bacterial phylogeny structure remains unclear. Using advanced metagenomic techniques and machine learning approach, the current study conducted a year-long investigation to explore the relationship between ARGs and the bacterial community of activated sludge in a full-scale MWTP in Beijing, where seasonal dynamics are remarkable. High abundance of ARGs, notably the clinically relevant high-risk ARGs, was observed in winter and spring, the cold season in Beijing. Seasonal patterns were also observed in the diversity of ARGs and the overall bacterial community. Machine learning-based random forest classification models were utilized to identify biomarkers for ARGs and bacterial genera as indicators of seasonal differences. Subsequent analysis of the relationship between ARGs and bacterial biomarkers was examined using random forest regression models. Results showed that the enrichment of potential pathogens such as Mycobacterium, Clostridium and Pseudomonas was high in winter and spring, strongly contributing to the abundance of high-risk ARGs (ermB, aac(6′)-I, tetM, blaTEM, and mefA) during cold season. Conversely, functional taxa associated with activated sludge, such as Thauera, displayed seasonal fluctuations and a preference for ARGs with minor clinical implications. Metagenomic binning further illustrated the contribution of Mycobacterium to ARG enrichment in cold season. Our findings highlight the collective impact of human-derived clinically relevant taxa and functional bacterial taxa in activated sludge on the seasonal dynamics of ARGs in MWTPs. Additionally, this study offers valuable insights into the safe disposal of the excess sludge from MWTPs.

Research on planting planning of Glycyrrhiza uralensis in Naiman Banner based on MaxEnt model and remote sensing technology

Benefits of Glycyrrhiza uralensis include removing heat, detoxifying, and moistening the lungs, easing coughs, refueling the spleen, and balancing medications. In addition to providing theoretical guidance for the development of the G. uralensis industry and rural revitalization plan, it is anticipated that this paper will also provide basic data for the formulation of production layout of the G. uralensis industry at the county level, the control of cultivation industry direction, the establishment of high-quality G. uralensis cultivation technology system. The Maximum Entropy (MaxEnt) model was used to simulate the potential distribution of G. uralensis, a Chinese medicine resource, in Naiman Banner. By conducting a field inquiry and a broad assessment of the available Chinese medicine resources, the distribution information was acquired. The random forest technique was used to classify G. uralensis. The phenological cycle and development mode of vegetation, which exhibits diverse temporal traits and aids in identification, were elucidated through long-term series analysis. The random forest classification algorithm based on multiple features showed high accuracy in remote sensing (RS) recognition of G. uralensis. Comparative analysis of the MaxEnt and RS results showed that the planting area of G. uralensis was smaller than that of its potential distribution. The expansion to high-suitability areas planting should be prioritized. Based on the dual analysis of regional and remote sensing, it not only proved the great potential of using geographic information to predict the distribution of G. uralensis, but also verified the great potential of extracting the distribution of G. uralensis from GF-6 images. These results will guide the planting and development of G. uralensis in Naiman Banner and a scientific basis for the development of G. uralensis economy, conducive to optimizing the ecological environment and promoting rural revitalization programs.

Remote Sensing Mapping and Analysis of Spatiotemporal Patterns of Land Use and Cover Change in the Helong Region of the Loess Plateau Region (1986–2020)

Land use and cover change (LUCC) is directly linked to the sustainability of ecosystems and the long-term well-being of human society. The Helong Region in the Loess Plateau has become one of the areas most severely affected by soil and water erosion in China due to its unique geographical location and ecological environment. The long-term construction of terraces and orchards is one of the important measures for this region to combat soil erosion. Despite the important role that terraces and orchards play in this region, current studies on their extraction and understanding remain limited. For this reason, this study designed a land use classification system, including terraces and orchards, to reveal the patterns of LUCC and the effectiveness of ecological restoration projects in the area. Based on this system, this study utilized the Random Forest classification algorithm to create an annual land use and cover (LUC) dataset for the Helong Region that covers eight periods from 1986 to 2020, with a spatial resolution of 30 m. The validation results showed that the maps achieved an average overall accuracy of 87.54% and an average Kappa coefficient of 76.94%. This demonstrates the feasibility of the proposed design and land coverage mapping method in the study area. This study found that, from 1986 to 2020, there was a continuous increase in forest and grassland areas, a significant reduction in cropland and bare land areas, and a notable rise in impervious surface areas. We emphasized that the continuous growth of terraces and orchards was an important LUCC trend in the region. This growth was primarily attributed to the conversion of grasslands, croplands, and forests. This transformation not only reduced soil erosion but also enhanced economic efficiency. The products and insights provided in this study help us better understand the complexities of ecological recovery and land management.

Super-resolution cropland mapping with Sentinel-2 images based on a self-training learning network

ABSTRACT The Sentinel-2 image is widely used for cropland mapping, but the limitation of its 10 m spatial resolution may significantly impact the accuracy of result in areas characterized by severe cropland fragmentation. To address the issue, this letter proposes a super-resolution cropland mapping model for Sentinel-2 images. The proposed model improves the spatial resolution of Sentinel-2 images to 2.5 m through self-training learning with the Swin Transformer for Image Restoration (SwinIR) model without needing fine-resolution training samples. Then, the random forest classification is applied to map cropland from the super-solved 2.5 m resolution image. The proposed model was assessed in the Jianghan Plain, China, and the results show that the super-resolution images produce cropland maps with higher accuracy than the original Sentinel-2 images. Comparing cropland mapping results before and after super-resolution, the overall accuracy improves from 0.82 to 0.89, while the commission error and omission error decrease from 0.09 to 0.05 and 0.17 to 0.11, respectively. This method addresses the shortage of training samples collection and improves the accuracy of cropland mapping, contributing to more reliable agricultural remote sensing applications.

Analysis of the Severity of Heterogeneity Protection Forest based on SVM and PCA

Forest heterogeneity indicates the forest condition on producing more carbon into environment. Semidang Bukit Kabu Hunting Park Forest is a nature reserve lies over two districts of Central Bengkulu and Seluma, Bengkulu Province, which should have a heterogeneous forest to protect its natural resources. However, the data showed that the condition of it does not appear to have dense forest heterogeneity anymore, and its rate still remain unknown. Remote sensing as one of tools to help the remote monitoring was believed to be helpful to this question. This study showed changes in the heterogeneity from 2016 to 2021. Sentinel-2 imageries were occupied to help the process of classification of forest and non-forest areas. Support Vector Machine, as one of powerful machine learning tools, was also help the process with the integrating of Principal Component Analysis to optimize forest characteristics. This study indicates that there are significant reductions of forest heterogeneity over the area. The number of forest (heterogeny areas) continues to decline from 8122 ha in 2016 to 4339 ha in 2021. Furthermore, this study had proven that the algorithm of support vector machines showed significant performance to build the model towards the data with overall accuracy rate of 0.9434 and a kappa index of 0.9833.

Mapping dominant tree species of miombo woodlands in Western Tanzania using PlanetScope imagery

Mapping dominant tree species in miombo woodlands is essential for enhancing their monitoring and management. We evaluated PlanetScope imagery to map Julbernardia globiflora, Brachystegia spiciformis, and Pterocarpus tinctorius in Tongwe Forest Reserve, Tanzania. The study assessed the effectiveness of PlanetScope bands in discriminating tree species and investigated how different months/seasons influenced tree species classification. Optimal months (seasons) and spectral bands were selected using Principal Component loading, temporal pattern analysis, mean decrease in accuracy, and mean decrease Gini techniques. Random forest classification was employed for tree species classification, and accuracy was assessed using an error matrix. The study identified March, July, and September as optimal months for acquiring imagery, with effective bands including blue, green-1, green, yellow, red, and red-edge. July and September imagery in the dry season achieved higher overall accuracies of 65% and 69%, respectively, while March imagery in the wet season reached 55%. The highest overall accuracy of 72% was achieved using images from different seasons. Producer’s accuracy was highest for Brachystegia spiciformis (79%) and Julbernardia globiflora (95%), whereas Pterocarpus tinctorius had lower accuracy (25%). User’s accuracy varied with 74% for Brachystegia spiciformis, 70% for Julbernardia globiflora, and 67% for Pterocarpus tinctorius. Mapping accuracy was notably high for Brachystegia spiciformis and Julbernardia globiflora, reflecting their high sample size (dominance) and distinct phenology. The yellow and red bands were particularly effective in distinguishing miombo tree species demonstrating PlanetScope’s capability. Future research should focus on scaling up PlanetScope’s application for broad miombo tree species mapping.

Fatty acids and secondary metabolites can predict grass-finished beef and supplemental cattle feeds

Beef raised using rotational grazing practices on biodiverse pastures offers potential benefits to animal and environmental health and can improve the nutrient density of meat to favor human health. However, many cattle producers contend with the seasonal unavailability of fresh forage, necessitating the utilization of supplementary feeds or indoor feeding. The objective of this study was to profile secondary metabolites and fatty acids in grass-finished beef supplemented with different feeds (4.5 kg/head/day) and to explore the potential for grass-finished beef authentication. In this two-year study, steers (n = 115) were randomly allocated to one of four diets: 1) pastured/supplemented with hay (control group), 2) pastured/supplemented with baleage, 3) pastured/supplemented with soybean hulls, or 4) baleage/soybean hulls in confinement. Secondary metabolites and fatty acids were measured using UHPLC-MS/MS and GC-MS, respectively. Of the 94 measured metabolites, pyridoxine, alpha-tocopherol, hippuric acid, and gallic acid differed between diets (p < 0.05 for all). Based on random forest classification, beef from the pasture/hay, pasture/baleage, pasture/soybean hulls, and confinement baleage/soybean hulls groups could be identified with a predictive accuracy of 100%, 50%, 41%, and 97%, respectively. Although minimal significant differences were observed, our data indicate that certain supplemental feeds maintain favorable nutritional profiles of grass-finished beef. In addition, metabolomics can predict cattle on exclusively forage-based or feed-based diets with a high degree of certainty.

B-122 Improving the Diagnostic Utility of Multiplexed Assays in Laboratory Medicine with Machine Learning

Abstract Background The application of machine learning (ML) and artificial intelligence (AI) in precision medicine is of great interest and continues to grow. ML approaches offer a flexible and data-centric methodology for modeling diagnostic and prognostic trends, capable of identifying complex non-linear patterns and relationships between predictor variables and outcomes within large data sets. Although ML holds great promise, there are several common pitfalls that must be avoided for ML models to provide clinical utility. In the current study, we provide a rigorous and systematic evaluation of the utility of ML algorithms to predict disease in several representative data sets generated via multiplexed biomarker assays. We compare five major classes of ML algorithms compared to more traditional combinatorial analysis (logistic regression) to offer perspective against the current gold standard. Methods We obtained five data sets from published literature that include measurements of multiplexed biomarkers in patients with obstructive sleep apnea, sepsis, and breast and colon cancers in comparison to healthy controls. These datasets were generated by bead-based and planar multiplexed immunoassays. We chose representative ML algorithms from the classes of support vector machines (SVM), random forests (RF), neural networks (NNet), and extreme gradient boosting (xgBoost) in comparison to logistic regression (LR). Datasets were randomly split into internal validation and external validation sets via 10 iterations of permutation analysis. We tuned and validated the models using 5-fold cross validation, then tested those on external subsets. We report the average of several model classification metrics and associated variances across all resampled data sets. Results For the classification of sepsis using inflammatory cytokines measured on the Luminex bead-based immunoassay, RF outperformed LR in external validation sets by a 9.8% increase in AUROC. For classification of breast cancer patients, xgBoost and RF performed best with 20.0% and 16.9% increases in AUROC, respectively, whereas for classification of colon cancer patients, NNet outperformed LR by 11.5%. Across all datasets, on average, all ML algorithms outperformed LR in the internal validation sets by a 7.9% (6.3% - 9.9%) increase in AUROC. However, in external validation sets, only xgBoost and SVM outperformed LR, where RF and NNet showed signs of overfitting. Conclusions Overall, certain ML algorithms show improvement over LR for diagnostic applications using multiplexed assays, by up to 20% increase in AUROC. Interpretation of ML results must be performed rigorously to prevent overly optimistic and unrealistic conclusions. In the context of laboratory medicine, our results showcase the utility of ML in clinical applications, while highlighting potential disadvantages of ML. This analysis underscores the need for establishing rigorous guidelines to support data analytics during the development of novel multiplexed assays, which is needed to advance precision medicine.

A multi-source approach to mapping habitat diversity: Comparison and combination of single-date hyperspectral and multi-date multispectral satellite imagery in a Mediterranean Natural Reserve

The increasing availability of spaceborne hyperspectral satellite imagery opens new opportunities for forest habitat mapping and monitoring, but the limitation of its generally low temporal resolution must be considered. In this study, we compare the ability of single-date PRISMA (PRecursore IperSpettrale della Missione Applicativa), the hyperspectral satellite from the Italian Space Agency, with that of both single-date and multi-date Sentinel-2 (S2) and PlanetScope (PS) to detect and correctly classify various EUNIS habitat types distributed over a relatively small spatial extent (6000 ha) in a natural reserve in Central Italy. The case study deals with multiple levels of spectral similarity, as the dominant canopy species of the target forest habitat classes belong to the same genus (Quercus spp., both deciduous and evergreen species) as well as of different taxa (Pinus and Fraxinus spp.). We performed a pixel-based classification with the Random Forest algorithm using a set of 28 spectral indices computed on PRISMA bands, 22 on S2, and 12 on PS. A Canopy Height Model (CHM) was also used as an input variable for the classification. Our results showed that PRISMA considerably outperforms the two multispectral satellites in single-date classifications, with an overall accuracy of 84 % compared to PlanetScope's 69 % and Sentinel-2's 72 %. Regarding the comparison between multi-date multispectral and single-date hyperspectral, 10-fold cross-validation results revealed that S2 achieves an out-of-bag error rate of approximately 16 %, while PRISMA achieves 17 % and PS 19 %. This demonstrates that a combination of spectral indices calculated during the growing season can capture phenological or physiological differences among the target species, which consequently results in a significant improvement in the classification accuracy of the multispectral sensors. Ultimately, classification results from all three sensors were combined to create probability maps for each forest class, identifying areas classified with a higher degree of certainty by each satellite tested and potentially contributing to forest management by defining areas with varying conservation levels.

Prediction of crystal structure, phase group, and stability of 2D materials through data science coupled with DFT

Two-dimensional materials offer unique mechanical strength, electrical conductivity, and tunable electronic properties, driving advancements in electronics, energy storage, and catalysis. The crystal structure of the materials is fundamental to several properties. In this study, we employ solely the elemental features to construct a random forest classification model achieving an 82.56% accuracy in predicting the crystal structure of the compounds. Additionally, one vs rest binary classifiers are developed for each crystal structure within our 2D materials dataset, with accuracies ranging from 86% to 99%, enhancing their practical utility. Features based on stoichiometric norms have been found to play a major role in the prediction because of the fact that certain crystal structures are associated with more balanced compositions, leading to lower norm values, while others with imbalances have higher norm values. It has also been observed that material compositions with an overall higher amount of p valence electrons tend to show monoclinic, orthorhombic and triclinic crystal structures. Moreover, in compounds with a lower total electronegativity of the constituent elements, the occurrence of trigonal and tetragonal systems has been found to be more probable. In a similar fashion, hexagonal crystal systems have been more often found in compounds where the sum of Van Der Waals radius of the constituent atoms is lower. To validate our model, Crystal structure AnaLYsis by Particle Swarm Optimization (CALYPSO) method, and Density Functional Theory (DFT) are utilized to predict the crystal structure, phase group, and stability of a 2D material.

Machine learning assisted dual-modal SERS detection for circulating tumor cells

Detecting circulating tumor cells (CTCs) from blood has become a promising approach for cancer diagnosis. Surface-enhanced Raman Spectroscopy (SERS) has rapidly developed as a significant detection technology for CTCs, offering high sensitivity and selectivity. Encoded SERS bioprobes have gained attention due to their excellent specificity and ability to identify tumor cells using Raman signals. Machine learning has also made significant contributions to biomedical applications, especially in medical diagnosis. In this study, we developed a detection strategy combining encoded SERS bioprobes and machine learning models to identify CTCs. Dual-modal SERS bioprobes were designed and co-incubated with tumor cells by the “cocktail” method. An identification model for CTCs was constructed using principal component analysis (PCA) and the Random Forest classification algorithm. This innovative strategy endows SERS bioprobes with both effective magnetic separation and highly sensitive identification of CTCs, even at low concentrations of 2 cells/mL. It achieved a high detection rate of 98% for CTCs and effectively eliminated interference from peripheral WBCs. This simple and efficient strategy provides a new approach for CTCs detection and holds important significance for cancer diagnosis.

Sepsis mortality prediction with Machine Learning Tecniques

ObjectiveTo develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU). DesignCross-sectional descriptive study. SettingThe Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database. Patients180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database. Main variables of interestAge, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels. ResultsA random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%. ConclusionsAccording to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.

Fake News Detection with Machine Learning Algorithms

Nowadays, with the advancement of technology, the use of news sources has also undergone a great evolution. News sources have constantly evolved from past to present, ranging from magazines to radios, from newspapers to televisions. The fact that it has become so easy to access news has caused society to pay more attention to fake news. Fake news has the ability to influence society through news sources such as social media, which can reach wider audiences with the development of technology. The difficulties of users in accessing accurate and reliable sources in this information flow that shapes their daily lives increases the potential for the spread of fake news, and it becomes increasingly difficult to distinguish between real and fake news. In this study, classification models for fake news detection were designed using machine learning algorithms. The dataset, which includes fake and real news examples, contains 42,000 examples. Each class, including fake and real samples, contains 22,000 sample data. In order to increase data quality, accuracy and usability, preprocessing methods were applied to the data set. The removal of numbers, stop words, and html tags was done in the pre-processing step to remove unnecessary information from the text. Models were created for fake news detection with singular and ensemble classification algorithms. Performance evaluation of the models was performed using 5-fold cross-validation. In the performance comparisons of the models, values such as accuracy, sensitivity, specificity, tp rate and fp rate were calculated. The highest performance results were observed in the random forest classification algorithm with an accuracy rate of 76%.