Tree Model Research Articles

Harnessing machine learning for predicting mechanical properties of lightweight Mg alloys

In this study, we introduce a machine learning methodology for predicting mechanical properties in Mg-based multicomponent alloys, incorporating alloying elements and processing methods as input variables. We employed eight ML models and assessed their efficacy using metrics such as R2, RMSE, and MAE after using five-fold cross validation grid search hyperparameters tuning process. Following this, we implemented the top-performing Extra Tree (ET), Random Forest (RF) and XGB models to predict mechanical properties for Mg alloys. The best performance was observed with an R2 of 95.1 % and 97.2 %, RMSE of 7 % and 8 %, and MAE of 4.7 % and 5 % for UTS and YS respectively using the Extra Tree model. This research not only showcases the efficiency of ML techniques with minimal intervention but also offers valuable insights paving the way for accelerated design of Mg-alloys for tailored application in the future.

Multiple Machine Learning Models, Molecular Subtyping and Singlecell Analysis Identify PANoptosis-related Core Genes and their Association with Subtypes in Crohn's Disease.

PANoptosis plays an important role in many inflammatory diseases. However, there are no reports on the association between PANoptosis and CD. This study used five machine learning algorithms - least absolute shrinkage and selection operator, support vector machine, random forest, decision tree and Gaussian mixture models - to construct CD's PANoptosis signature. Unsupervised hierarchical clustering analysis was used to identify PANoptosis-associated subgroups of CD. Gene Ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) were conducted to compare the PANoptosis-associated subgroups of CD among the potential biological mechanisms. Single sample GSEA was used to assess immune microenvironmental differences among the subgroups. The potential role of PANoptosis in CD was further explored using single-cell RNA-Seq (scRNA-Seq) for PANoptosis scoring, differential analysis, pseudotime analysis, cellular communication analysis and weighted gene co-expression network analysis (WGCNA) analysis. CD's PANoptosis signature consisted of seven genes: CEACAM6, CHP2, PIK3R1, CASP10, PSMB1, PSMB8 and UBC. The PANoptosis signature in multiple cohorts had a strong ability to recognise CD. The levels of immune cell infiltration and the vigour of the immune responses significantly varied between the two subpopulations of CD associated with PANoptosis. Multiple lines of evidence from the GO, KEGG, GSEA, GSVA, scRNA-Seq and WGCNA analyses suggested that I-kappaB kinase/NF- kappaB signalling, mitogen-activated protein kinase (MAPK), leukocyte activation and leukocyte migration were mechanisms closely associated with PANoptosis in CD. This study is the first to construct a PANoptosis signature with excellent efficacy in recognising CD. PANoptosis may mediate the process of CD through inflammatory and immune mechanisms, such as NF- kappaB, MAPK and leukocyte migration.

Estimating high-resolution snow depth over the North Hemisphere mountains utilizing active microwave backscatter and machine learning

While ground meteorological stations provide accurate snow depth data, their limited spatial coverage results in observational gaps. Satellites offer long-term, large-scale observations, addressing these gaps. Existing snow depth retrieval algorithms mainly use passive microwave remote sensing data with a 25 km resolution, insufficient for capturing snow depth variability in mountainous areas. This paper introduces active microwave backscatter data and machine learning techniques for high-resolution snow depth estimation. We conducted a preliminary exploration of the relationship between Sentinel-1 backscatter coefficient σ0 and snow depth. Due to factors such as vegetation coverage and underlying soil properties, the relationship between σ0 and snow depth is complex and nonlinear. Consequently, six machine learning models were trained to learn this relationship using σ0 and auxiliary data as input features, with in-situ snow depth serving as the target variable. After extensive validation, the Extreme Random Trees (ERT) model was selected for its high accuracy and stability. Using the ERT model, we generated 500 m-resolution snow depth data for northern hemisphere mountains, then analyzed temporal snow depth variations and altitudinal stratification.

Multivariate Decision Tree-Oriented Early Warning Method for College Students’ Psychological Crisis Behavior

To prevent the occurrence of psychological crisis behavior and help college students grow from the crisis is not only an important issue related to college students’ mental health, but also a very necessary and urgent practical issue related to college students’ family happiness, college talent training, and social harmony and stability. Therefore, a multivariable decision tree-oriented early warning method for college students’ psychological crisis behavior is proposed. Using the laser beam emitted by the sensor as a reference standard, the psychological crisis behavior data is extracted, converted into different formats, divided into linear regions, and used to build a multivariate decision tree model. The model is used as the judgment processing target, and the judgment equation of mental health status data is established. The status data is divided into different processing groups as the processing object, calculate the maximum state value of the state data in the two data combinations to obtain the optimal early warning result, and finally realize the early warning of psychological crisis behavior. The experimental results show that the final success rate of early warning obtained by this method is high, which can improve the efficiency of early warning; the number of missing data sets was the least, and most of the subjects’ psychological risk tolerance was at the medium level.

Conceptual Model of Graph-based Individual Tree and Its Utilization in Digital Twin and Metaverse of Urban Forest

Abstract. 3D city models are an important cornerstone in the development of digital twin cities, allowing for various analyses and simulations. CityGML, as an open standard for 3D city models, emphasizes five main aspects: scale or level of detail (LoD), semantics, geometry, topology, and appearance. One of the important elements in CityGML 3D city models is representation of vegetation. Vegetation in CityGML, especially individual trees, is still limited in terms of detail and resolution, reducing its effectiveness for specific applications. This paper proposes a graph-based conceptual model for individual trees that conforms to the CityGML v2.0 specification. The model refers to the morphological structure of a tree consisting of roots, trunk, and crown (including branches, twigs, and leaves), and considers the five main aspects of CityGML. By enhancing semantic information and geometric details, the model aims to provide an information-rich and realistic representation of individual trees in a 3D city environment. The 3D tree model created based on this conceptual model may be applicable in the development of digital twin urban forests and virtual forest simulations that utilize immersive technologies such as the metaverse. This research opens up new opportunities in the development of solitary vegetation objects through CityGML ADE by including more detailed semantic and topological information.

ADVANCEMENTS IN AIRLINE SECURITY: EVALUATING MACHINE LEARNING MODELS FOR THREAT DETECTION

This study assessed the performance of four machine learning algorithms—Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN)—for predicting airline security threats using a dataset of 100,000 entries with 30 features. The models were evaluated based on accuracy, precision, recall, F1-Score, and AUC-ROC. The Neural Network achieved the highest performance, with an accuracy of 88%, precision of 86%, recall of 85%, F1-Score of 85.5%, and AUC-ROC of 0.90, demonstrating superior capability in capturing complex, non-linear patterns. The Random Forest model followed, with an accuracy of 85%, precision of 83%, recall of 82%, F1-Score of 82.5%, and AUC-ROC of 0.87, offering a robust and generalizable solution. The SVM model attained an accuracy of 81%, precision of 80%, recall of 78%, F1-Score of 79%, and AUC-ROC of 0.84, showing effective binary classification but with higher computational costs. The Decision Tree model, while interpretable, had the lowest performance metrics: accuracy of 78%, precision of 76%, recall of 72%, F1-Score of 74%, and AUC-ROC of 0.79. The results indicate that Neural Networks and Random Forests are the most effective models for airline security threat detection, with Neural Networks providing the highest overall accuracy and AUC-ROC.

Enhanced stereodivergent evolution of carboxylesterase for efficient kinetic resolution of near-symmetric esters through machine learning

Carboxylesterases serve as potent biocatalysts in the enantioselective synthesis of chiral carboxylic acids and esters. However, naturally occurring carboxylesterases exhibit limited enantioselectivity, particularly toward ethyl 3-cyclohexene-1-carboxylate (CHCE, S1), due to its nearly symmetric structure. While machine learning effectively expedites directed evolution, the lack of models for predicting the enantioselectivity for carboxylesterases has hindered progress, primarily due to challenges in obtaining high-quality training datasets. In this study, we devise a high-throughput method by coupling alcohol dehydrogenase to determine the apparent enantioselectivity of the carboxylesterase AcEst1 from Acinetobacter sp. JNU9335, generating a high-quality dataset. Leveraging seven features derived from biochemical considerations, we quantitively describe the steric, hydrophobic, hydrophilic, electrostatic, hydrogen bonding, and π-π interaction effects of residues within AcEst1. A robust gradient boosting regression tree model is trained to facilitate stereodivergent evolution, resulting in the enhanced enantioselectivity of AcEst1 toward S1. Through this approach, we successfully obtain two stereocomplementary variants, DR3 and DS6, demonstrating significantly increased and reversed enantioselectivity. Notably, DR3 and DS6 exhibit utility in the enantioselective hydrolysis of various symmetric esters. Comprehensive kinetic parameter analysis, molecular dynamics simulations, and QM/MM calculations offer insights into the kinetic and thermodynamic features underlying the manipulated enantioselectivity of DR3 and DS6.

Estimating Total Rice Biomass and Crop Yield at Field Scale Using PlanetScope Imagery Through Hybrid Machine Learning Models

AbstractNear real-time crop monitoring has been a challenging due to the lack of high-resolution remote sensing images suitable for agricultural applications. The PlanetScope constellation, comprising approximately 130 Dove satellites, collects images of the entire Earth daily, with a resolution of 3.7 m. The high-resolution images from the PlanetScope satellite, along with vegetation indices, geo-environmental data, and soil and crop parameters, were utilized and analysed using machine learning models to enhance the accuracy of predicting total biomass and rice crop yield at the field scale. The study area, covering nearly 214 sample rice plots, was located in the Tarekswar block of Hooghly, West Bengal, India. Alongside ten vegetation indices and three Principal Component Analysis (PCA) soil nutrient levels, approximately thirty-six factors were analyzed to predict rice total biomass and crop yield using ten machine learning (ML) models, namely Random forest (RF), Extreme Gradient Boosting (XGB), Support Vector Machine (SVM), Bagging Tree (Treebag), Generalized Additive Models (gamSpline), Elastic Net (enet), Ordinary regression with LASSO penalty (rqlasso), Tree Models from Genetic Algorithm (evtree), Bayesian Regularized Neutral Networks (brnn), cubist models, and there hybrid of ensembles. Boruta and multi-collinearity analysis were also conducted for the selected factors to explore their influence levels. The study area exhibited robust rice yields ranging from 5 to 10 t/ha, accompanied by healthy biomass growth. Four ML models ─cubist, random forest, enet, and the hybrid model—showed promising predictions with R2 > 0.88. Most models classified less than 20 ha of the study area as falling into the “very-low suitable class”, showing the region’s suitability for rice cultivation due to its highly fertile alluvial soil. Boruta sensitive analysis revealed that nearly 24 individual factors significantly influenced the final crop yield including, organic carbon (OC), phosphorus (P), electrical conductivity (EC), mechanization level, and the majority of the vegetation indices. A critical analysis carried out through the Map query tool showed that five vegetation indices estimated via PlanetScope displayed strong correlations (exceeding 89%) in identifying areas with high to very high rice yields. The study can serve as a guideline for near-real-time crop monitoring in the near future, using high-resolution PlanetScope images.

Kernel-Based Versus Tree-Based Data-Driven Models: On Applying Suspended Sediment Load Estimation

River sediment load estimation poses a critical challenge for water engineers due to its complex and nonlinear hydrological processes. This study assessed the amount of suspended sediment at the Bagh-e-Kalayeh hydrometric station on the Alamut River in the Qazvin province of Iran using two hydrological and meteorological variables, including discharge and rainfall, by considering three scenarios (discharge, discharge + monthly rainfall, and discharge + monthly rainfall + daily rainfall). For modeling, kernel-based data-driven methods, including Gaussian process regression (GPR) and support vector regression (SVR), and tree models, including the M5 tree, random forest (RF), random tree (RT), extra trees, reduced error pruning tree (REPT), and multi-search methods, were used. The results showed that the best performance was achieved by the SVR, with r = 0.948, Wilmot index = 0.965, and RMSE = 0.011 in the first scenario (only discharge). Discharge had the most significant impact on sediment estimation compared to rainfall. It was determined that the suspended sediment load in the Alamut River can be successfully estimated by the SVR method, where only the discharge was used as the input parameter. Additionally, the results indicated that given its characteristics and inherent features, the multi-search method can be used as a complementary approach in sediment modeling, especially in situations where the data volume is not extensive.

Vehicle drivability evaluation based on PCA-SSA-XGBoost

In order to improve the efficiency and quality of vehicle drivability evaluation, a drivability evaluation model based on principal component analysis, extreme gradient boosting tree and sparrow optimization algorithm is proposed. In this paper, the power upshift of DCT vehicle is taken as a typical working condition, and 18 objective evaluation indicators under the power upshift working condition are studied and defined. The objective evaluation indicators are simplified by principal component analysis, their redundancy and blockiness are reduced, and the model input samples are optimized. The extreme gradient boosting tree model is trained to predict the subjective score of drivability, and the sparrow algorithm is used to optimize the core hyperparameters of the extreme gradient boosting tree to improve the accuracy and stability of the model. Road tests show that after the objective evaluation indicators are simplified by principal component analysis, the model evaluation accuracy reaches 97%, which is better than BPNN ( 90%), SVM ( 91%), ELM ( 92%) and SSA-XGBoost ( 95%). It is proved that the accuracy and stability of the proposed PCA-SSA-XGBoost model are better than other models, and it can complete the drivability evaluation more effectively. The evaluation model can be transferred and applied to other driving conditions, and has application value in solving the subjective and objective mapping problem in drivability evaluation.

A sustainable solution for soil improvement: a decision tree model combined with metaheuristic optimizations for fiber reinforced clays

A sustainable solution for soil improvement: a decision tree model combined with metaheuristic optimizations for fiber reinforced clays

Multi-scale modeling of aerosol transport in a mouth-to-truncated bronchial tree system

Computational fluid particle dynamics (CFPD) is widely employed to predict aerosol transport in a truncated bronchial tree model on account of its capacity to reveal details of flow field and particle movement. However, setting a physiologically consistent boundary condition in the CFPD for the idealized or image-based truncated bronchial tree model is still a challenge. This paper proposes a multi-scale modeling method, which contains an Extend-Bronchial tree-Network (EBN) boundary condition for a mouth-to-truncated bronchi system. The comparison between EBN boundary condition and a commonly used uniform pressure (UP) boundary condition is conducted. Subsequently, EBN method is used to study the nano-micron (100 nm–10 μm) particles transport in the mouth-to-truncated bronchi model at different inhalation volume rates (15, 60, 90 L/min). Results show that EBN method is more physiologically rational and two methods differ in flow distribution in lobes, vortex structure, and particle transport. The maximum difference in flow rate distribution in lobes between two methods is about 20 %, while the maximum relative disparity of particle penetration fraction from lobes and deposition fraction in the TLB is about 93 % and 30 %, respectively. Meanwhile, this paper reveals the variation of deposition fraction and penetration fraction with the changes in particle diameter and inhalation volume. Deposition efficiency, deposition hotspots and deposition mechanism are also analyzed with inlet Stokes number (Stk) and Reynolds number (Re). This research establishes a foundation for the simulation of aerosol transport in a whole respiratory tract and provides references for inhalation drug delivery and air pollutant management.

Testing spatial out-of-sample area of influence for grain forecasting models

Abstract We examine the factors that determine if a grain forecasting model fit to one region can be transferred to another region. Prior research has proposed examining the area of applicability (AoA) of a model based on structurally similar characteristics in the Earth Observation predictors and weights based on the model derived feature importance. We expand on and evaluate this approach in the context of grain yield forecasting in Sub-Saharan Africa. Specifically, we evaluate an AoA methodology established for generating raster surfaces and apply it to vector supported grain data. We fit a series of ensemble tree models both within single countries and across multiple sets of countries and then test those models in countries excluded from the training set. We then calculate and decompose AoA measures and examine several different performance metrics. We find that the spatial transfer accuracy does not vary across season but does vary by average rainfall and across high, medium, and low yielding regions. In general, areas with higher yields and medium to high average rainfall tend to have higher accuracy for both model training and transfer. Finally, we find that fitting models with multiple countries provides more accurate out-of-sample estimates when compared to models fitted to a single country.

Devising a Breast Cancer Diagnosis Protocol through Machine Learning

AbstractBreast cancer is a life-threatening disease and has serious health implications. It is categorized based on receptors, including the estrogen receptor (ER) and human epidermal growth factor receptor 2 (HER2), which are the focus of the present research We analyzed gene expression from data obtained from a functional genomics repository called Array Express. The accession numbers are E-GEOD-52194, E-GEOD-75367, and E-GEOD-58135, and the molecular details of these subsets of cancer receptors. Upon following a predefined computational pipeline, we identified 369 genes that had distinct patterns of gene expression profiles in cases of ER-positive (ER + ) and HER2-negative (HER2-) breast cancer. The support vector machine (SVM) and decision tree models of machine learning were used to evaluate the prognostic and diagnostic significance. Accuracy, sensitivity, and specificity were examined to gauge the effectiveness of these models. Then, a network analysis was performed to assess the significant biological process and signaling pathways of HER2- and ER+ breast cancer development. The present study facilitates an enhanced approach to these subcategories of breast cancer so that precise diagnoses can be made, and better and more focused treatment plans can be provided. The current research provides valuable information on the molecular and genetic basis of ER+ and HER2- breast cancer and has great potential for improving patients' treatment.

Cost-effectiveness of Procalcitonin (PCT) guidance for antibiotics management of adult sepsis patients in the Egyptian context

BackgroundSepsis, which is described as a life-threatening organ malfunction brought on by an unbalanced host response to infection, continues to be a significant healthcare issue that affects millions of individuals each year. It is well-known that sepsis can affect anyone around the world, but the employed survey results showed that there are significant regional variations in sepsis incidence as well as mortality rates. Although there are no definite estimates for Egypt, the highest rates were in Low-Middle-Income Countries (LMICs).Procalcitonin (PCT) is a host response marker with high specificity for bacterial infections, unlike C-reactive protein (CRP) or white blood cell count (WBC), which represent the traditional methods of detecting inflammation and infection. Its dynamic profile and superior prognostic prediction make it invaluable for assessing response to antibiotic treatment and improving clinical care for sepsis patients.Our main purpose was to evaluate the cost-effectiveness of PCT guidance compared to no PCT guidance in the antibiotic management of adult sepsis patients according to the Egyptian context.MethodsWe developed a decision tree model to compare the PCT-guided antibiotic management duration endpoint versus the conventional laboratory culture-based antibiotic management in adult sepsis patients. We employed the“Delphi technique” to reach a satisfactory consensus regarding the resources attributed to each compared alternative. The primary measure of the study was the additional cost associated with each Quality-Adjusted Life Year (QALY) gained by sepsis survivors over a one-year time horizon.Base-case, deterministic and probabilistic sensitivity analyses were conducted using TreeAge, Software.ResultsBase-case analysis showed no dominance for either alternative and resulted in an Incremental Cost-Effectiveness Ratio (ICER) value of 297,783.57 Egyptian Pounds per Quality Adjusted Life Year (L.E/QALY) in favor of the PCT guidance alternative, Deterministic sensitivity analysis revealed that the highest impact magnitudes on ICER reside with seven input parameters, the top two parameters that had the most significant influence were the costs of ICU stay with and without PCT guidance. The CEAC showed a slightly higher probability in terms of acceptability in favor of the no PCT guidance choice along the WTP scale till reaching equal probabilities at the willingness-to-pay (WTP) value point of 390,000 (state currency) after which the - probability supports the PCT guidance choice. ConclusionsIn the Egyptian context, PCT guidance has no cost-effectiveness domination over no PCT guidance in Antibiotics management for adult sepsis patients. This may be attributed to the high cost of PCT investigation that shall be resolved by standardization of its cost when applying the approach of DRG cost packages.

Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.

With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the 'golden hour' is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming to optimize their use in clinical practice. We searched Medline, PubMed, Google Scholar, and CENTRAL for studies published from inception to October 2023. We focused on studies predicting sepsis in real-time settings in adult patients in any hospital settings without language limits. The primary outcome was area under the curve (AUC) of the receiver operating characteristic. This meta-analysis was conducted according to PRISMA-NMA guidelines and Cochrane Handbook recommendations. A Network Meta-Analysis using the CINeMA approach compared ML models against traditional scoring systems, with meta-regression identifying factors affecting model quality. From 3,953 studies, 73 articles encompassing 457,932 septic patients and 256 models were analyzed. The pooled AUC for ML models was 0.825 and it significantly outperformed traditional scoring systems. Neural Network and Decision Tree models demonstrated the highest AUC metrics. Significant factors influencing AUC included ML model type, dataset type, and prediction window. This study establishes the superiority of ML models, especially Neural Network and Decision Tree types, in sepsis prediction. It highlights the importance of model type and dataset characteristics for prediction accuracy, emphasizing the necessity for standardized reporting and validation in ML healthcare applications. These findings call for broader clinical implementation to evaluate the effectiveness of these models in diverse patient groups. https://inplasy.com/inplasy-2023-12-0062/, identifier, INPLASY2023120062.

Interpretable Machine Learning: A Case Study on Predicting Fuel Consumption in VLGC Ship Propulsion

The integration of machine learning (ML) in marine engineering has been increasingly subjected to stringent regulatory scrutiny. While environmental regulations aim to reduce harmful emissions and energy consumption, there is also a growing demand for the interpretability of ML models to ensure their reliability and adherence to safety standards. This research highlights the need to develop models that are both transparent and comprehensible to domain experts and regulatory bodies. This paper underscores the importance of transparency in machine learning through a use case involving a VLGC ship two-stroke propulsion engine. By adhering to the CRISP-DM standard, we fostered close collaboration between marine engineers and machine learning experts to circumvent the common pitfalls of automated ML. The methodology included comprehensive data exploration, cleaning, and verification, followed by feature selection and training of linear regression and decision tree models that are not only transparent but also highly interpretable. The linear model achieved an RMSE of 23.16 and an MRAE of 14.7%, while the accuracy of decision trees ranged between 96.4% and 97.69%. This study demonstrates that machine learning models for predicting propulsion engine fuel consumption can be interpretable, adhering to regulatory requirements, while still achieving adequate predictive performance.

Leveraging a decade of Landsat-8 spectral records for mapping blue carbon storage in tidal salt marshes

Tidal salt marsh ecosystems are known to accumulate and store large amounts of “blue” carbon, making them an important component of regional carbon cycle processes and a potential target for ecosystem-based carbon crediting efforts. However, blue carbon content in salt marshes can vary substantially at relatively small spatial scales. Understanding spatial variations of blue carbon storage at the landscape or local scale is important for developing carbon inventories, guiding ecological restorations, and informing habitat management strategies. We investigated the potential of spectral index records from the Landsat-8 Operational Land Imager spanning from 2014 to 2023 for mapping blue carbon storage in the soils of two tidal salt marsh systems in the Mid-Atlantic United States. The decadal mean of a non-photosynthetic vegetation index and standard deviations of a normalized difference vegetation index and a modified normalized difference water index were identified as predictors of blue carbon. These predictors were used to train a gradient boosted trees model for predicting soil organic matter content that achieved a testing set r-squared value of 0.67. We estimated that the two study marshes stored a combined 133–208 Gg of organic carbon in the top 30 cm of soil. We emphasize the need for better quantification of deep soil carbon in tidal salt marsh systems, which is likely quite high, and demonstrate the potential for satellite-based mapping of blue carbon within individual tidal wetland systems.

How did COVID-19 case distribution associate with the urban built environment? A community-level exploration in Shanghai focusing on non-linear relationship.

Several associations between the built environment and COVID-19 case distribution have been identified in previous studies. However, few studies have explored the non-linear associations between the built environment and COVID-19 at the community level. This study employed the March 2022 Shanghai COVID-19 pandemic as a case study to examine the association between built-environment characteristics and the incidence of COVID-19. A non-linear modeling approach, namely the boosted regression tree model, was used to investigate this relationship. A multi-scale study was conducted at the community level based on buffers of 5-minute, 10-minute, and 15-minute walking distances. The main findings are as follows: (1) Relationships between built environment variables and COVID-19 case distribution vary across scales of analysis at the neighborhood level. (2) Significant non-linear associations exist between built-environment characteristics and COVID-19 case distribution at different scales. Population, housing price, normalized difference vegetation index, Shannon's diversity index, number of bus stops, floor-area ratio, and distance from the city center played important roles at different scales. These non-linear results provide a more refined reference for pandemic responses at different scales from an urban planning perspective and offer useful recommendations for a sustainable COVID-19 post-pandemic response.

Chemical composition alterations in rat brain hypothalamus induced by irisin administration using spectroscopic and machine learning techniques

This study employed Fourier transform infrared (FTIR) spectroscopy to determine the chemical composition of brain tissues and the changes induced by irisin at doses of 50 mg and 100 mg. Brain tissues were collected from control rats and those administered with irisin, and key vibrational peaks were analyzed. In the 50 mg irisin group, all described vibrations decreased compared to control tissues, while the 100 mg group showed a decrease only in lipid vibrations. Comparatively, the 50 mg group had lower absorbance of phospholipids, amides, and lipid functional groups than the 100 mg group. Lower amounts of these compounds were found in treated tissues compared to controls, with higher levels in the 100 mg group. Ratios between amide peaks revealed significant differences between groups. Principal component analysis (PCA) differentiated control and irisin-treated tissues, primarily using PC1 and PC3. The decision tree model exhibited high classification accuracy, especially in the 800–1800 cm⁻1 range, with high sensitivity and specificity. FTIR spectroscopy effectively highlighted chemical changes in brain tissues due to irisin, demonstrating dose-dependent variations. The combination of PCA, ROC analysis, and decision tree modeling underscored the potential of FTIR spectroscopy for studying the biochemical effects of compounds like irisin.