Statistical Machine Learning Approaches Research Articles

A Mode Evolution Metric to Extract Reaction Coordinates for Biomolecular Conformational Transitions.

The complex, multidimensional energy landscape of biomolecules makes the extraction of suitable, nonintuitive collective variables (CVs) that describe their conformational transitions challenging. At present, dimensionality reduction approaches and machine learning (ML) schemes are employed to obtain CVs from molecular dynamics (MD)/Monte Carlo (MC) trajectories or structural databanks for biomolecules. However, minimum sampling conditions to generate reliable CVs that accurately describe the underlying energy landscape remain unclear. Here, we address this issue by developing a Mode evolution Metric (MeM) to extract CVs that can pinpoint new states and describe local transitions in the vicinity of a reference minimum from nonequilibrated MD/MC trajectories. We present a general mathematical formulation of MeM for both statistical dimensionality reduction and machine learning approaches. Application of MeM to MC trajectories of model potential energy landscapes and MD trajectories of solvated alanine dipeptide reveals that the principal components which locate new states in the vicinity of a reference minimum emerge well before the trajectories locally equilibrate between the associated states. Finally, we demonstrate a possible application of MeM in designing efficient biased sampling schemes to construct accurate energy landscape slices that link transitions between states. MeM can help speed up the search for new minima around a biomolecular conformational state and enable the accurate estimation of thermodynamics for states lying on the energy landscape and the description of associated transitions.

An initial exploration of machine learning for establishing associations between genetic markers and THC levels in Cannabis sativa samples

Cannabis sativa, a globally commercialized plant used for medicinal, food, fiber production, and recreation, necessitates effective identification to distinguish legal and illegal varieties in forensic contexts. This research utilizes multivariate statistical models and Machine Learning approaches to establish correlations between specific genotypes and tetrahydrocannabinol (Δ9-THC) content (%) in C. sativa samples. 132 cannabis leaves samples were obtained from legal growers in Piedmont, Italy, and illegal drug seizures in Turin. Samples were genetically profiled using a 13-loci STR multiplex and their Δ9-THC content was detected through quantitative GC-MS analysis. This study aims to assess the use of supervised classification modelling on genetic data to distinguish cannabis samples into legal and illegal categories, revealing distinct clusters characterized by unique allele profiles and THC content. t-distributed Stochastic Neighbor Embedding (t-SNE), Random Forest (RF) and Partial Least Squares Regression (PLS-R) were executed for the machine learning modelling. All the tested models resulted effective discriminating between legal samples and illegal. Although further validation is necessary, this study presents a novel forensic investigative approach, potentially aiding law enforcement in significant marijuana seizures or tracking illicit drug trafficking routes.

ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting.

Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This article proposes a novel hybrid hierarchical deep-learning (DL) model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small dataset. A multilayer RNN is equipped with a new type of dilated recurrent cell designed to efficiently model both short and long-term dependencies in TS. To improve the internal TS representation and thus the model's performance, RNN learns simultaneously both the ES parameters and the main mapping function transforming inputs into forecasts. We compare our approach against several baseline methods, including classical statistical methods and machine learning (ML) approaches, on STLF problems for 35 European countries. The empirical study clearly shows that the proposed model has high expressive power to solve nonlinear stochastic forecasting problems with TS including multiple seasonality and significant random fluctuations. In fact, it outperforms both statistical and state-of-the-art ML models in terms of accuracy.

Exploring Selenoprotein P in Liver Cancer: Advanced Statistical Analysis and Machine Learning Approaches.

Selenoprotein P (SELENOP) acts as a crucial mediator, distributing selenium from the liver to other tissues within the body. Despite its established role in selenium metabolism, the specific functions of SELENOP in the development of liver cancer remain enigmatic. This study aims to unravel SELENOP's associations in hepatocellular carcinoma (HCC) by scrutinizing its expression in correlation with disease characteristics and investigating links to hormonal and lipid/triglyceride metabolism biomarkers as well as its potential as a prognosticator for overall survival and predictor of hypoxia. SELENOP mRNA expression was analyzed in 372 HCC patients sourced from The Cancer Genome Atlas (TCGA), utilizing statistical methodologies in R programming and machine learning techniques in Python. SELENOP expression significantly varied across HCC grades (p < 0.000001) and among racial groups (p = 0.0246), with lower levels in higher grades and Asian individuals, respectively. Gender significantly influenced SELENOP expression (p < 0.000001), with females showing lower altered expression compared to males. Notably, the Spearman correlation revealed strong positive connections of SELENOP with hormonal markers (AR, ESR1, THRB) and key lipid/triglyceride metabolism markers (PPARA, APOC3, APOA5). Regarding prognosis, SELENOP showed a significant association with overall survival (p = 0.0142) but explained only a limited proportion of variability (~10%). Machine learning suggested its potential as a predictive biomarker for hypoxia, explaining approximately 18.89% of the variance in hypoxia scores. Future directions include validating SELENOP's prognostic and diagnostic value in serum for personalized HCC treatment. Large-scale prospective studies correlating serum SELENOP levels with patient outcomes are essential, along with integrating them with clinical parameters for enhanced prognostic accuracy and tailored therapeutic strategies.

Statistical mechanic and machine learning approach for competitive adsorption of CO2/CH4 on coals and shales for CO2-enhanced methane recovery

Understanding the adsorption behavior of CO2, CH4, and their mixture on coal at high pressures is necessary to achieve enhanced CH4 recovery and the simultaneous sequestration of CO2. The adsorption of CO2 and CH4 on dry coal is known to exhibit complex behavior as a function of temperature, pressure, and composition. In this study, a model for CO2 adsorption under supercritical conditions was proposed based on a combination of surface adsorption and dissolution in the coal matrix. However, the corresponding CH4 adsorption can only be presented by a surface mechanism. Although the theoretical model provides an idealized description of the heterogeneous nature of coal, it retains the ability to capture the qualitative features of the experimental isotherms. The results indicate reasonable adsorption on the coal surface and dissolution into the coal matrix in the model mechanisms. The model also provides binding energies, surface areas, absolute adsorption isotherms, and isotherms in terms of the fractional occupancy. Considering the complex behavior of mixture adsorption, a machine learning (ML) approach was applied to the adsorption data of various coals. The ML model was reliable for predicting the competitive adsorption of CO2 and CH4 regardless of the coal type (R2 = 0.9950 and 0.9923 for CO2 and CH4, respectively). According to the analytical results obtained from the theoretical model and the ML approach, the volatile matter content, fixed carbon content, and vitrinite reflectance of coal were determined to be important properties for predicting the competitive adsorption of CO2 and CH4 on coal.

Optimization of wear parameters for ECAP-processed ZK30 alloy using response surface and machine learning approaches: a comparative study

The present research applies different statistical analysis and machine learning (ML) approaches to predict and optimize the processing parameters on the wear behavior of ZK30 alloy processed through equal channel angular pressing (ECAP) technique. Firstly, The ECAPed ZK30 billets have been examined at as-annealed (AA), 1-pass, and 4-passes of route Bc (4Bc). Then, the wear output responses in terms of volume loss (VL) and coefficient of friction (COF) have been experimentally investigated by varying load pressure (P) and speed (V) using design of experiments (DOE). In the second step, statistical analysis of variance (ANOVA), 3D response surface plots, and ML have been employed to predict the output responses. Subsequently, genetic algorithm (GA), hybrid DOE–GA, and multi-objective genetic algorithm techniques have been used to optimize the input variables. The experimental results of ECAP process reveal a significant reduction in the average grain size by 92.7% as it processed through 4Bc compared to AA counterpart. Furthermore, 4Bc exhibited a significant improvement in the VL by 99.8% compared to AA counterpart. Both regression and ML prediction models establish a significant correlation between the projected and the actual data, indicating that the experimental and predicted values agreed exceptionally well. The minimal VL at different ECAP passes was obtained at the highest condition of the wear test. Also, the minimal COF for all ECAP passes was obtained at maximum wear load. However, the optimal speed in the wear process decreased with the number of billets passes for minimum COF. The validation of predicted ML models and VL regression under different wear conditions have an accuracy range of 70–99.7%, respectively.

Biomolecular Adsorption on Nanomaterials: Combining Molecular Simulations with Machine Learning.

Adsorption free energies of 32 small biomolecules (amino acids side chains, fragments of lipids, and sugar molecules) on 33 different nanomaterials, computed by the molecular dynamics - metadynamics methodology, have been analyzed using statistical machine learning approaches. Multiple unsupervised learning algorithms (principal component analysis, agglomerative clustering, and K-means) as well as supervised linear and nonlinear regression algorithms (linear regression, AdaBoost ensemble learning, artificial neural network) have been applied. As a result, a small set of biomolecules has been identified, knowledge of adsorption free energies of which to a specific nanomaterial can be used to predict, within the developed machine learning model, adsorption free energies of other biomolecules. Furthermore, the methodology of grouping of nanomaterials according to their interactions with biomolecules has been presented.

Data Mining in Different Fields: A Study

A revolutionary technique for managing massive amounts of data from databases is data mining. These days, information is more commonplace in all types of businesses and industries. For a range of business objectives, fields choose data mining approaches, and data mining is what makes it possible for fields to establish the ideal customer baseline and cultivate long-lasting relationships. Statistical analysis, machine learning, predictive modelling, and database approaches are all combined in knowledge discovery. This review research focuses on and quickly discusses the various domains in which data mining is applied. Here, we discuss several sectors where data mining is relevant in order to comprehend its significance. We also discuss the numerous technologies used in related fields, which depend on user desire. To learn about it, many algorithms are described.

Estimating the natural gas compressibility factor using a statistical correlations and machine learning approaches

Gas compressibility factor plays an critical role in petroleum engineering applications such as gas metering, pipeline design, reserve estimation, gas flow rate, material balance calculations, and many other significant tasks. Therefore, it is crucial to accurately estimate the gas compressibility factor. There have been a lot of studies on calculating the gas compressibility factor from laboratory data, which can be summarized into two main approaches: statistical correlations and machine learning algorithms. In this study, on statistical correlations the authors implement explicit and implicit method while on machine learning algorithms, we use Artificial Neural Network (ANN) and Least-Squares Support Vector Machine (LS-SVM). The data was collected from open literature. Implementing the two approaches mentioned above and comparing statistical parameters such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2 ) found that machine learning algorithms give much more accurate estimation results than statistical correlations, and besides, the ANN algorithm has the most accurate prediction results with the lowest MSE and RMSE (0.000002 and 0.0016) and the highest R2 (0.9999). The high-precision calculation results show that the ANN algorithm mentioned above can be applied to estimate other real gas compressibility factor data sets. On the other hand, this study can be extended to another subset of machine learning algorithms, such as deep learning and ensemble learning.

Software Estimation in the Design Stage with Statistical Models and Machine Learning: An Empirical Study

Accurate estimation of software effort and time in the software development process is a key activity to achieve the necessary product quality. However, underestimation or overestimation of effort has become a key challenge for software development. One of the main problems is the estimation with metrics from late stages, because the product must already be finished to make estimates. In this paper, the use of statistical models and machine learning approaches for software estimation are used in early stages such as software design, and a data set is presented with metric values of design artifacts with 37 software projects. As results, models for the estimation of development time and effort are proposed and validated through leave-one-out cross-validation. Further, machine learning techniques were employed in order to compare software projects estimations. Through the statistical tests, it was proven that the errors were not statistically different with the regression models for effort estimation. However, with Random Forest the best statistical results were obtained for estimating development time.

Enhancing Time Series Anomaly Detection: A Hybrid Model Fusion Approach

Exploring and Identifying Anomalies in time-series data is very crucial in today’s world revolve around data. These data are being used to make important decisions; hence, an efficient and reliable anomaly detection system should be involved in this process to ensure that the best decisions are being made. The paper explores other types of anomalies and proposes efficient detection methods which can be used. Anomalies are patterns that deviate from usual expected behavior. These can come from system failures or unexpected activity. This research paper explores the vulnerabilities of commonly used anomaly detection algorithms such as the Z-Score and static threshold approach. Each method used in this paper has its unique capabilities and limitations. These methods range from using statistical methods and machine learning approaches to detecting anomalies in a time-series dataset. Furthermore, this paper explores other open-source libraries that can be used to detect anomalies, such as Greykite and Prophet Python library. This paper serves as a good source for anyone new to anomaly detection and willing to explore.

Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach

ObjectivesTo predict and identify the key demographic and clinical exposure factors associated with dental anxiety among young adults, and to compare if the traditional statistical modelling approach provides similar results to the machine learning (ML) approach in predicting factors for dental anxiety.MethodsA cross-sectional study of Western Illinois University students. Three survey instruments (sociodemographic questionnaire, modified dental anxiety scale (MDAS), and dental concerns assessment tool (DCA)) were distributed via email to the students using survey monkey. The dependent variable was the mean MDAS scores, while the independent variables were the sociodemographic and dental concern assessment variables. Multivariable analysis was done by comparing the classical statistical model and the machine learning model. The classical statistical modelling technique was conducted using the multiple linear regression analysis and the final model was selected based on Akaike information Criteria (AIC) using the backward stepwise technique while the machine learining modelling was performed by comparing two ML models: LASSO regression and extreme gradient boosting machine (XGBOOST) under 5-fold cross-validation using the resampling technique. All statistical analyses were performed using R version 4.1.3.ResultsThe mean MDAS was 13.73 ± 5.51. After careful consideration of all possible fitted models and their interaction terms the classical statistical approach yielded a parsimonious model with 13 predictor variables with Akaike Information Criteria (AIC) of 2376.4. For the ML approach, the Lasso regression model was the best-performing model with a mean RMSE of 0.617, R2 of 0.615, and MAE of 0.483. Comparing the variable selection of ML versus the classical statistical model, both model types identified 12 similar variables (out of 13) as the most important predictors of dental anxiety in this study population.ConclusionThere is a high burden of dental anxiety within this study population. This study contributes to reducing the knowledge gap about the impact of clinical exposure variables on dental anxiety and the role of machine learningin the prediction of dental anxiety. The predictor variables identified can be used to inform public health interventions that are geared towards eliminating the individual clinical exposure triggers of dental anxiety are recommended.

Assessing the virtual reality perspectives and self-directed learning skills of nursing students: A machine learning-enhanced approach

AimThis study aims to investigate nursing students’ perspectives on virtual reality technologies and their self-directed learning skills, specifically focusing on how these variables interact and influence each other in the context of nursing education. We also discern potential disparities in these skills based on descriptive characteristics, using both traditional statistical and advanced machine learning approaches for a comprehensive analysis. BackgroundRapid developments in technology, particularly during the Covid-19 pandemic, have brought virtual reality technologies to the forefront of nursing education. However, there is a gap in understanding how nursing students’ perceptions of these technological relate to their development of self-directed learning skills. DesignA descriptive and cross-sectional study design is employed to both quantify nursing students’ perspectives on virtual reality in their education and assess their self-directed learning skills. This approach integrates traditional statistical methods with advanced machine learning techniques, with the intention of offering a comprehensive and nuanced analysis to inform future teaching strategies in nursing. MethodsThe study used a blend of survey scales and a tree-based machine learning model to measure and analyze nursing students’ views, attitudes and self-directed learning levels. This dual approach allows for a more detailed assessment of the factors influencing self-directed learning abilities. Traditional statistical techniques were also applied to assess the reliability of the machine learning findings. ResultsFindings reveal that nursing students generally held positive views towards virtual reality technologies and exhibited a high level of self-directed learning skills. Notable differences in self-directed learning skills were influenced by gender on the overall scale (p <0.001), with male students scoring higher than their female counterparts in both specific sub-dimensions and on the overall scale, but not by academic year. The machine learning analysis provided deeper insights into these variations, highlighting subtle distinctions in student demographics that traditional statistical methods did not fully capture. ConclusionsThe study offers valuable insights into interconnected nature of nursing students’ views on virtual reality technologies and their self-directed learning skills. The results support the integration of virtual reality in nursing curriculum programs and underscore the importance of customizing teaching strategies based on insights gained from machine learning analyses. This approach has the potential to substantially improve both the learning experience and the overall quality of nursing education.

DTox: A deep neural network-based in visio lens for large scale toxicogenomics data.

With the advancement of large-scale omics technologies, particularly transcriptomics data sets on drug and treatment response repositories available in public domain, toxicogenomics has emerged as a key field in safety pharmacology and chemical risk assessment. Traditional statistics-based bioinformatics analysis poses challenges in its application across multidimensional toxicogenomic data, including administration time, dosage, and gene expression levels. Motivated by the visual inspection workflow of field experts to augment their efficiency of screening significant genes to derive meaningful insights, together with the ability of deep neural architectures to learn the image signals, we developed DTox, a deep neural network-based in visio approach. Using the Percellome toxicogenomics database, instead of utilizing the numerical gene expression values of the transcripts (gene probes of the microarray) for dose-time combinations, DTox learned the image representation of 3D surface plots of distinct time and dosage data points to train the classifier on the experts' labels of gene probe significance. DTox outperformed statistical threshold-based bioinformatics and machine learning approaches based on numerical expression values. This result shows the ability of image-driven neural networks to overcome the limitations of classical numeric value-based approaches. Further, by augmenting the model with explainability modules, our study showed the potential to reveal the visual analysis process of human experts in toxicogenomics through the model weights. While the current work demonstrates the application of the DTox model in toxicogenomic studies, it can be further generalized as an in visio approach for multi-dimensional numeric data with applications in various fields in medical data sciences.

Impact of Formulation and Slurry Properties on Lithium‐ion Electrode Manufacturing

AbstractThe characteristics and performance of lithium‐ion batteries typically rely on the precise combination of materials in their component electrodes. Understanding the impact of this formulation and the interdependencies between each component is critical in optimising cell performance. Such optimisation is difficult as the cost and effort for the myriad of possible combinations is too high. This problem is addressed by combining a design of experiments (DoE) and advanced statistical machine learning approach with comprehensive experimental characterisation of electrode slurries and coatings. An industry relevant graphite anode system is used, and with the aid of DoE, less than 30 experiments are defined to map impact of different weight fractions of active material (80–96 wt%), conductive additive (Carbon Black at 1–10 wt%) and a two‐component binder system (Carboxymethyl Cellulose (CMC) at 1–3 wt% and Styrene Butadiene Rubber (SBR), at 1–7 wt%). Using Explainable Machine Learning (XML) methods, correlations between the formulation, slurry weight percentage (30–50 wt% in water) and coating speed (1–15 m/min) are quantified. Slurry viscosity, while known to depend on the CMC concentration, is also heavily influenced by carbon black and SBR when at high concentration, as is common in research. Viscosity increasing components also improve adhesion, by improving dispersion and hindering binder migration. Conductivity of the coating on current collector is sensitive to the current collector‐coating interface, which makes it a highly useful probe. Improvements in cell capacity are observed with higher viscosity formulations (High weight percentage, CMC content), attributed to reduction in migration and slumping of the slurry on the current collector. SBR had a negative impact at any concentration due to its insulating nature, and carbon black reduces gravimetric capacity when included at high concentrations. The insights from this study facilitate the formulation optimisation of electrodes providing improved slurry design rules for future high performance electrode manufacturing.

Classification of household poverty in West Java using the generalized mixed-effects trees model

Dealing with fixed effects and random effects can be accomplished by combining statistical modeling and machine learning techniques. This paper discusses the modeling of fixed effects and random effects using a statistical machine-learning approach. We used the generalized mixed-effects trees (GMET), a tree-based mixed-effect model for dealing with response variables that belong to the exponential family of distributions. In this study, both simulation and actual/empirical data utilized the GMET method to discover data conditions that were appropriate for employing this approach. The simulation data was generated using different response variable generations, as well as different values of the variance of random effect and fixed effect coefficients. The findings indicated that the GMET performs similarly for different response variable generation scenarios. However, it performed better when the fixed effect value and the variance of random effects were large. When applied to the empirical data, the GMET method describes fixed effects and random effects and classifies household poverty status quite well based on the area under curve (AUC) value. It has also revealed that important variables for poverty classification are the number of household members, owning land, the type of main fuel used for cooking, and the main source of water used for drinking. In order to address the socioeconomic disparity that leads to poverty, the government may become concerned about these factors. In addition to that information, the use of regional typology as a random effect in the model has also contributed to the variation of household poverty status. Based on research, the fixed effects in mixed models do not need to be linear and GMET may be employed in grouped data structures, giving the GMET technique the ability to compete with other approaches/methods.

Regional variability of terrain index and machine learning model applications for prediction of ephemeral gullies

Terrain, or topographic, index models aggregate morphometric features of a landscape and use them to predict trajectories and initiation points of classical or ephemeral gullies. As an alternative to the index-based models, statistical machine learning approaches have been recently gaining an increased attention for identification of areas of gully susceptibility. Application of index-based or statistical models is normally restricted to the area of study, and regional model transferability is not well understood. In this study, seven terrain index models and two machine learning algorithms were applied to eight watersheds in Kansas and two watersheds in Sicily. The predictive ability of the nine models was measured by using both cut-off independent (area under the receiver operating characteristic curve) and dependent (Cohen's kappa index, sensitivity, specificity) statistics. The performance statistics of both terrain index and statistical models were cross-examined by finding an optimal threshold in one watershed and applying it to other watersheds. In Kansas, the model based on stream order (GORD) was found to perform similar to machine learning approaches, whereas the modified stream power index (MSPI) model overperformed other terrain index models in Sicily. Different landform characteristics in cultivated areas of the High Plains region in Kansas and in the steep hillslopes of Central Sicily caused models to have variable success rate when the indexes from one region were transferred to another region. The results also showed that a well-calibrated terrain index model, especially based on stream grid order, can be viewed as a valid alternative to a data driven approach for ephemeral gully mapping, but transferability of the optimal thresholds can be applied with caution.

Development and internal validation of a prediction model for long-term opioid use-an analysis of insurance claims data.

In the United States, a public-health crisis of opioid overuse has been observed, and in Europe, prescriptions of opioids are strongly increasing over time. The objective was to develop and validate a multivariable prognostic model to be used at the beginning of an opioid prescription episode, aiming to identify individual patients at high risk for long-term opioid use based on routinely collected data. Predictors including demographics, comorbid diseases, comedication, morphine dose at episode initiation, and prescription practice were collected. The primary outcome was long-term opioid use, defined as opioid use of either >90 days duration and ≥10 claims or >120 days, independent of the number of claims. Traditional generalized linear statistical regression models and machine learning approaches were applied. The area under the curve, calibration plots, and the scaled Brier score assessed model performance. More than four hundred thousand opioid episodes were included. The final risk prediction model had an area under the curve of 0.927 (95% confidence interval 0.924-0.931) in the validation set, and this model had a scaled Brier score of 48.5%. Using a threshold of 10% predicted probability to identify patients at high risk, the overall accuracy of this risk prediction model was 81.6% (95% confidence interval 81.2% to 82.0%). Our study demonstrated that long-term opioid use can be predicted at the initiation of an opioid prescription episode, with satisfactory accuracy using data routinely collected at a large health insurance company. Traditional statistical methods resulted in higher discriminative ability and similarly good calibration as compared with machine learning approaches.

Fractal dimension: analyzing its potential as a neuroimaging biomarker for brain tumor diagnosis using machine learning.

Purpose: The main purpose of this study was to comprehensively investigate the potential of fractal dimension (FD) measures in discriminating brain gliomas into low-grade glioma (LGG) and high-grade glioma (HGG) by examining tumor constituents and non-tumorous gray matter (GM) and white matter (WM) regions. Methods: Retrospective magnetic resonance imaging (MRI) data of 42 glioma patients (LGG, n = 27 and HGG, n = 15) were used in this study. Using MRI, we calculated different FD measures based on the general structure, boundary, and skeleton aspects of the tumorous and non-tumorous brain GM and WM regions. Texture features, namely, angular second moment, contrast, inverse difference moment, correlation, and entropy, were also measured in the tumorous and non-tumorous regions. The efficacy of FD features was assessed by comparing them with texture features. Statistical inference and machine learning approaches were used on the aforementioned measures to distinguish LGG and HGG patients. Results: FD measures from tumorous and non-tumorous regions were able to distinguish LGG and HGG patients. Among the 15 different FD measures, the general structure FD values of enhanced tumor regions yielded high accuracy (93%), sensitivity (97%), specificity (98%), and area under the receiver operating characteristic curve (AUC) score (98%). Non-tumorous GM skeleton FD values also yielded good accuracy (83.3%), sensitivity (100%), specificity (60%), and AUC score (80%) in classifying the tumor grades. These measures were also found to be significantly (p < 0.05) different between LGG and HGG patients. On the other hand, among the 25 texture features, enhanced tumor region features, namely, contrast, correlation, and entropy, revealed significant differences between LGG and HGG. In machine learning, the enhanced tumor region texture features yielded high accuracy, sensitivity, specificity, and AUC score. Conclusion: A comparison between texture and FD features revealed that FD analysis on different aspects of the tumorous and non-tumorous components not only distinguished LGG and HGG patients with high statistical significance and classification accuracy but also provided better insights into glioma grade classification. Therefore, FD features can serve as potential neuroimaging biomarkers for glioma.

Specific and label-free endogenous signature of dystrophic muscle by Synchrotron deep ultraviolet radiation

Dystrophic muscle is characterized by necrosis/regeneration cycles, inflammation, and fibro-adipogenic development. Conventional histological stainings provide essential topographical data of this remodeling but may be limited to discriminate closely related pathophysiological contexts. They fail to mention microarchitecture changes linked to the nature and spatial distribution of tissue compartment components. We investigated whether label-free tissue autofluorescence revealed by Synchrotron deep ultraviolet (DUV) radiation could serve as an additional tool for monitoring dystrophic muscle remodeling. Using widefield microscopy with specific emission fluorescence filters and microspectroscopy defined by high spectral resolution, we analyzed samples from healthy dogs and two groups of dystrophic dogs: naïve (severely affected) and MuStem cell-transplanted (clinically stabilized) animals. Multivariate statistical analysis and machine learning approaches demonstrated that autofluorescence emitted at 420–480 nm by the Biceps femoris muscle effectively discriminates between healthy, dystrophic, and transplanted dog samples. Microspectroscopy showed that dystrophic dog muscle displays higher and lower autofluorescence due to collagen cross-linking and NADH respectively than that of healthy and transplanted dogs, defining biomarkers to evaluate the impact of cell transplantation. Our findings demonstrate that DUV radiation is a sensitive, label-free method to assess the histopathological status of dystrophic muscle using small amounts of tissue, with potential applications in regenerative medicine.