Machine learning analysis of drivers of differences in PAH content between PM1 and PM10 in Zagreb, Croatia

Background: Acute Type A Aortic Dissection (ATAD) is a surgical emergency with 18% mortality. Anatomic segment (root, ascending, arch, descending) impacts aneurysm natural history but mechanisms remain unclear. Aim: To compare proteomic profiles of human thoracic aortic segments that could account for distinct phenotypes and clinical outcomes; to analyze the largest cohort to date with enhanced depth of coverage. Methods: Aortic tissues were collected (N=148) from 82 unique individuals and analyzed using our customized proteomics protocol ( Figure 1A ). Conventional statistics, machine learning (t-distributed Stochastic Neighbour Embedding, t-SNE), and functional enrichment analyses were used to characterize significant phenotypic differences by segment. Differential protein expression was validated using immunofluorescence. Results: From all samples, 7251 proteins were identified (5660 quantified), exceeding literature (by 100s-1000s). Significant differences were greatest in comparisons of root, ascending, and descending aorta ( Figure 1B-C ). Root vs descending and ascending vs descending comparisons had clear separation in t-SNE analysis; root and ascending samples also clustered modestly ( Figure 1D ). MFAP4, a cellular-binding protein previously associated with descending thoracic dissection in Marfan patients, was significantly elevated in ascending aortic segments compared to root and descending. This was validated by immunofluorescence ( Figure 1E ). Conclusions: We extensively profiled thoracic aneurysm tissue using enhanced coverage, customized proteomics from the largest known cohort of human samples. Thoracic aneurysm phenotype differs by aortic segment as a function of intrinsic biochemical (proteomic) processes. Potential thoracic aneurysm biomarkers likely must account for aortic segment. Multiomic integrative analysis (DNA, RNA, post-translational data) are underway.

BackgroundThe rising incidence of youth-onset type 2 diabetes mellitus (T2DM), along with the risk of early cardiovascular complications, is concerning. Brachial-ankle pulse wave velocity (baPWV) and carotid intima-media thickness (cIMT) are noninvasive markers of arterial stiffness and atherosclerosis. They serve as important markers for cardiovascular risk assessment. This study aimed to apply machine learning models to identify high-risk individuals who may benefit from early and targeted cardiovascular screening.MethodsThis retrospective study included 129 patients with youth-onset T2DM who underwent baPWV and cIMT measurements between January 2018 and July 2024. High-risk groups were defined as having values of ≥ mean + 1 standard deviation for baPWV (arterial stiffness) and cIMT (atherosclerosis). Clinical predictors were evaluated using linear, logistic regression, and machine learning analyses. Multiple machine learning models were trained using oversampling and cross-validation techniques to enhance prediction performance.ResultsAmong the models tested, the gradient boosting model with adaptive synthetic sampling oversampling achieved the best performance in predicting both arterial stiffness (accuracy 0.81) and atherosclerosis prediction (accuracy 0.92). Age and hypertension were consistently identified as the most important factors for arterial stiffness. For atherosclerosis risk, traditional analysis identified dyslipidemia, male sex, and duration of illness as relevant factors; machine learning more clearly emphasized low-density lipoprotein cholesterol and triglyceride levels as key predictors of increased cIMT.ConclusionHypertension and age were consistent predictors of arterial stiffness, while atherosclerosis risk factors were further clarified with lipid parameters by machine learning analysis. These findings suggest that conventional and machine learning analyses offer complementary strengths. Their combined use may enable earlier to detect nuanced cardiovascular risk patterns and support early and targeted vascular screening in youth-onset T2DM.

Machine learning (ML) has emerged as a transformative force in cardiovascular disease research, offering innovative approaches to prevention, diagnosis, and treatment. This report provides an overview of the current landscape of ML applications in cardiology, highlighting its potential to revolutionize the field. Key ML algorithms such as Support Vector Machine (SVM), Random Forests, Adaboost, XGBoost, and Convolutional Neural Networks (CNN) are discussed for their unique capabilities in handling complex cardiovascular data and improving disease prediction and risk stratification. Notably, the integration of feature selection techniques with ML algorithms enables the identification of biomarkers and clinical indicators, facilitating personalized care and targeted interventions. The potential of ML extends to early disease diagnosis, patient stratification, and the design of new therapeutic strategies, thereby transforming cardiology into a domain of precision medicine. While the advancements are promising, there is a pressing need for further research to enhance the interpretability, generalizability, and integration of ML models into real-world healthcare settings. Collaborative efforts between ML experts, healthcare providers, and policymakers are essential to address regulatory, ethical, and privacy concerns and to fully harness the capabilities of ML in cardiovascular medicine.

In many domains such as Telecom various scenarios necessitate the processing of large amounts of data using statistical and machine learning algorithms. A noticeable effort has been made to move the data management systems into MapReduce parallel processing environments such as Hadoop and Pig. Nevertheless these systems lack the features of advanced machine learning and statistical analysis. Frame-works such as Mahout on top of Hadoop support machine learning but their implementations are at the preliminary stage. For example Mahout does not provide Support Vector Machine (SVM) algorithms and it is difficult to use. On the other hand traditional statistical software tools such as R containing comprehensive statistical algorithms for advanced analysis are widely used. But such software can only run on a single computer and therefore it is not scalable. In this paper we propose an integrated solution RPig which takes the advantages of R (for machine learning and statistical analysis capabilities) and parallel data processing capabilities of Pig. The RPig framework offers a scalable advanced data analysis solution for machine learning and statistical analysis. Analysis jobs can be easily developed with RPig script in high level languages. We describe the design implementation and an eclipse-based RPigEditor for the RPig framework. Using application scenarios from the Telecom domain we show the usage of RPig and how the framework can significantly reduce the development effort. The results demonstrate the scalability of our framework and the simplicity of deployment for analysis jobs.

BackgroundThe aims of this study were to determine the predictive value of decision support analysis for the shock wave lithotripsy (SWL) success rate and to analyze the data obtained from patients who underwent SWL to assess the factors influencing the outcome by using machine learning methods.MethodsWe retrospectively reviewed the medical records of 358 patients who underwent SWL for urinary stone (kidney and upper-ureter stone) between 2015 and 2018 and evaluated the possible prognostic features, including patient population characteristics, urinary stone characteristics on a non-contrast, computed tomographic image. We performed 80% training set and 20% test set for the predictions of success and mainly used decision tree-based machine learning algorithms, such as random forest (RF), extreme gradient boosting trees (XGBoost), and light gradient boosting method (LightGBM).ResultsIn machine learning analysis, the prediction accuracies for stone-free were 86.0, 87.5, and 87.9%, and those for one-session success were 78.0, 77.4, and 77.0% using RF, XGBoost, and LightGBM, respectively. In predictions for stone-free, LightGBM yielded the best accuracy and RF yielded the best one in those for one-session success among those methods. The sensitivity and specificity values for machine learning analytics are (0.74 to 0.78 and 0.92 to 0.93) for stone-free and (0.79 to 0.81 and 0.74 to 0.75) for one-session success, respectively. The area under curve (AUC) values for machine learning analytics are (0.84 to 0.85) for stone-free and (0.77 to 0.78) for one-session success and their 95% confidence intervals (CIs) are (0.730 to 0.933) and (0.673 to 0.866) in average of methods, respectively.ConclusionsWe applied a selected machine learning analysis to predict the result after treatment of SWL for urinary stone. About 88% accurate machine learning based predictive model was evaluated. The importance of machine learning algorithm can give matched insights to domain knowledge on effective and influential factors for SWL success outcomes.

Detection of Longitudinal Visual Field Progression in Glaucoma Using Machine Learning

Hepatocellular carcinoma (HCC) is a common tumor. Although the diagnosis and treatment of HCC have made great progress, the overall prognosis remains poor. As the core component of artificial intelligence, machine learning (ML) has developed rapidly in the past decade. In particular, ML has become widely used in the medical field, and it has helped in the diagnosis and treatment of cancer. Different algorithms of ML have different roles in diagnosis, treatment, and prognosis. This article reviews recent research, explains the application of different ML models in HCC, and provides suggestions for follow-up research.

Food flavor analysis 4.0: A cross-domain application of machine learning

BackgroundApproximately 80% of those infected with COVID-19 are immune. They are asymptomatic unknown carriers who can still infect those with whom they come into contact. Understanding what makes them immune could inform public health policies as to who needs to be protected and why, and possibly lead to a novel treatment for those who cannot, or will not, be vaccinated once a vaccine is available.ObjectiveThe primary objectives of this study were to learn if machine learning could identify patterns in the pathogen-host immune relationship that differentiate or predict COVID-19 symptom immunity and, if so, which ones and at what levels. The secondary objective was to learn if machine learning could take such differentiators to build a model that could predict COVID-19 immunity with clinical accuracy. The tertiary purpose was to learn about the relevance of other immune factors.MethodsThis was a comparative effectiveness research study on 53 common immunological factors using machine learning on clinical data from 74 similarly grouped Chinese COVID-19–positive patients, 37 of whom were symptomatic and 37 asymptomatic. The setting was a single-center primary care hospital in the Wanzhou District of China. Immunological factors were measured in patients who were diagnosed as SARS-CoV-2 positive by reverse transcriptase-polymerase chain reaction (RT-PCR) in the 14 days before observations were recorded. The median age of the 37 asymptomatic patients was 41 years (range 8-75 years); 22 were female, 15 were male. For comparison, 37 RT-PCR test–positive patients were selected and matched to the asymptomatic group by age, comorbidities, and sex. Machine learning models were trained and compared to understand the pathogen-immune relationship and predict who was immune to COVID-19 and why, using the statistical programming language R.ResultsWhen stem cell growth factor-beta (SCGF-β) was included in the machine learning analysis, a decision tree and extreme gradient boosting algorithms classified and predicted COVID-19 symptom immunity with 100% accuracy. When SCGF-β was excluded, a random-forest algorithm classified and predicted asymptomatic and symptomatic cases of COVID-19 with 94.8% AUROC (area under the receiver operating characteristic) curve accuracy (95% CI 90.17%-100%). In total, 34 common immune factors have statistically significant associations with COVID-19 symptoms (all c<.05), and 19 immune factors appear to have no statistically significant association.ConclusionsThe primary outcome was that asymptomatic patients with COVID-19 could be identified by three distinct immunological factors and levels: SCGF-β (>127,637), interleukin-16 (IL-16) (>45), and macrophage colony-stimulating factor (M-CSF) (>57). The secondary study outcome was the suggestion that stem-cell therapy with SCGF-β may be a novel treatment for COVID-19. Individuals with an SCGF-β level >127,637, or an IL-16 level >45 and an M-CSF level >57, appear to be predictively immune to COVID-19 100% and 94.8% (AUROC) of the time, respectively. Testing levels of these three immunological factors may be a valuable tool at the point of care for managing and preventing outbreaks. Further, stem-cell therapy via SCGF-β and M-CSF appear to be promising novel therapeutics for patients with COVID-19.

The objective of this research is to design and implement a performance evaluation system that combines Machine Learning for data processing, predictive modeling, and pattern recognition with the GAP method to measure discrepancies between expected competencies and actual performance. Eight primary criteria were cooperation, communication, initiative, alertness, discipline, leadership, problem solving, time usage each consisting of several sub-criteria. The study involved 18 lecturers, and the evaluation was conducted using a web-based decision support system equipped with machine learning models trained to classify performance levels and identify underlying patterns within the assessment data. System usability was examined through four categories: ease of use, completeness, accuracy, and interface composition. The results show that the integrated system successfully identified the highest-performing lecturer (Lecturer 7) with a score of 6.1801, followed by Lecturer 12 with 4.9314 and Lecturer 4 with 4.1157. Usability testing also yielded positive outcomes, with scores of 89% for ease of use, 87% for completeness, 90% for accuracy enhanced through machine learning validation and 88% for interface composition. These results produced an overall average of 88%, classifying the system as Very Worthy. In conclusion, integrating Machine Learning and GAP Analysis in a web-based DSS significantly improves the effectiveness and efficiency of lecturer performance evaluation. The system accelerates data processing, enhances assessment quality, and strengthens decision-making through predictive analytics and automated classification. This framework offers a valuable reference for future performance evaluations in higher education institutions seeking accountability, transparency, and data-driven decision-making.

Although several machine learning driven solutions are deemed to be effective at detecting data breaches, the recent proliferation in data breach incidents resulting from cyber attacks on computer networks demands an updated, thorough analysis of Machine Learning (ML) based data breach countermeasures to identify research gaps and guide future studies. In view of this, this study employs a systematic approach and draws insight from 89 research articles to classify machine learning based data breach countermeasures using eight criteria namely learning tasks, learning classifiers, datasets, feature engineering methods, multimodal approaches, pre-training approaches and performance. In classifying the studies, we: (a) propose a taxonomy of feature extraction and representation to classify studies using ten sub-criteria, (b) classify multimodal machine learning approaches used in the studies into three fusion sub-criteria: namely early fusion, intermediate fusion and late fusion, (c) show a comparison of studies based on pre-training techniques employed such as pre-text objective, learning model and data used in pre-training, (d) classify the datasets used in the study evaluation into two categories: real dataset and simulated dataset and (e) evaluate studies by detection performance and effectiveness against data breaches on unknown and obfuscated network traffic. To aid the literature identification, we analyse forty recent incidents and obtain prevalent cyber attack vectors of data breaches, which we present as the general workflow for data breaches due to cyber attacks. Finally, we highlight the research issues associated with existing ML-based data breach countermeasures and recommend future research directions.

The relationship between the demographical characteristics of building occupants and their perception of indoor comfort is increasingly being studied. However, the added value from accounting for such characteristics when modeling and predicting occupants’ perceptions remains unclear. An incremental machine learning (ML) modeling and analysis approach is proposed to quantify the influence of four demographical factors (gender, age, nationality, and time lived in the environment) on occupants’ perceptions of their indoor environment conditions. A three-step methodology is presented: (1) data collection through sensors and a questionnaire administered on 206 occupants of academic and office buildings in Abu Dhabi, UAE, (2) development of ML models (i.e., support vector machine, random forest, and gradient boosting) to predict occupants’ perceptions under different scenarios of demographical representation (i.e., from no representation to all demographical parameters included), and (3) analysis of the impact of demographical parameters’ inclusion on the performance of the ML models in terms of predictive accuracy, F1-scores, and computing time. Results confirm that including demographical variables could increase prediction accuracy and F1-scores by approximately 19% and 56%, respectively. However, in some instances, the inclusion of these variables reduced model performance while increasing computing time by as much as 50%. A detailed discussion is presented on the comparative performance of the different tested ML algorithms and the need to strike a balance between increasing model complexity and computational costs.

The application of nonlinear analysis in machine learning (ML) has emerged as a significant approach to understanding and enhancing educational systems. This research explores the integration of nonlinear mathematical and statistical models in various education streams to identify patterns, trends, and opportunities for improvement. By leveraging ML algorithms such as neural networks, decision trees, and support vector machines, the study examines complex relationships and dynamics that linear models often fail to capture. Key areas of focus include predicting student performance, optimizing curriculum design, and identifying at-risk students. The study also investigates the role of advanced statistical techniques such as regression analysis, chaos theory, and fractals in interpreting large-scale educational data. The findings highlight how nonlinear techniques can address challenges in data heterogeneity, noise, and multidimensionality, thereby enhancing decision-making processes in educational management. This paper aims to provide a robust framework for implementing nonlinear ML techniques, offering actionable insights for educators, administrators, and policymakers.

The compatibility of theoretical frameworks with machine learning analyses in psychological research

Colorectal cancer (CRC) is the third most common cause of cancer-related deaths. The five-year relative survival rate for CRC is estimated to be approximately 90% for patients diagnosed with early stages and 14% for those diagnosed at an advanced stages of disease, respectively. Hence, the development of accurate prognostic markers is required. Bioinformatics enables the identification of dysregulated pathways and novel biomarkers. RNA expression profiling was performed in CRC patients from the TCGA database using a Machine Learning approach to identify differential expression genes (DEGs). Survival curves were assessed using Kaplan-Meier analysis to identify prognostic biomarkers. Furthermore, the molecular pathways, protein-protein interaction, the co-expression of DEGs, and the correlation between DEGs and clinical data have been evaluated. The diagnostic markers were then determined based on machine learning analysis. The results indicated that key upregulated genes are associated with the RNA processing and heterocycle metabolic process, including C10orf2, NOP2, DKC1, BYSL, RRP12, PUS7, MTHFD1L, and PPAT. Furthermore, the survival analysis identified NOP58, OSBPL3, DNAJC2, and ZMYND19 as prognostic markers. The combineROC curve analysis indicated that the combination of C10orf2-PPAT- ZMYND19 can be considered as diagnostic markers with sensitivity, specificity, and AUC values of 0.98, 1.00, and 0.99, respectively. Eventually, ZMYND19 gene was validated in CRC patients. In conclusion, novel biomarkers of CRC have been identified that may be a promising strategy for early diagnosis, potential treatment, and better prognosis.