We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Empowering cardiovascular care: a comprehensive approach using advanced machine learning models and algorithmic optimization.
AI summary Read the abstract
This study tested computer programs (machine learning models) that analyze patient data to predict cardiovascular disease. Researchers compared several models and found one called Hist Gradient Boosting worked best, especially when combined with an optimization method called Original PSS, which improved prediction accuracy on test data.
Cardiovascular disease is one of the global health issues, exacerbated by lifestyle changes, environmental influences, and plastic pollution. Algorithms are used in the healthcare industry to optimize patient care and prevent complications. Connections with machine learning (ML) and artificial intelligence (AI) enhance timely detection, more accurate projections, reduced risk, and better patient outcomes. This technological progress makes medical processes easier, faster, and better, and optimizes the use of resources with as little high-level human involvement as possible during interventions. To undertake this exploration, 4 different ML models were used: Hist Gradient Boosting, XGBoost, Random Forest, and Extra Trees; and a challenging comparison was made to select an optimum model for use. The accuracy of the selected model was optimized for the enhancement of accuracy and combined with the base model (initial model) using the following algorithms: Original FPA algorithm, Original PSS algorithm, JADE algorithm, Enhanced AEO algorithm, Enhanced TWO algorithm. Evaluation results indicate that the Hist Gradient Boosting model is more competent than the rest. The evaluation results showed that the other machine learning models were not able to perform as well as Hist Gradient Boosting. Based on the results of the evaluated optimization methods, the combination of Hist Gradient Boosting and Original PSS outperformed the others on the test dataset with a 0.7408 F1 score, showing the effectiveness of the proposed optimized framework for the prediction of cardiovascular disease.
More Papers Like This
Applicability of machine learning techniques to analyze Microplastic transportation in open channels with different hydro-environmental factors
AI summary Read the abstract
Researchers applied machine learning models to predict how microplastics move through open water channels under different flow conditions, vegetation patterns, and particle densities. They found that tree-based algorithms like Random Forest and Extreme Gradient Boost significantly outperformed traditional statistical models in prediction accuracy. The study demonstrates that machine learning can be a valuable tool for understanding and forecasting microplastic transport in waterways.
AI-Driven Framework Development for Predictive Classification of Microplastic Concentration of Aquatic Systems in the United States
AI summary Read the abstract
Researchers compared four machine learning models—logistic regression, random forest, support vector machine, and a neural network—for predicting microplastic density in US coastal waters across three regions. The support vector machine performed best with 93.94% average accuracy, demonstrating the potential of AI-driven tools for microplastic monitoring.
How Microplastics Influence Health Risk Pathways in Urban Water Systems? Integrated Binary classification, Machine Learning and Structural Equation Modeling Approach
AI summary Read the abstract
Researchers used data modeling and machine learning to trace how microplastics move through city water systems and connect to potential health risks. By combining several analysis methods, they were able to identify which factors most strongly link microplastic contamination to human exposure, offering a clearer roadmap for pinpointing where water treatment efforts should focus. This matters because it helps scientists and city planners target the biggest risks first, rather than guessing where microplastic pollution is most likely to affect the water you drink.
The toxicological impact of PET-MPs exposure on atherosclerosis: insights from network toxicology, molecular docking, and machine learning
AI summary Read the abstract
Researchers used network toxicology, molecular docking, and machine learning to identify how PET microplastics may promote atherosclerosis, narrowing 28 candidate targets to seven key genes and predicting interactions with atherosclerosis-relevant pathways including inflammation and lipid metabolism.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.