Constructing a comprehensive nursing risk assessment model for older adults inpatients with multiple chronic conditions: A multicenter cross-sectional study.

Machine learning classification of PAH exposure in the Antarctic limpet Nacella concinna.

Development and validation of data-driven, decision tree-based algorithms for identifying Behçet's disease in claims data.

Interpretable machine learning-based prediction of liver metastasis risk in elderly patients with small cell lung Cancer: A study based on the SEER database and external validation in a Chinese cohort.

Development and validation of interpretable machine learning models for dynamic prediction of prognosis in acute pancreatitis complicated by acute kidney injury: A multicenter study.

Designing a machine learning model for predicting cardiovascular events using the triglyceride-glucose index: a cohort study.

Optimizing depression diagnosis: fNIRS and machine learning differentiate unipolar, bipolar, and healthy states.

Seizure risk prediction using machine learning following glioma resection surgery in seizure-naïve patients.

• Proposes DTE, a new method to improve pre-trained decision trees through post-training optimization. • DTE applies to data sets with continuous or continuous and discrete features. • The proposed formulation allows the decision maker to optimize the accuracy or recall of the decision tree. • DTE is feasible in practice, as it delivers improvements even when computation time is limited. Decision trees are off-the-shelf machine learning models widely used for classification and regression tasks in medical, logistics, financial, and other critical areas where interpretability is a key factor. They can efficiently handle numerical and categorical variables, making them a versatile choice for various applications. However, traditional decision-tree training methods are based on greedy heuristics, which cannot provide guarantees regarding whether further improvements could be achieved. We propose Decision Tree Enhancer (DTE), which employs optimization as a post-training step to improve previously trained decision trees. Moreover, the proposed method precludes the need for a pre-processing step for continuous features such as discretization or bucketization , and can be applied regardless of the model used to first train the decision tree. Lastly, DTE’s mathematical programming formulation enables, for example, the consideration of recall thresholds and class prioritization. Tested on 63 classification datasets from the UCI Machine Learning Repository, using tree depths from 1 to 5, four time limits (1, 5, 10, and 30 seconds), and 5 randomized train-test splits cross-validation, the proposed post-training step demonstrated superior performance over CART (Classification And Regression Tree), for both in- and out-of-sample data. With a 30-second time limit, DTE was able to improve the weighted recall in 83.2% of the datasets with an average improvement of 9.0% in training and 5.0% in testing.

Multiple screen addiction and neurological complaints in adolescents: A machine learning-based classification model.

Rapid identification of adulteration in American ginseng powder using near-infrared spectroscopy combined with machine learning.

FTIR spectroscopy combined with machine learning reveals molecular signatures distinguishing three phenotypes of endometriosis.

Numerical modeling of dissolved mercury dynamics and transformation in sea water in Minamata Bay, Japan.

Machine learning-based prediction of three-year mortality in elderly inpatients with coronary artery disease combined with heart failure.

Machine learning-driven multi-objective optimization of Dunaliella salina cultivation for enhanced biomass and β-carotene production.

Machine learning (ML) is increasingly being used in food science due to its ability to extract insights from large datasets. However, the advantages of ML over traditional mechanistic knowledge-based models remain unclear, especially under the limited data conditions often encountered in food bioprocesses. This study aims to address this gap by critically evaluating supervised ML techniques-specifically decision trees, support vector machines, and neural networks-in comparison to a knowledge-based model (KB), using wine fermentation as a practical, experimental example. We evaluated these approaches in three tasks. Tasks 1 and 2 use time-series fermentation data to (1) classify industrial yeast strains based on their metabolite profiles and (2) predict fermentation dynamics. Task 3 focuses on creating a fast surrogate model using ML techniques applied to synthetic data generated by a mechanistic model. For yeast strain classification, we achieved our highest test accuracy of 74% when utilizing all available metabolite data. In predicting fermentation dynamics, the KB model outperformed the ML models, achieving an average normalized root mean squared error of approximately 6%. The ML models, when additional data was incorporated, had a prediction error of around 7.6%. Lastly, a deep learning surrogate model trained solely on synthetic, mechanistic data demonstrated very low errors (around 0.6%) on test sets, compared to the KB model, while also reducing simulation time by a factor of 30. Our findings highlight the significance of experimental design: although ML models perform well when trained on large and diverse datasets, they often struggle with limited data or when predicting outcomes beyond the conditions observed during training. In contrast, mechanistic models show better generalization and biological interpretability. The complementary nature of both approaches suggests that combining them can lead to more robust, data-informed design and control in complex fermentation systems. Leveraging these complementary strengths, we developed and validated a hybrid model that integrates knowledge-based predictions with a residual neural network to correct systematic errors, reducing overall NRMSE from 6% to 5% and improving prediction for most key compounds.

Over the last decade, international police have witnessed a steady rise in criminal activity related to three-dimensional (3D) printed firearms, documenting seizures of blueprints, components, whole 3D printed firearms as well as 3D printers. Investigators have determined traditional firearm examination techniques are insufficient to facilitate the source printer of 3D printed firearms, instead requiring foundational research and adapted forensic methodologies that will better suit the novel toolmarks. Therefore, the current study aimed to bridge the gaps in understanding of 3D print to printer relationships. The study conducted a comprehensive examination of 3D printed items manufactured by five UltiMaker S5 3D printers to establish the presence and persistence of nozzle deposited markings; known as drag marks, between 3D prints of the same make and model, as well as assessing their potential for source information. The feature exhibited a strong potential to discriminate to specific UltiMaker S5 printers. To further assess drag marks utility in a forensic scenario, exclusion-based decision trees were developed and applied to a blind study of 3D printed items. Which resulted in successful source determination of 44 % of samples, demonstrating the previously unassessed possibility of striations on 3D printed items as class and individual level evaluators. The study suggested the continuance of cataloguing and understanding the presence of toolmarks on seized and laboratory generated 3D printed firearms before implementation into casework. Thereby, forensic investigators can begin to disrupt illicit 3D printed firearm manufacturing and distribution.

Variable Priority for Unsupervised Variable Selection.

Socio-demographic and occupational determinants of poor self-perceived health among seasonal migrant farmworkers: A cross-sectional analysis.

Prevalence and correlates of drug use during incarceration among people with opioid use disorder: A focused decision tree analysis.