To investigate the influence of different feature aggregation and selection methods on the predictive performance of fluorine-18 fluorodeoxyglucose ( 18 F-FDG) PET radiomics in assessing survival outcomes in patients with lymphoma. This retrospective analysis included 80 patients with histologically confirmed lymphoma, each presenting with at least three lesions on baseline 18 F-FDG PET images. Metabolic tumor volumes were segmented using a standardized uptake value threshold of 4.0. From each lesion, 107 radiomic features were extracted. Of these, 30 features were preselected based on their robustness to variations in tracer uptake time, image reconstruction parameters, and respiratory motion. Six distinct feature aggregation approaches were evaluated in combination with six feature selection methods. Multivariable Cox proportional hazards regression was used to assess the predictive performance of each aggregation-selection strategy for progression-free survival (PFS) and overall survival (OS). All combinations of feature aggregation and selection methods produced statistically significant prognostic models for PFS and OS, with Harrell's concordance indices (C-index) ranging from 0.582 to 0.668 for PFS and from 0.597 to 0.721 for OS. The best predictive performance was achieved using median value aggregation across all individual lesions combined with feature selection via the least absolute shrinkage and selection operator. Integrating clinical variables with radiomic features further improved predictive performance. The prognostic value of 18 F-FDG PET radiomics remained consistent across different feature aggregation and selection strategies. The establishment of standardized analysis workflows is essential to facilitate its clinical implementation in personalized treatment planning for patients with lymphoma.

Interval retention optimization (IRO): An efficient feature selection method for expanding spectral datasets.

Exploring the feature prioritization and data sampling of PCOS diagnosis via densely connected attention based squeeze deep learning detection model.

Prey capture enhanced Harris hawks optimizer for wrapper-based feature selection in high-dimensional medical data.

Predictors of short-term, relapse-independent progression in multiple sclerosis: A machine learning approach based on clinical data and conventional MRI-derived features.

Opposition and reinforcement learning growth-starfish optimization algorithm for engineering design and feature selection

Variable Priority for Unsupervised Variable Selection.

In multi-dimensional classification (MDC), each instance is associated with labels from multiple potentially interdependent class dimensions. However, existing approaches often overlook the fact that different semantic dimensions may require distinct feature representations. Additionally, irrelevant and redundant features in the feature space can adversely affect model performance. To address these issues, a feature selection approach based on evolutionary multi-tasking named Fest is proposed for MDC. It treats feature selection for each class dimension as a separate subtask for evolution, ensuring the selected features effectively capture the semantics of each dimension. To effectively identify and select shared features between correlated class dimensions, Fest introduces an exploration mechanism for feature interaction that considers class dependencies. Extensive experiments are conducted on eleven benchmark datasets as well as on four state-of-the-art MDC approaches. Experimental results clearly demonstrate that selecting dimension-specific features instead of all features can significantly improve the classification performance of existing MDC approaches.

Spatial and multi-omics transcriptomic dissects platinum resistance in lung adenocarcinoma: a five-gene predictive model with tumor microenvironment dynamics.

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.

Multi-subspace graph clustering joint dimensionality reduction and feature selection

Aircraft pilots can be faced with a high mental workload (MW) combined with moderate hypoxia and sleep restriction. We aimed to assess the cross-validation of a machine learning-based MW predictive model under hypoxia and/or sleep restriction. Secondly, we developed a robust predictive model using multimodal physiological parameters to improve the validity across different physiological conditions. Seventeen healthy participants were randomly exposed to three 12-minute periods of increased MW (low, medium, and high) in a 4-condition crossover design: sleep restriction (SR, <3 h Total Sleep Time, TST) vs. habitual sleep (HS, >6 h TST), hypoxia (HY, 2 h, FIO2=13.6%, ∼3500 m) vs. normoxia (NO, FIO2=21%). MW levels were designed using the Multi-Attribute Test Battery (MATB)-II with an additional auditory Oddball-like task. Six machine learning classifiers were compared. Features selection (from EEG, ECG, respiratory and eye tracking sensors) was performed using backward Recursive Feature Elimination (RFE). The best models for 1-minute MW levels classification on HSNO were K-Nearest Neighbors (KNN, F1 score = 80.3 ± 8.9%), Support Vector Machine (SVM, 77.8 ± 10.3%) and Random Forest (RF, 75.7 ± 9.1%). Exposure to sleep restriction and/or hypoxia decreased models' performance (F1 <35%). KNN and RF models, in particular those including EEG and eye tracking, trained on All-Conditions performed well across conditions (F1 scores = 77.4 ± 7.8% and 70.7 ± 10.2%). Our results highlight the need for training MW models under different physiological constraints and using multimodal datasets to improve robustness. (NCT05563688).

Multicentre development and validation of a risk model integrating immunotherapy and coagulation biomarkers for thrombosis in autoimmune neurological disorders.

High tunnels are widely used by growers in the United States to extend the growing season, but their low-cost design often lacks temperature monitoring and automated ventilation. Consequently, crops can experience rapid increases in air temperature that may lead to heat stress or damage. Accurate 1-hour temperature forecasts can support timely manual ventilation and reduce crop risk. We evaluated the reuse of a machine learning (ML) artificial neural network (ANN) architecture, developed originally for solar radiation forecasting, for predicting internal high-tunnel temperatures. Three weather data sources were tested as model inputs: local weather station data, the National Oceanic and Atmospheric Administration’s High-Resolution Rapid Refresh (HRRR) forecasts, and HRRR data enhanced with solar radiation predictions from a previously developed ML-based solar radiation forecasting model. Models were trained using high-tunnel and weather data from Apr and Oct 2024 at two solar radiation thresholds (&gt; 400 W·m –2 and &gt; 100 W·m –2 ) tested on both the same 2024 (training-year) data and future data from Mar 2025 to assess model generalization. Results showed that for the training-year data, the enhanced HRRR feature group provided the most useful forecasts, particularly for locations without local weather data. Expanding training data to include data from &gt; 100 W·m –2 broadened the model’s operating range, but sometimes reduced accuracy within 500 to 700 W·m –2 . When applied to future (2025) data, model performance degraded substantially; however, removing the date and time variables from the input features improved results, though they were still less than training-year accuracy. Models retrained using combined 2024 and 2025 datasets performed notably better, especially when trained with a solar radiation threshold &gt; 100 W·m –2 , outperforming those trained solely on 2024 data. These findings demonstrate that the ANN structure can be repurposed effectively for high-tunnel temperature forecasting. They also underscore the importance of training data quality, feature (input variable) selection, and generalization strategy for reliable, real-world agricultural applications, where early temperature warnings can help growers minimize crop losses and improve management decisions. Looking forward, continuous learning approaches, such as retraining with new data or updating key input features such as solar radiation forecasts, may help sustain model performance as environmental conditions and tunnel characteristics evolve.

Enhancing VMamba for change detection via lightweight feature interaction and selection

Adaptive neural seizure detection through intelligent EEG channel selection and dynamic feature recognition

Fuzzy neighborhood-based feature selection with missing labels via feature graph matrix and label enhancement

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

Scene coordinate regression (SCR) offers an efficient alternative to computation-heavy feature-matching methods for visual relocalization but often suffers from incorrect geometric associations in complex environments. This paper proposes a novel contour-guided feature selection framework to enhance SCR robustness by integrating point and line features. We introduce two key mechanisms: a Feature Contribution Estimation (FCE) module that dynamically reweights features to suppress noise, and a Contour Guidance (CG) module that leverages edge maps to prioritize geometrically significant structures during training. Extensive experiments on the 7-Scenes and Cambridge Landmarks datasets demonstrate that our method outperforms state-of-the-art learning-based baselines, achieving an average accuracy of 80.6% on the 7-Scenes dataset. This approach encourages the model to learn more stable and semantically meaningful features, ultimately enhancing localization performance.