Leafy Green Phenotyping Review Finds Imaging Outpaces Insight
A scoping review of 59 studies finds imaging-based phenotyping of leafy greens excels at observation but rarely translates into operational ...
Tag: Machine Learning
Machine learning models predict severe chemotherapy-induced neutropenia in breast cancer using only pre-treatment data
Machine learning models built only from pre-chemotherapy data predicted severe neutropenia in breast cancer patients with AUCs around 0.75 across ...
Diffusion model refines coarse elevation data into sharper terrain maps
A new conditional diffusion model called DSR-STRDiff reconstructs high-resolution elevation data from coarse inputs, reporting the best metrics among compared ...
New AI Network Monitors High-Speed Train Brake Pads Across Different Speeds
A new domain adaptation network learns brake pad vibration patterns at multiple rotational speeds to support cross-speed condition monitoring for ...
Machine learning outperforms traditional models in precision poultry nutrition review
A new review finds machine learning outperforms traditional linear models in predicting poultry nutrient requirements, with big data enabling precise, ...
Gut Microbiome Test Spots Cholangiocarcinoma Across Fungi, Viruses and Bacteria
A stool-based machine learning model combining gut archaea, bacteria, fungi, viruses and microbial genes detected cholangiocarcinoma with an average AUC ...
Machine Learning Predicts ICU Deaths in PAD Patients, but Hemodynamics Add Little
An explainable XGBoost model retained good discrimination for 28-day mortality in a later MIMIC-IV calendar period, but early hemodynamic summaries ...
Generalized Model Predicts Rice Bran Pellet Drying as Well as Machine Learning
A generalized Midilli drying model matched or outperformed machine learning benchmarks for predicting moisture removal from rice bran pellets under ...
AI model predicts heart defect severity in premature infants from routine NICU data
An AI model using routine NICU data predicted hemodynamically significant patent ductus arteriosus in very low birth weight infants with ...
Research report: Integrating inheritance model selection, weighted polygenic scoring, and interpretable machine learning for cardiotoxicity risk prediction in pediatric ALL
In 216 Pakistani children with ALL, a weighted five-variant polygenic score discriminated anthracycline-induced cardiotoxicity far better than an unweighted score, ...
New Feature-Selection Algorithm Predicts Aortic Calcification in Dialysis Patients
An enhanced kernel search optimizer paired with a support vector machine predicted abdominal aortic calcification in hemodialysis patients with 92.8 ...
Vision-Language AI Model Detects Bengali Fake News with Explainable Reasoning
Researchers report a multimodal framework combining Bengali OCR, hybrid visual encoders, and vision-language reasoning that achieved 97% accuracy on a ...
Blood vesicle proteins flag advanced scarring in fatty liver disease
An 11-protein signature from circulating extracellular vesicles, validated in an independent cohort, was associated with advanced fibrosis in MASH and ...
New Feature Selection Method Trims Intrusion Detection Models for Industrial Edge Devices
A cluster-preserving feature selection framework cut intrusion detection features from 78 to 27 on the CICIDS2017 benchmark while Random Forest ...
Brain Wiring Maps Could Steer Personalized Cognitive Rehab After Stroke
A narrative review maps how stroke disrupts large-scale brain networks and argues that connectome data could personalize cognitive rehabilitation, while ...
Machine Learning Flags Anxiety in Sudden Hearing Loss Patients, Study Finds
A retrospective single-center study found 62.5% of hospitalized adults with sudden sensorineural hearing loss met a screening threshold for anxiety ...
Brain Connectivity Patterns May Flag Which Back Pain Patients Will Chronicify
A resting-state fMRI and machine learning study identified six brain regions whose individualized dysconnectivity patterns distinguished subacute back pain patients ...
AI and fuzzy framework reconstructs China’s economic growth quality index
A new hybrid AI and fuzzy algorithm framework reconstructs a multidimensional Economic Growth Quality Index from Chinese provincial data spanning ...
Open-Source AI Framework Cuts Particle Beam Losses at GSI/FAIR from 45% to 12%
An open-source optimization framework developed with CERN has automated accelerator tuning at GSI and FAIR, cutting SIS18 injection losses from ...
Neural Networks Learn Stable Physics-Based Models Straight From Data
Researchers in Stuttgart have introduced a machine-learning framework that identifies stable, passive port-Hamiltonian models directly from data, validated on systems ...
