Results 221 to 230 of about 85,695 (269)

Active Learning for the Discovery of Antiviral Polymers

Macromolecular Rapid Communications, EarlyView.
Machine learning and active learning are integrated to accelerate the discovery of antiviral polymers. Molecular descriptors derived from polymer composition enable predictive modeling of antiviral activity, while unsupervised clustering explores chemical diversity. The active learning workflow identifies optimal candidates for synthesis, demonstrating
Clodagh M Boland, Nhat Quynh Nguyen, Nathan RB Boase   +2 more
wiley   +1 more source

An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson's disease motor progression. [PDF]

Front Digit Health
Fırat Y.
europepmc   +1 more source

Clinical Outcome Assessments in Parkinson's Disease: A Scoping Review of Current Rating Scales and Future Needs

Movement Disorders Clinical Practice, EarlyView.
Abstract Background Clinical outcome assessments (COAs) are essential for evaluating symptom severity, treatment response, and disease progression in Parkinson's disease (PD). As clinical knowledge evolves, it is necessary to revisit the recommendation status on the COAs to ensure their continued relevance and validity. Objectives To provide an updated
Evita Papathoma, Panagiota Tsitsi, Nirosen Vijiaratnam, Camila Aquino, Stephen R. Duma, Norbert Kovacs, Kigocha Lameck Okeng'o, Aparna Wagle Shukla, Roongroj Bhidayasiri, Tiago A. Mestre, Alvaro Sanchez Ferro, Alberto J. Espay, Michelle H.S. Tosin, Matej Skorvanek, Ioanna Markaki   +14 more
wiley   +1 more source

Risk Stratification for In-Hospital Mortality in Alzheimer's Disease Using Interpretable Regression and Explainable AI. [PDF]

Geriatrics (Basel)
Alkam T, Tarshizi E, Benschoten AHV.
europepmc   +1 more source

The Brain‐Age Gap in Pediatric Dystonia: Neuroanatomical Deviations Inform Deep Brain Stimulation Outcomes

Movement Disorders, EarlyView.
Abstract Background Dystonia in children is a heterogeneous condition with variable response to deep brain stimulation (DBS). Brain‐age gap, a machine learning‐derived metric of structural deviation from norm, may capture signatures that differentiate underlying biotypes and predict outcomes.
Timur H. Latypov, Alexandre Berger, Manuela Mohareb, Karim Mithani, Sara Breitbart, Lindsey M. Vogt, Thiemo Dinger, Inge Meijer, Alexander G. Weil, Alfonso Fasano, Carolina Gorodetsky, George M. Ibrahim   +11 more
wiley   +1 more source

Development of a predictive model for in-hospital new-onset atrial fibrillation in older adults with hypertension and acute myocardial infarction, enhanced by SHAP interpretability: a retrospective cohort study. [PDF]

Front Med (Lausanne)
Ge X, Tao Y, Zhang L, Cao J, Dong X, Ma L.   +5 more
europepmc   +1 more source

Diagnostic Value of Glycocalyx Shedding in Blood for Differentiating between Parkinson's Disease and Multiple System Atrophy

Movement Disorders, EarlyView.
Abstract Background Blood–brain barrier disruption is increasingly recognized in synucleinopathies, but the role of the endothelial glycocalyx (GLX) in Parkinson's disease (PD) and multiple system atrophy (MSA) remains unclear. Objectives The aim was to determine whether plasma GLX markers differ between PD, MSA, and healthy controls (HC), relate to ...
Jonas Folke, Brian DellaValle, Mathias Lindh Jørgensen, Phillip Bredahl Mogensen, Casper Hempel, Jørgen Rungby, Anne‐Mette Hejl, Annemette Løkkegaard, Lisette Salvesen, Sara Bech, Mette Møller, Erik Hvid Danielsen, Morten Blaabjerg, Matthias Bode, Tomasz Brudek, Susana Aznar   +15 more
wiley   +1 more source

Prediction of Smartphone Addiction Among Korean Adolescents Based on Physical Activity and Mental Health: A Machine Learning Analysis Using LASSO and SHAP From the Korea Youth Risk Behavior Survey. [PDF]

Alpha Psychiatry
Lee K, Seo W, Jung SY.
europepmc   +1 more source

Exploring the Strengths and Limitations of Polymer Chemistry Informed Neural Networks

Macromolecular Reaction Engineering, EarlyView.
PCINNs are able to reach high levels of predictive performance utilizing imperfect kinetic models and a relatively small dataset, with reliable extrapolation at reaction temperatures significantly beyond the range of the original dataset. ABSTRACT Kinetic models are essential tools for providing a fundamental understanding of polymerization processes ...
Shaghayegh Hamzehlou, Nicholas Ballard, José M. Asua   +2 more
wiley   +1 more source