Publications by authors named "D GRAFF"
Background: The pediatric emergency department is a high-value site for screening and resource referral for health-related social needs. However, best practices for this unique environment remain unclear. This study's objective was to introduce a consensus-based social care training toolkit for the pediatric emergency medicine (PEM) setting.
View Article and Find Full Text PDFObjective: The aim of the study is to assess the association of social determinants of health (SDOH) education and social needs training on pediatric emergency medicine (PEM) physician perception and practices of social care.
Methods: Data were derived from the 2021 National Social Care Practices Survey of PEM program directors (PDs) and fellows. Ordinal and binary logistic regression modeling were completed for educational/training factors and social care perspective and practice outcomes.
Chemprop: A Machine Learning Package for Chemical Property Prediction.
J Chem Inf Model
January 2024
Article Synopsis
- Deep learning is now widely used for predicting molecular properties, creating a demand for user-friendly software that non-experts can use.
- Directed message-passing neural networks (D-MPNNs), particularly via the Chemprop software, have shown strong performance in these prediction tasks and come with new features like multimolecule properties and advanced uncertainty quantification.
- The latest version of Chemprop offers improved tools for training D-MPNN models, achieving top-tier results on various datasets in molecular property prediction.
Immersive virtual reality (VR) is a promising tool to reduce pain in clinical setting. Digital scripts displayed by VR disposals can be enriched by several analgesic interventions, which are widely used to reduce pain. One of these techniques is hypnosis induced through the VR script (VRH) which is facilitated by immersive environment and particularly efficient even for low hypnotizable patients.
View Article and Find Full Text PDFIn molecular discovery and drug design, structure-property relationships and activity landscapes are often qualitatively or quantitatively analyzed to guide the navigation of chemical space. The roughness (or smoothness) of these molecular property landscapes is one of their most studied geometric attributes, as it can characterize the presence of activity cliffs, with rougher landscapes generally expected to pose tougher optimization challenges. Here, we introduce a general, quantitative measure for describing the roughness of molecular property landscapes.
View Article and Find Full Text PDF