98%
921
2 minutes
20
Purpose: Randomized controlled trials are considered the golden standard for estimating treatment effect but are costly to perform and not always possible. Observational data, although readily available, is sensitive to biases such as confounding by indication. Structure learning algorithms for Bayesian Networks (BNs) can be used to discover the underlying model from data. This enables identification of confounders through graph analysis, although the model might contain noncausal edges. We propose using a blacklist to aid structure learning in finding causal relationships. This is illustrated by an analysis into the effect of active treatment ( observation) in localized prostate cancer.
Methods: In total, 4,121 prostate cancer records were obtained from the Netherlands Cancer Registry. Subsequently, we developed a (causal) BN using structure learning while precluding noncausal relations. Additionally, we created several Cox proportional hazards models, each correcting for a different set of potential confounders (including propensity scores). Model predictions for overall survival were compared with expected survival on the basis of the general population using data from Statistics Netherlands (Centraal Bureau voor de Statistiek).
Results: Structure learning precluding noncausal relations resulted in a causal graph but did not identify significant edges toward treatment; they were added manually. Graph analysis identified year of diagnosis and age as confounders. The BN predicted a treatment effect of 1 percentage point at 10 years. Chi-squared analysis found significant associations between year of diagnosis, age, stage, and treatment. Propensity score correction was successful. Adjusted Cox models predicted significant treatment effect around 3 percentage points at 10 years.
Conclusion: A blacklist in conjunction with structure learning can result in a causal BN that can be used for confounder identification. Treatment effect found here is close to the 5 percentage point found in the literature.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1200/CCI.22.00080 | DOI Listing |
Mol Divers
September 2025
Department of Biotechnology, National Institute of Technology Raipur, Raipur, Chhattisgarh, 492001, India.
Traditional drug discovery methods like high-throughput screening and molecular docking are slow and costly. This study introduces a machine learning framework to predict bioactivity (pIC₅₀) and identify key molecular properties and structural features for targeting Trypanothione reductase (TR), Protein kinase C theta (PKC-θ), and Cannabinoid receptor 1 (CB1) using data from the ChEMBL database. Molecular fingerprints, generated via PaDEL-Descriptor and RDKit, encoded structural features as binary vectors.
View Article and Find Full Text PDFChaos
September 2025
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, USA.
Although many real-world time series are complex, developing methods that can learn from their behavior effectively enough to enable reliable forecasting remains challenging. Recently, several machine-learning approaches have shown promise in addressing this problem. In particular, the echo state network (ESN) architecture, a type of recurrent neural network where neurons are randomly connected and only the read-out layer is trained, has been proposed as suitable for many-step-ahead forecasting tasks.
View Article and Find Full Text PDFJ Chem Theory Comput
September 2025
Institute of Theoretical Chemistry, Faculty of Chemistry, University of Vienna, Währinger Straße 17, 1090 Vienna, Austria.
We present a novel, flexible framework for electronic structure interfaces designed for nonadiabatic dynamics simulations, implemented in Python 3 using concepts of object-oriented programming. This framework streamlines the development of new interfaces by providing a reusable and extendable code base. It supports the computation of energies, gradients, various couplings─like spin-orbit couplings, nonadiabatic couplings, and transition dipole moments─and other properties for an arbitrary number of states with any multiplicities and charges.
View Article and Find Full Text PDFJ Vis
September 2025
Neuroscience Program, Western University, London, ON, Canada.
Studies of visual face processing often use flat images as proxies for real faces due to their ease of manipulation and experimental control. Although flat images capture many features of a face, they lack the rich three-dimensional (3D) structural information available when binocularly viewing real faces (e.g.
View Article and Find Full Text PDFJ Microbiol Biol Educ
September 2025
School of Marine and Biological Engineering, Yancheng Teachers University, Yancheng, China.
This paper conducts an in-depth investigation and analysis of 25 microbiology course outlines from 23 domestic universities in China, focusing on the structure of prerequisite courses. The study finds that microbiology course outlines typically include basic course information, objectives, content, teaching methods, resources, assessment, and scheduling. Reasonable prerequisite course settings are vital for clarifying logical relationships among courses in talent training programs, organizing key and challenging knowledge systems, and enhancing university course quality.
View Article and Find Full Text PDF