Search

Machine learning algorithms make predictions by fitting highly parameterized nonlinear functions to massive amounts of data. Yet those models are not necessarily consistent with physical laws and offer limited interpretability. Extending machine learning models by introducing scientific knowledge in the optimization problem is known as physics-based and data-driven modelling. A promising development are physics informed neural networks (PINN) which ensure consistency to both physical laws and measured data. The aim of this research is to model the time-dependent temperature profile in bulk materials following the passage of a moving laser focus by a PINN. The results from the PINN agree essentially with finite element simulations, proving the suitability of the approach. New perspectives for applications in laser material processing arise when PINNs are integrated in monitoring systems or used for model predictive control.

Design of experiments (DOE) is an established method to allocate resources for efficient parameter space exploration. Model based active learning (AL) data sampling strategies have shown potential for further optimization. This paper introduces a workflow for conducting DOE comparative studies using automated machine learning. Based on a practical definition of model complexity in the context of machine learning, the interplay of systematic data generation and model performance is examined considering various sources of uncertainty: this includes uncertainties caused by stochastic sampling strategies, imprecise data, suboptimal modeling, and model evaluation. Results obtained from electrical circuit models with varying complexity show that not all AL sampling strategies outperform conventional DOE strategies, depending on the available data volume, the complexity of the dataset, and data uncertainties. Trade-offs in resource allocation strategies, in particular between identical replication of data points for statistical noise reduction and broad sampling for maximum parameter space exploration, and their impact on subsequent machine learning analysis are systematically investigated. Results indicate that replication oriented strategies should not be dismissed but may prove advantageous for cases with non-negligible noise impact and intermediate resource availability. The provided workflow can be used to simulate practical experimental conditions for DOE testing and DOE selection., Competing Interests: Declarations. Competing interests: The authors declare no competing interests., (© 2024. The Author(s).)

Neurodevelopmental conditions, such as Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD), present unique challenges due to overlapping symptoms, making an accurate diagnosis and targeted intervention difficult. Our study employs advanced machine learning techniques to analyze functional magnetic resonance imaging (fMRI) data from individuals with ASD, ADHD, and typically developed (TD) controls, totaling 120 subjects in the study. Leveraging multiclass classification (ML) algorithms, we achieve superior accuracy in distinguishing between ASD, ADHD, and TD groups, surpassing existing benchmarks with an area under the ROC curve near 98%. Our analysis reveals distinct neural signatures associated with ASD and ADHD: individuals with ADHD exhibit altered connectivity patterns of regions involved in attention and impulse control, whereas those with ASD show disruptions in brain regions critical for social and cognitive functions. The observed connectivity patterns, on which the ML classification rests, agree with established diagnostic approaches based on clinical symptoms. Furthermore, complex network analyses highlight differences in brain network integration and segregation among the three groups. Our findings pave the way for refined, ML-enhanced diagnostics in accordance with established practices, offering a promising avenue for developing trustworthy clinical decision-support systems., Competing Interests: EpilabKI is funded through the Bavarian stated Ministery for Sciences and the Arts research. This does not alter our adherence to PLOS ONE policies on sharing data and materials., (Copyright: © 2024 Alves et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Importance: Boarding in the emergency department (ED) is a critical indicator of quality of care for hospitals. It is defined as the time between the admission decision and departure from the ED. As a result of boarding, patients stay in the ED until inpatient beds are available; moreover, boarding is associated with various adverse events., Study Objective: The objective of our systematic review was to determine whether ED boarding (EDB) time is associated with in-hospital mortality (IHM)., Methods: A systematic search was conducted in academic databases to identify relevant studies. Medline, PubMed, Scopus, Embase, Cochrane, Web of Science, Cochrane, CINAHL and PsychInfo were searched. We included all peer-reviewed published studies from all previous years until November 2018. Studies performed in the ED and focused on the association between EDB and IHM as the primary objective were included. Extracted data included study characteristics, prognostic factors, outcomes, and IHM. A search update in PubMed was performed in May 2019 to ensure the inclusion of recent studies before publishing., Results: From the initial 4,321 references found through the systematic search, the manual screening of reference lists and the updated search in PubMed, a total of 12 studies were identified as eligible for a descriptive analysis. Overall, six studies found an association between EDB and IHM, while five studies showed no association. The last remaining study included both ICU and non-ICU subgroups and showed conflicting results, with a positive association for non-ICU patients but no association for ICU patients. Overall, a tendency toward an association between EDB and IHM using the pool random effect was observed., Conclusion: Our systematic review did not find a strong evidence for the association between ED boarding and IHM but there is a tendency toward this association. Further well-controlled, international multicenter studies are needed to demonstrate whether this association exists and whether there is a specific EDB time cut-off that results in increased IHM., Competing Interests: AB is the CEO of Global Healthcare Network & Research Innovation Institute LLC. There are no related patents, products in development, or marketed products to declare. This does not alter our adherence to PLOS ONE policies on data and materials sharing.