Background And Objective: Healthcare datasets are plagued by issues of data scarcity and class imbalance. Clinically validated virtual patient (VP) models can provide accurate in-silico representations of real patients and thus a means for synthetic data generation in hospital critical care settings. This research presents a realistic, time-varying mechanically ventilated respiratory failure VP profile synthesised using a stochastic model.
Methods: A stochastic model was developed using respiratory elastance (E) data from two clinical cohorts and averaged over 30-minute time intervals. The stochastic model was used to generate future E data based on current E values with added normally distributed random noise. Self-validation of the VPs was performed via Monte Carlo simulation and retrospective E profile fitting. A stochastic VP cohort of temporal E evolution was synthesised and then compared to an independent retrospective patient cohort data in a virtual trial across several measured patient responses, where similarity of profiles validates the realism of stochastic model generated VP profiles.
Results: A total of 120,000 3-hour VPs for pressure control (PC) and volume control (VC) ventilation modes are generated using stochastic simulation. Optimisation of the stochastic simulation process yields an ideal noise percentage of 5-10% and simulation iteration of 200,000 iterations, allowing the simulation of a realistic and diverse set of E profiles. Results of self-validation show the retrospective E profiles were able to be recreated accurately with a mean squared error of only 0.099 [0.009-0.790]% for the PC cohort and 0.051 [0.030-0.126]% for the VC cohort. A virtual trial demonstrates the ability of the stochastic VP cohort to capture E trends within and beyond the retrospective patient cohort providing cohort-level validation.
Conclusion: VPs capable of temporal evolution demonstrate feasibility for use in designing, developing, and optimising bedside MV guidance protocols through in-silico simulation and validation. Overall, the temporal VPs developed using stochastic simulation alleviate the need for lengthy, resource intensive, high cost clinical trials, while facilitating statistically robust virtual trials, ultimately leading to improved patient care and outcomes in mechanical ventilation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cmpb.2023.107728 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Fractional and stochastic modeling of breast cancer progression with real data validation.
PLoS One
January 2025
Biology Department, Faculty of Science, Islamic University of Madinah, Madinah, Saudi Arabia.
This study presents a novel approach to modeling breast cancer dynamics, one of the most significant health threats to women worldwide. Utilizing a piecewise mathematical framework, we incorporate both deterministic and stochastic elements of cancer progression. The model is divided into three distinct phases: (1) initial growth, characterized by a constant-order Caputo proportional operator (CPC), (2) intermediate growth, modeled by a variable-order CPC, and (3) advanced stages, capturing stochastic fluctuations in cancer cell populations using a stochastic operator.
View Article and Find Full Text PDFImplementation of Stochastic Gradient Descent in an Automated Glow Peak Identification Software for Multiple Thermoluminescent Dosimeter Types.
Health Phys
January 2025
Department of Nuclear Engineering and Radiological Sciences, University of Michigan, 2355 Bonisteel Boulevard, Ann Arbor, MI 48109-2104.
A glow-curve analysis code was previously developed in C++ to analyze thermoluminescent dosimeter glow curves using automated peak detection while a first-order kinetics model. A newer version of this code was implemented to improve the automated peak detection and curve fitting models. The Stochastic Gradient Descent Algorithm was introduced to replace the prior approach of taking first and second-order derivatives for peak detection.
View Article and Find Full Text PDFStochastic decisions support optimal foraging of volatile environments, and are disrupted by anxiety.
Cogn Affect Behav Neurosci
January 2025
Department of Psychology, Royal Holloway, University of London, London, UK.
Adolescence is a developmental period of relative volatility, where the individual experiences significant changes to their physical and social environment. The ability to adapt to the volatility of one's surroundings is an important cognitive ability, particularly while foraging, a near-ubiquitous behaviour across the animal kingdom. As adolescents experience more volatility in their surroundings, we predicted that this age group would be more adept than adults at using exploration to adjust to volatility.
View Article and Find Full Text PDFThe impact of preschool children's physical fitness evaluation under self organizing maps neural network.
Sci Rep
January 2025
Faculty of Education, Universiti Kebangsaan Malaysia, Bangi, Selangor, 43600, Malaysia.
To improve the scientific accuracy and precision of children's physical fitness evaluations, this study proposes a model that combines self-organizing maps (SOM) neural networks with cluster analysis. Existing evaluation methods often rely on traditional, single statistical analyses, which struggle to handle the complexity of high-dimensional, nonlinear data, resulting in a lack of precision and personalization. This study uses the SOM neural network to reduce the dimensionality of high-dimensional health data.
View Article and Find Full Text PDFA scalable variational inference approach for increased mixed-model association power.
Nat Genet
January 2025
Department of Statistics, University of Oxford, Oxford, UK.
The rapid growth of modern biobanks is creating new opportunities for large-scale genome-wide association studies (GWASs) and the analysis of complex traits. However, performing GWASs on millions of samples often leads to trade-offs between computational efficiency and statistical power, reducing the benefits of large-scale data collection efforts. We developed Quickdraws, a method that increases association power in quantitative and binary traits without sacrificing computational efficiency, leveraging a spike-and-slab prior on variant effects, stochastic variational inference and graphics processing unit acceleration.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!