6 research outputs found
Scalable Bayesian Reduced-Order Models for Simulating High-Dimensional Multiscale Dynamical Systems
No full textWhile existing mathematical descriptions can accurately account for phenomena at microscopic scales (e. g., molecular dynamics), these are often high-dimensional, stochastic, and their applicability over macroscopic time scales of physical interest is computationally infeasible or impractical. In complex systems, with limited physical insight on the coherent behavior of their constituents, the only available information is data obtained from simulations of the trajectories of huge numbers of degrees of freedom over microscopic time scales. The analysis of these large amounts of data hinges upon the ability to efficiently extract meaningful latent properties and to discover reduced, predictive descriptions. This paper discusses a Bayesian approach to deriving probabilistic coarse-grained models that simultaneously addresses the problems of identifying appropriate reduced coordinates and the effective dynamics in this lower-dimensional representation. At the core of the models proposed lie simple, low-dimensional dynamical systems which serve as the building blocks of the global model. These approximate the latent generating sources and parametrize the reduced-order dynamics. On their own, each of these simple models would be unable to explain and predict the various complexities encountered in multiscale dynamics of physical interest. Similar to the way one would synthesize opinions from various experts in order to reach a conclusion, we propose probabilistic models that combine the predictions of all these building blocks in order to obtain an integrated model that provides a good global approximation. We discuss parallelizable, online inference and learning algorithms that employ sequential Monte Carlo samplers and scale linearly with the dimensionality of the observed dynamics. We propose a Bayesian adaptive time-integration scheme that utilizes probabilistic predictive estimates and enables rigorous concurrent simulation over macroscopic time scales. The data-driven perspective advocated assimilates computational and experimental data and thus can materialize data-model fusion. It can deal with applications that lack a mathematical description and where only observational data is available. Furthermore, it makes nonintrusive use of existing computational models
Scalable Bayesian reduced-order models for simulating high-dimensional multiscale dynamical systems
No full textWhile existing mathematical descriptions can accurately account for phenomena at microscopic scales (e. g., molecular dynamics), these are often high-dimensional, stochastic, and their applicability over macroscopic time scales of physical interest is computationally infeasible or impractical. In complex systems, with limited physical insight on the coherent behavior of their constituents, the only available information is data obtained from simulations of the trajectories of huge numbers of degrees of freedom over microscopic time scales. The analysis of these large amounts of data hinges upon the ability to efficiently extract meaningful latent properties and to discover reduced, predictive descriptions. This paper discusses a Bayesian approach to deriving probabilistic coarse-grained models that simultaneously addresses the problems of identifying appropriate reduced coordinates and the effective dynamics in this lower-dimensional representation. At the core of the models proposed lie simple, low-dimensional dynamical systems which serve as the building blocks of the global model. These approximate the latent generating sources and parametrize the reduced-order dynamics. On their own, each of these simple models would be unable to explain and predict the various complexities encountered in multiscale dynamics of physical interest. Similar to the way one would synthesize opinions from various experts in order to reach a conclusion, we propose probabilistic models that combine the predictions of all these building blocks in order to obtain an integrated model that provides a good global approximation. We discuss parallelizable, online inference and learning algorithms that employ sequential Monte Carlo samplers and scale linearly with the dimensionality of the observed dynamics. We propose a Bayesian adaptive time-integration scheme that utilizes probabilistic predictive estimates and enables rigorous concurrent simulation over macroscopic time scales. The data-driven perspective advocated assimilates computational and experimental data and thus can materialize data-model fusion. It can deal with applications that lack a mathematical description and where only observational data is available. Furthermore, it makes nonintrusive use of existing computational models.</p
An Artificial Intelligence–Driven Digital Health Solution to Support Clinical Management of Patients With Long COVID-19: Protocol for a Prospective Multicenter Observational Study
No full textBackground: COVID-19 pandemic has revealed the weaknesses of most health systems around the world, collapsing them and depleting their available health care resources. Fortunately, the development and enforcement of specific public health policies, such as vaccination, mask wearing, and social distancing, among others, has reduced the prevalence and complications associated with COVID-19 in its acute phase. However, the aftermath of the global pandemic has called for an efficient approach to manage patients with long COVID-19. This is a great opportunity to leverage on innovative digital health solutions to provide exhausted health care systems with the most cost-effective and efficient tools available to support the clinical management of this population. In this context, the SENSING-AI project is focused on the research toward the implementation of an artificial intelligence-driven digital health solution that supports both the adaptive self-management of people living with long COVID-19 and the health care staff in charge of the management and follow-up of this population.Objective: The objective of this protocol is the prospective collection of psychometric and biometric data from 10 patients for training algorithms and prediction models to complement the SENSING-AI cohort.Methods: Publicly available health and lifestyle data registries will be consulted and complemented with a retrospective cohort of anonymized data collected from clinical information of patients diagnosed with long COVID-19. Furthermore, a prospective patient-generated data set will be captured using wearable devices and validated patient-reported outcomes questionnaires to complement the retrospective cohort. Finally, the 'Findability, Accessibility, Interoperability, and Reuse' guiding principles for scientific data management and stewardship will be applied to the resulting data set to encourage the continuous process of discovery, evaluation, and reuse of information for the research community at large.Results: The SENSING-AI cohort is expected to be completed during 2022. It is expected that sufficient data will be obtained to generate artificial intelligence models based on behavior change and mental well-being techniques to improve patients' self-management, while providing useful and timely clinical decision support services to health care professionals based on risk stratification models and early detection of exacerbations.Conclusions: SENSING-AI focuses on obtaining high-quality data of patients with long COVID-19 during their daily life. Supporting these patients is of paramount importance in the current pandemic situation, including supporting their health care professionals in a cost-effective and efficient management of long COVID-19.Trial Registration: Clinicaltrials.gov NCT05204615; https://clinicaltrials.gov/ct2/show/NCT0520461
An Artificial Intelligence–Driven Digital Health Solution to Support Clinical Management of Patients With Long COVID-19: Protocol for a Prospective Multicenter Observational Study
No full textBACKGROUND: COVID-19 pandemic has revealed the weaknesses of most health systems around the world, collapsing them and depleting their available health care resources. Fortunately, the development and enforcement of specific public health policies, such as vaccination, mask wearing, and social distancing, among others, has reduced the prevalence and complications associated with COVID-19 in its acute phase. However, the aftermath of the global pandemic has called for an efficient approach to manage patients with long COVID-19. This is a great opportunity to leverage on innovative digital health solutions to provide exhausted health care systems with the most cost-effective and efficient tools available to support the clinical management of this population. In this context, the SENSING-AI project is focused on the research toward the implementation of an artificial intelligence–driven digital health solution that supports both the adaptive self-management of people living with long COVID-19 and the health care staff in charge of the management and follow-up of this population. OBJECTIVE: The objective of this protocol is the prospective collection of psychometric and biometric data from 10 patients for training algorithms and prediction models to complement the SENSING-AI cohort. METHODS: Publicly available health and lifestyle data registries will be consulted and complemented with a retrospective cohort of anonymized data collected from clinical information of patients diagnosed with long COVID-19. Furthermore, a prospective patient-generated data set will be captured using wearable devices and validated patient-reported outcomes questionnaires to complement the retrospective cohort. Finally, the ‘Findability, Accessibility, Interoperability, and Reuse’ guiding principles for scientific data management and stewardship will be applied to the resulting data set to encourage the continuous process of discovery, evaluation, and reuse of information for the research community at large. RESULTS: The SENSING-AI cohort is expected to be completed during 2022. It is expected that sufficient data will be obtained to generate artificial intelligence models based on behavior change and mental well-being techniques to improve patients’ self-management, while providing useful and timely clinical decision support services to health care professionals based on risk stratification models and early detection of exacerbations. CONCLUSIONS: SENSING-AI focuses on obtaining high-quality data of patients with long COVID-19 during their daily life. Supporting these patients is of paramount importance in the current pandemic situation, including supporting their health care professionals in a cost-effective and efficient management of long COVID-19. TRIAL REGISTRATION: Clinicaltrials.gov NCT05204615; https://clinicaltrials.gov/ct2/show/NCT05204615 INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/3770
Challenging challenges : a metaphysical redress of van den Haag's retributive axiom : Unequal justice over equal injustice
No full textIncludes abstract.
Includes bibliographical references
