Click here to read some interesting recently published papers from our community. If you have published an article in the field of in silico medicine, send it to us: we will include it in this section of the newsletter!
Nature BPJ - Digital Medicine: Digital twins and Big AI: the future of truly individualised healthcare.
Peter Coveney et al
Abstract
The integration of physics-based digital twins with data-driven artificial intelligenceātermed āBig AIāācan advance truly personalised medicine. While digital twins offer individual āhealthcasts,ā accuracy and interpretability, and AI delivers speed and flexibility, each has limitations. Big AI combines their strengths, enabling faster, more reliable and individualised predictions, with applications from diagnostics to drug discovery. Above all, Big AI restores mechanistic insights to AI and complies with the scientific method.
---------------------------------------
Critical Care Medicine: Digital Twins to Evaluate the Risk of Ventilator-Induced Lung Injury During Airway Pressure Release Ventilation Compared With Pressure-Controlled Ventilation
William Joy et al
Abstract
Objective: To use digital twins constructed based on data from patients with acute respiratory distress syndrome (ARDS) to calculate all key indices of ventilator-induced lung injury (VILI) during airway pressure release ventilation (APRV), and to compare them with corresponding values obtained during pressure-controlled ventilation (PCV).
---------------------------------------
North American Spine Society Journal: Implant density reduction to avoid proximal junctional failure in adult spine surgery: Computer models and simulations
Morteza Rasouligandomani et al
Abstract
Proximal Junctional Failure (PJF) is a common complication in Adult Spine Deformity (ASD) surgeries, often leading to reoperations. While revision surgeries with osteotomies carry high complication rate of 34.8%, alternatives such as hardware proximal extension may increase PJF risk in patients with severe Global Alignment and Proportion (GAP) scores. Implant Density Reduction (IDR) has emerged to mitigate PJF risk. This study assessed the impact of IDR on PJF risk and explored sub-optimal strategies.
---------------------------------------
IOP- Physiological Measurement: Physics-informed neural networks for physiological signal processing and modeling: a narrative review
Anni Zhao et al
Abstract
Physics-informed neural networks (PINNs) represent a transformative approach to data models by incorporating known physical laws into neural network training, thereby improving model generalizability, reduce data dependency, and enhance interpretability. Like many other fields in engineering and science, the analysis of physiological signals has been influenced by PINNs in recent years. This manuscript provides a comprehensive overview of PINNs from various perspectives in the physiological signal analysis domain. After exploring the literature and screening the search results, more than 40 key studies in the related domain are selected and categorized based on both practically and theoretically significant perspectives, including input data types, applications, physics-informed models, and neural network architectures. While the advantages of PINNs in tackling forward and inverse problems in physiological signal contexts are highlighted, challenges such as noisy inputs, computational complexity, loss function types, and overall model configuration are discussed, providing insights into future research directions and improvements. This work can serve as a guiding resource for researchers exploring PINNs in biomedical and physiological signal processing, paving the way for more precise, data-efficient, and clinically relevant solutions.
---------------------------------------
Computer Methods in Applied Mechanics and Engineering: A multi-component, multi-physics computational model for solving coupled cardiac electromechanics and vascular haemodynamics
Sharp C.Y. Lo et al
Abstract
The circulatory system, comprising the heart and blood vessels, is vital for nutrient transport, waste removal, and homeostasis. Traditional computational models often treat cardiac electromechanics and blood flow dynamics separately, overlooking the integrated nature of the system. This paper presents an innovative approach that couples a 3D electromechanical model of the heart with a 3D fluid mechanics model of vascular blood flow. Using a file-based partitioned coupling scheme, these models run independently while sharing essential data through intermediate files. We validate this approach using solvers developed by separate research groups, each targeting disparate dynamical scales employing distinct discretisation schemes, and implemented in different programming languages. Numerical simulations using idealised and realistic anatomies show that the coupling scheme is reliable and requires minimal additional computation time relative to advancing individual time steps in the heart and blood flow models. Notably, the coupled model predicts muscle displacement and aortic wall shear stress differently than the standalone models, highlighting the importance of coupling between cardiac and vascular dynamics in cardiovascular simulations. Moreover, we demonstrate the modelās potential for medical applications by simulating the effects of myocardial scarring on downstream vascular flow. This study presents a paradigm case of how to build virtual human models and digital twins by productive collaboration between teams with complementary expertise.
---------------------------------------
American Journal of Physiology: Untangling the nets - a roadmap to standardized sampling and analysis of exhaled volatile organic compounds powered by in silico medicine
Robin Curnow et al
Abstract
Biomarkers based on volatile organic compounds (VOCs) measured in human breath have been investigated in a wide range of diseases. However, the excitement surrounding such biomarkers has not yet translated to the discovery of any that are ready for clinical implementation. A lack of standardisation in sampling and analysis has been identified as a key obstacle to the validation of potential biomarkers in in multi-centre studies.
Some progress towards standardisation has been made, but further progress is required to optimise sampling protocols and account for the confounding factors identified. This review highlights the important role that in silico (i.e. computational modelling) methods can play in addressing these gaps. Moreover, we discuss their potential for targeting and validating disease biomarkers by mechanistically linking them to the underlying metabolomic processes. We explore pertinent examples of mathematical, computational and machine learning models, that have proven useful in similar contexts, such as the development of fractional exhaled nitric oxide sampling standards. We then propose a roadmap outlining how existing and new modelling approaches can be applied to the problem of standardisation in breathomics research.
---------------------------------------
