Graph representation forecasting of patient’s medical conditions: towards a digital twin

Abstract

Objective: Modern medicine needs to shift from a wait and react, curative discipline to a preventative, interdisciplinary science aiming at providing personalised, systemic and precise treatment plans to patients. The aim of this work is to present how the integration of machine learning approaches with mechanistic computational modelling could yield a reliable infrastructure to run probabilistic simulations where the entire organism is considered as a whole. Methods: We propose a general framework that composes advanced AI approaches and integrates mathematical modelling in order to provide a panoramic view over current and future physiological conditions. The proposed architecture is based on a graph neural network (GNNs) forecasting clinically relevant endpoints (such as blood pressure) and a generative adversarial network (GANs) providing a proof of concept of transcriptomic integrability. Results: We show the results of the investigation of pathological effects of overexpression of ACE2 across different signalling pathways in multiple tissues on cardiovascular functions. We provide a proof of concept of integrating a large set of composable clinical models using molecular data to drive local and global clinical parameters and derive future trajectories representing the evolution of the physiological state of the patient. Significance: We argue that the graph representation of a computational patient has potential to solve important technological challenges in integrating multiscale computational modelling with AI. We believe that this work represents a step forward towards a healthcare digital twin.

Developments of digital twin technologies in industrial, smart city and healthcare sectors: a survey

“…Rodríguez-Aguilar [100] developed a digital twin model for the city's public health emergency system by integrating the city modeling and simulation. Karakra et al [101] proposed a digital twin model for their hospital system, including IoT, artificial intelligent algorithms, and cloud computing technologies.…”

“…According to the advantages of the DT technology, this framework could provide real-time monitoring of the patient status and protect the patient in time [101] . Barbiero et al [102] developed a DT model that combined machine learning algorithms, deep learning algorithms, and some physical models, which could offer a panoramic map and upcoming physiological situations.…”

GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks

“…Graph Neural Networks (GNNs) are a class of deep learning methods for reasoning about graphs (Bacciu et al, 2020). Their significance lies in incorporating both the feature information and structural information of a graph, which allows deriving new insights from a plethora of data (Ying et al, 2019;Lange & Perez, 2020;Barbiero et al, 2020;Xiong et al, 2021). Unfortunately, similar to other deep learning methods, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), GNNs have a notable drawback: the computations that lead to a prediction cannot be interpreted directly (Tjoa & Guan, 2015).…”