A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients

Abstract

Background: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two or more diagnostic categories. Digital twin models, which forecast entire trajectories of patient health data, have potential applications in clinical trials and patient management. Methods: In this study, we apply a digital twin model based on a variational autoencoder to a population of patients who went on to experience an ischemic stroke. The digital twin’s ability to model patient clinical features was assessed with regard to its ability to forecast clinical measurement trajectories leading up to the onset of the acute medical event and beyond using International Classification of Diseases (ICD) codes for ischemic stroke and lab values as inputs. Results: The simulated patient trajectories were virtually indistinguishable from real patient data, with similar feature means, standard deviations, inter-feature correlations, and covariance structures on a withheld test set. A logistic regression adversary model was unable to distinguish between the real and simulated data area under the receiver operating characteristic (ROC) curve (AUCadversary = 0.51). Conclusion: Through accurate projection of patient trajectories, this model may help inform clinical decision making or provide virtual control arms for efficient clinical trials.

Personal Digital Twin: A Close Look into the Present and a Step towards the Future of Personalised Healthcare Industry

“…Pairing AI with DT technologies creates new efficiencies for smart healthcare industries. For example, applying predictive data analytic techniques (e.g., ML and DL) using data-driven DTs provides predictions of the disease progression in near real time [ 41 , 42 ]. These predictions are used as biomarkers to support early clinical decision making and propose patient-specific therapy using existing drugs.…”

Supporting of manufacturer’s demand plans as an element of logistics coordination in the distribution network

“…The use of cloud technology to support the operation of regular WMS, the use of standardisation to increase the transparency of flows (and their accompanying data) and the use of EDI have a positive impact on the verifiability of forecasts. The positive aspect associated with the use of modern technology as a support for forecasting is sometimes exposed in the literature, where we can already find concepts related to, for example, the use of a developed form of Digital Twins as a support for forecasting (Allen et al, 2021;Xie et al, 2019). Examining the possibility of implementing Digital Twins into the structures of distribution network operations as support offered to the manufacturer by the logistics service provider seems an interesting field for further research.…”

Future directions in regulatory affairs

“…Another use of digital twins is modeling disease progression, and this will lead to digital twin control groups in clinical trials, reducing ethical and operational concerns with control cohorts (30)(31)(32). As the number of digital twins of individuals increase, there will be a greater ability to predict medicine effects before administering any medication to the patient.…”