Digital Twin Generators for Disease Modeling

TL;DR

This paper introduces Digital Twin Generators, a neural network architecture that can create personalized digital twins for patients across multiple medical indications, potentially transforming personalized medicine and clinical trial efficiency.

Contribution

The paper presents a versatile neural network architecture capable of generating accurate digital twins for various diseases by adjusting training data and hyperparameters.

Findings

Effective digital twin generation across 13 indications

Scalable neural network architecture for personalized health modeling

Potential to create digital twins for any patient worldwide

Abstract

A patient's digital twin is a computational model that describes the evolution of their health over time. Digital twins have the potential to revolutionize medicine by enabling individual-level computer simulations of human health, which can be used to conduct more efficient clinical trials or to recommend personalized treatment options. Due to the overwhelming complexity of human biology, machine learning approaches that leverage large datasets of historical patients' longitudinal health records to generate patients' digital twins are more tractable than potential mechanistic models. In this manuscript, we describe a neural network architecture that can learn conditional generative models of clinical trajectories, which we call Digital Twin Generators (DTGs), that can create digital twins of individual patients. We show that the same neural network architecture can be trained to generate accurate digital twins for patients across 13 different indications simply by changing the training set and tuning hyperparameters. By introducing a general purpose architecture, we aim to unlock the ability to scale machine learning approaches to larger datasets and across more indications so that a digital twin could be created for any patient in the world.