Digital twin computer models developed to help patients fight diseases
Image credit: Getty Images
Computer models that replicate a patient’s physiology, dubbed their 'digital twin', could be used to fight diseases and test out medications before being applied in real life.
Medication is typically ineffective with common diseases in 40-70 per cent of patients as they are seldom caused by a single, easily treatable fault. Instead, most diseases depend on altered interactions between thousands of genes in many different cell types.
An international research team based at Linkoping University in Sweden aims to solve this by constructing computational disease models of the altered gene interactions across many cell types.
The technology could be used to better tailor medicines to individual sufferers by testing thousands of drugs across different cell types on the computer version of the patient before actual treatment takes place.
“Our aim is to develop those models into ‘digital twins’ of individual patients’ diseases in order to tailor medication to each patient,” said Linköping University’s Dr Mikael Benson.
“Ideally, each twin will be computationally matched with and treated with thousands of drugs, before actually selecting the best drug to treat the patient.”
The team used a mouse model of human rheumatoid arthritis to build their first digital twin. They used a technique - single-cell RNA sequencing - to determine all gene activity in each of thousands of individual cells from the sick mouse joints.
In order to construct computer models of all the data, the researchers used network analysis.
“Networks can be used to describe and analyse most complex systems”, Benson said. “A simple example is a soccer team, in which the players are connected into a network based on their passes. The player that exchanges passes with most other players may be most important”.
After the most important cell type was found, it was matched digitally with thousands of medicines, meaning optimal drugs could then be used to treat and cure the mice. The study also showed it could be possible to use the computer models for diagnosis in humans.
By analysing T cells from patients with 13 diseases, including cancer, cardiovascular and autoimmune diseases, researchers found it was possible to distinguish most of the diseases from each other as well as patients from healthy people.
“Since T cells function as a sort of spy satellite, which is continuously surveying the body to discover and combat disease as early as possible, it may be possible to use this cell type for the early diagnosis of many different diseases,” said Prof. Benson.
The concept of digital twins is also becoming widely adopted outside of healthcare; planners are even building digital versions of buildings in order to model smart city growth. The island of Jersey is also positioning itself as a digital twin testbed for companies to use as a walled-garden testing environment for cutting-edge technologies, given the island's status as one of the most connected areas in the world.
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.