Digital Twins in Healthcare: 4 Things to Know
SUMMARY:
A data driven Digital Twin represents all processes and operations related to the real world physical twin.
The same disease will manifest and respond differently from one patient to another, therefore the Digital Twin will be personalized from genotype to phenotype and social determinants.
Although shown of benefit in various industries, the Digital Twin has had limited use in healthcare.
Current challenges are described.
BACKGROUND
One of the recent technology advancements is the development of the Digital Twin (DT) which creates a virtual representation of patients, spaces or processes.
·The goal is to provide a virtual digital model which can be used to develop and test care models in the virtual space. This will allow to test quicker, cheaper and with far less potential negative outcomes than in real life.
Despite the high level of interest in the potential value of DTs, their current use remains low, especially in healthcare.
Below are the 4 things to know about DTs.
REVIEW:
1. DTs consist of: 1) a real space; 2) a virtual space; 3 a digital thread allowing for flow of information
DTs can be used to simulate the results of individual therapeutic interventions as well as disease progression for a patient.
DTs also extend to medical devices and hospital operational systems.
DT data sources include:
EHRs
Registries
Genomics
Physical markers
Demographics
Social Determinants
Digital components (smartphones, wearables, implantable sensors)
There are 3 types of DTs:
Product twinning – To test if the physical product will perform exactly as planned
Process twinning – Testing process and workflow changes
System or Performance Twinning – Operational data analysis to optimize interactions of components within a system.
2. DT in Medical Decision Making:
DTs via precision medicine test approaches to improve/maximize disease treatment and prevention based on individual patient characteristics.
Unlimited copies of a patient’s DT can be constructed with computational integration of thousands of possible variables.
Each DT can follow a different treatment path.
The drug or treatment path with the best results can then be selected for the real patient treatment.
Current DT applications being explored include:
Heart
Brain
Respiratory
Multiple sclerosis
Viral infections
Trauma management
Diabetes
3. DTs in Hospital Management
DTs replicating hospitals or treatment facilities can help in understanding and optimizing business operations processes.
Can address areas such as:
Overcrowding
Waiting times
Delays
Supply chain
Predicting Resource shortages
Staffing
Cybersecurity
Strategies to improve communication and patient centered care can be tested via DTs to assess outcomes before real life adoption.
4. DTs Challenges
Technical limitations of data collection and data flow of digitally twinned sensors
Data security and privacy of interconnected devices
Socio-ethical issues:
Artificial Intelligence
The Internet of Things
Big Data
Robotics
Who owns the extracted data?
Can DTs adequately predict outcomes alone be sufficient for therapy selection or preventative care processes?
CONCLUSIONS:
Digital Twins hold great potential
Numerous barriers prevent Digital Twins from current use within the healthcare system.
Digital Twins should be used as decision support aids, but not to replace clinical decision making.
Subscribe to the monthly newsletter here: http://eepurl.com/gFJKYD