Synthetic Users in More Industries
Synthetic Users in Healthcare
by Sherry Jones (September 2025)
Synthetic users are transforming healthcare by simulating realistic patient interactions and medical scenarios. These virtual entities are increasingly applied in medical training, research, and for optimizing patient care pathways, offering a safe and efficient environment for innovation and skill development.
Patient Simulation and Training
In healthcare training, synthetic users take the form of simulated patients that allow clinicians to practice without endangering real people. These can be computer-based virtual patients or lifelike mannequin robots, each capable of presenting medical scenarios from routine check-ups to critical emergencies.
Unlike human actors, virtual patients don't mind experiencing severe complications or even "dying" during a scenario, enabling trainees to safely make mistakes and learn from them. High-fidelity patient mannequins allow teams to practice procedures using actual medical equipment in realistic clinical settings.
Stanford University
Uses immersive VR and computerized mannequins to recreate clinical cases for student training
U.S. Air Force
Partners with SimX for virtual reality training of aeromedical teams in challenging environments
Clinical Trial Modeling and In-Silico Trials
Synthetic users are transforming clinical research by enabling "in-silico trials" – virtual experiments conducted entirely on computer models. These digital trials use computational models and simulations to predict the safety and efficacy of new drugs and medical devices, significantly accelerating development timelines and reducing costs.
By simulating diverse patient populations and disease progressions, researchers can test numerous variables and scenarios that would be impractical or unethical in traditional human trials. This approach allows for faster iteration, identification of potential risks earlier, and more targeted development of therapies.
1
Accelerated Drug Development
Streamlining the discovery and testing phases to bring treatments to patients faster.
2
Reduced Costs
Minimizing expensive physical trials and associated logistical challenges.
3
Enhanced Safety
Identifying adverse effects and optimizing dosages in a risk-free virtual environment.
Clinical Trial Modeling and In-Silico Trials
Synthetic users are increasingly used to model trials on computers – often referred to as in-silico trials or synthetic control arms. Virtual patient data can substitute for some real participants, especially in control groups, making trials faster and less risky.
Reduced Risk
Decreases exposure of real patients to potentially ineffective or unsafe experimental treatments
Faster Trials
Shortens trial duration and speeds up regulatory approvals through synthetic control groups
Rare Diseases
Particularly valuable for studies where recruiting enough participants is difficult
FDA Approvals Using Synthetic Data
Regulatory agencies in the United States have begun accepting evidence from synthetic trial models, marking a significant shift in drug approval processes.
1
2017 - Cerliponase Alfa (Brineura)
FDA approved therapy for Batten disease based on single-arm trial of 22 children, compared against 42 untreated patients as synthetic historical control
2
Alectinib Expansion
FDA allowed expanded indication for lung cancer drug using external dataset of 67 patients instead of traditional control arm
Digital Twins for Personalized Medicine
Digital twins are detailed virtual models of individual patients that mirror real people using comprehensive data. Unlike static simulations, they dynamically integrate real-time information from electronic health records and wearable sensors.
This technology enables highly personalized diagnosis, treatment planning, and disease management by creating faithful replicas of patient anatomy and physiology.
01
Data Integration
Combines medical history, real-time vitals, and clinical guidelines
02
Virtual Testing
Tests different interventions on the twin to observe outcomes
03
Personalized Treatment
Recommends tailored therapy based on virtual results
Leading Digital Twin Innovations
Duke University
Researchers build patient-specific vascular twins to help surgeons practice procedures like stent placement before operating on actual patients
Unlearn.AI
Creates "digital twin" profiles of clinical trial participants that forecast patient outcomes on standard therapy, enabling smaller control groups
Mayo Clinic
Developing scenarios where digital clones run through medication regimens to identify optimal treatment plans for complex conditions
Unlearn.AI Presentation on AI Patient Digital Twins
This presentation, "Synthetic Users in Healthcare - Deep Dive Analysis," explains the problems facing healthcare and the need to use synthetic users or digital twins to forecast patient health outcomes and possible treatments, transforming the future of healthcare.
Synthetic Data for Healthcare Research
Beyond direct patient care, synthetic users prove valuable in healthcare research, public health, and system design. The MITRE Corporation developed Synthea, an open-source tool generating realistic patient populations with synthetic medical histories.
1
Privacy Protection
Work with realistic datasets without risking patient privacy or needing permissions
2
Machine Learning
Train AI models and validate EHR software using synthetic patient records
3
Public Health
Run pandemic simulations and explore intervention strategies safely
CDC Childhood Obesity Initiative
The U.S. Centers for Disease Control and Prevention adopted Synthea to support its Childhood Obesity Data Initiative. MITRE generated synthetic data reflecting children's growth and health profiles in specific regions.
Researchers ran simulations of various weight-loss program scenarios on virtual patients, from successful to unsuccessful outcomes. This provided a rich, risk-free dataset to identify promising strategies for later validation with real-world data.
100K+
Synthetic Patients
Generated for obesity research
50+
Intervention Scenarios
Tested virtually before real trials
Hospital Digital Twins
Healthcare organizations use synthetic modeling at the systems level to improve operations and patient experience. Hospital digital twins are virtual replicas of entire medical facilities that serve as safe environments to experiment with process changes.
1
Patient Flow Modeling
Mirror real patient and staff workflows to identify bottlenecks and optimize processes
2
Capacity Planning
Test how adding beds or redesigning units would impact waiting times and resource utilization
3
Surge Preparedness
Simulate emergency scenarios to improve hospital readiness and response capabilities
NVIDIA Digital Twins of Hospital Environments

NVIDIA explains that creating digital twins of hospital environments with synthetic data and users can help improve healthcare:
The Future of Synthetic Users in Healthcare
Major U.S. health systems like AdventHealth in Florida and Children's Mercy Hospital in Kansas City are using digital twin simulations to guide capacity planning and workflow optimizations. As data integration and AI models improve, this technology will become increasingly powerful.
Preventive Medicine
Early intervention through predictive modeling
Surgical Planning
Risk-free practice before real procedures
Chronic Disease
Personalized management strategies
Clinical Research
Accelerated drug development
Hospital Operations
Optimized patient care delivery
Synthetic users represent an expanding frontier in healthcare, extending from individual patient avatars to entire populations and institutions, driving innovation in a safe, cost-effective manner.
References
[1] [2] Stanford Medicine Center for Immersive and Simulation-based Learning. (n.d.). Simulation modalities available. Stanford University. https://med.stanford.edu/cisl/explore-simulation-based-education/simulation-modalities-available.html
[3] Wood, D. (2023, March 30). SimX, USAF partner on VR medical simulation training capability. Airforce Technology. https://www.airforce-technology.com/news/simx-usaf-vr-simulation-training/
[4] Pammi, M., et al. (2025). Digital twins, synthetic patient data, and in-silico trials: can they empower paediatric clinical trials? The Lancet Digital Health, 7(5), 367-371. https://pmc.ncbi.nlm.nih.gov/articles/PMC12171946/
[5] [6] Walonoski, J., et al. (2022). Introduction to synthetic control arm. PharmaSUG 2022 Proceedings. https://pharmasug.org/proceedings/2022/RW/PharmaSUG-2022-RW-192.pdf
[7] [8] Unlearn.AI. (2023). Digital twins in clinical trials: How they work, and how they don’t. Unlearn Blog. https://www.unlearn.ai/blog/digital-twins-in-clinical-trials-how-they-work-and-how-they-dont
[9] [10] [11] Randles, A. (2025, March 7). Digital Twins in Healthcare: Revolutionizing Patient Care at Duke. Center for Computational and Digital Health Innovation. https://comphealth.duke.edu/digital-twins-in-healthcare-revolutionizing-patient-care-at-duke/
[12] [13] Halamka, J., & Cerrato, P. (2024, December 23). Digital twin technology has potential to redefine patient care. Mayo Clinic Platform. https://www.mayoclinicplatform.org/2024/12/23/digital-twin-technology-has-potential-to-redefine-patient-care/
[14] [15] Randles, A. (2025, March 7). Digital Twins in Healthcare: Revolutionizing Patient Care at Duke. Center for Computational and Digital Health Innovation. https://comphealth.duke.edu/digital-twins-in-healthcare-revolutionizing-patient-care-at-duke/
[16] [17] [18] [19] [20] [21] [22] MITRE Corporation. (2020, May 22). For patient data, Synthea is the "missing piece" in health IT. MITRE News & Insights. https://www.mitre.org/news-insights/impact-story/patient-data-synthea-missing-piece-health-it
[23] NHS Gloucestershire Health and Care (n.d.). Hospital Digital Twin to Improve Operations and Enhance Patient Experience. AnyLogic Simulation Software. https://www.anylogic.com/resources/case-studies/hospital-digital-twin-to-improve-operations-and-enhance-patient-experience/
[24] [25] (2025). Capacity strategy with a Digital Twin. GE HealthCare. https://www.gehccommandcenter.com/digital-twin
[26] Halamka, J., & Cerrato, P. (2024, December 23). Digital twin technology has potential to redefine patient care. Mayo Clinic Platform. https://www.mayoclinicplatform.org/2024/12/23/digital-twin-technology-has-potential-to-redefine-patient-care/
[27]Pammi, M., et al. (2025). Digital twins, synthetic patient data, and in-silico trials: can they empower paediatric clinical trials? The Lancet Digital Health, 7(5), 367-371. https://pmc.ncbi.nlm.nih.gov/articles/PMC12171946/