Every day, it seems, some new algorithm enables computers to diagnose a disease with unprecedented accuracy, renewing predictions that computers will soon replace doctors. What if computers could replace patients as well? If virtual humans could have replaced real people in some stages of a coronavirus vaccine trial, for instance, it could have sped development of a preventive tool and slowed down the pandemic. Similarly, potential vaccines that weren't likely to work could have been identified early, slashing trial costs and avoiding testing poor vaccine candidates on living volunteers. These are some of the benefits of “in silico medicine,” or the testing of drugs and treatments on virtual organs or body systems to predict how a real person will respond to the therapies. For the foreseeable future, real patients will be needed in late-stage studies, but in silico trials will make it possible to conduct quick and inexpensive first assessments of safety and efficacy, drastically reducing the number of live human subjects required for experimentation.

With virtual organs, the modeling begins by feeding anatomical data drawn from noninvasive high-resolution imaging of an individual's actual organ into a complex mathematical model of the mechanisms that govern that organ's function. Algorithms running on powerful computers resolve the resulting equations and unknowns, generating a virtual organ that looks and behaves like the real thing.

In silico clinical trials are already underway to an extent. The U.S. Food and Drug Administration, for instance, is using computer simulations in place of human trials for evaluating new mammography systems. The agency has also published guidance for designing trials of drugs and devices that include virtual patients.

Beyond speeding results and mitigating the risks of clinical trials, in silico medicine can be used in place of risky interventions that are required for diagnosing or planning treatment of certain medical conditions. For example, HeartFlow Analysis, a cloud-based service approved by the FDA, enables clinicians to identify coronary artery disease based on CT images of a patient's heart. The HeartFlow system uses these images to construct a fluid dynamic model of the blood running through the coronary blood vessels, thereby identifying abnormal conditions and their severity. Without this technology, doctors would need to perform an invasive angiogram to decide whether and how to intervene. Experimenting on digital models of individual patients can also help personalize therapy for any number of conditions and is already used in diabetes care.

The philosophy behind in silico medicine is not new. The ability to create and simulate the performance of an object under hundreds of operating conditions has been a cornerstone of engineering for decades, such as for designing electronic circuits, airplanes and buildings. Various hurdles remain to its widespread implementation in medical research and treatment.

First, the predictive power and reliability of this technology must be confirmed, and that will require several advances. Those include the generation of high-quality medical databases from a large, ethnically diverse patient base that has women as well as men; refinement of mathematical models to account for the many interacting processes in the body; and further modification of artificial-intelligence methods that were developed primarily for computer-based speech and image recognition and need to be extended to provide biological insights. The scientific community and industry partners are addressing these issues through initiatives such as the Living Heart Project by Dassault Systèmes, the Virtual Physiological Human Institute for Integrative Biomedical Research and Microsoft's Healthcare NExT.

In recent years the FDA and European regulators have approved some commercial uses of computer-based diagnostics, but meeting regulatory demands requires considerable time and money. Creating demand for these tools is challenging given the complexity of the health care ecosystem. In silico medicine must be able to deliver cost-effective value for patients, clinicians and health care organizations to accelerate their adoption of the technology.