How Leveraging Exponential Technologies Will Virtualize Clinical Trials

“Clinical trials are the most expensive part of developing a drug. And, it’s very hard to do a clinical trial testing the new drug’s interaction with every other drug that might be out there.”

William F Feehery, CEO of Certara
Image Credit:

Traditional clinical trials are equivalent to billions of dollars and years of hard work with no guarantee for the new drug to be approved by regulatory bodies, not to speak about the dangers of testing medication on animals or humans. According to CB Insights, on average, it costs $2.6B to research and develop a successful drug and takes 10+ years to come to market. It’s estimated that in-vivo testing (testing on animals and humans) accounts for more than 75% of the total cost, with recruitment alone being one of the most significant barriers to drug development — only 6% of clinical trials are ultimately completed on time.

Then there’s the issue of clinical effectiveness. According to the US Food and Drug Administration (FDA), medication ineffectiveness ranges from 38 to 75% for various illnesses ranging from depression to osteoporosis. The primary cause is each individual’s genetic makeup. It is so diverse and their interaction so unique that medicines designed for the “ideal patient” may not be appropriate for the “actual patient.”

Amid a global health crisis, the challenges only multiply: Covid-19 interrupted an estimated 80% of non-Covid-related clinical trials. One way to modernize the drug testing process is by applying technologies to the traditional framework, such as online platforms to seek out participants. An alternative method is to build an entirely new setting. That new setting leverages the multiplier effect of several exponential technologies to virtualize the clinical trial process.

If you’ve been following this blog, you know that I’ve written on several of the critical topics before in my “Straight Talk” series of posts. Here are the major ones:

For this post, I want to focus on two additional areas recently getting attention: digital twins and in-silico trials. These are generally lumped together. But for this review, I’ve chosen to keep them separate.

As part of the move to personalized medicine, researchers are interested in developing digital twins that could integrate known human physiology and immunology with an individual patient’s clinical data in real-time, then produce predictions of what would happen during various medical events. A digital twin is a virtual representation of a single person where every known medicine for that person’s illness can be tested. This will allow the best treatment to be determined. It can even monitor the virtual “person” and notify you if a medical condition develops as a side-effect enabling preventive actions. As a result, the digital twin has numerous applications across multiple therapeutic areas in healthcare.

It’s been reported that 66% of healthcare executives expect increasing investment in digital twins over the next three years. This is because digital twins improve healthcare organization performance, discover areas for improvements, provide customization and personalization of medicine and diagnosis, and enable the development of new medications and devices.

If we return to the list of exponential technologies above, digital twins use all of them to create a complete picture of an individual’s vitals, medical state, response to drugs, therapy, and the surrounding environment. Companies are creating digital twins to specifically look at chronic diseases like diabetes, where a chronic diabetes patient’s lifestyle, daily food habits, and blood sugar data are analyzed. The model notifies the patient about prescriptions, dietary habit modifications, medical consultations, and so on.

YouTube video credit: TEDx, Perth, Jacqueline Alderson

Another excellent example of the advancement of the field is the Oncosimulator project. The In Silico Oncology Group is developing an in silico experimental platform, as well as an advanced medical decision support tool called Oncosimulator, in collaboration with several research centers in Europe and Japan to optimize cancer treatment. The oncosimulator is an integrated software system simulating in vivo tumor response to therapeutics within a clinical trial environment. It aims to support clinical decision-making for individual patients.

YouTube video credit: VPH Institute

Several companies have created digital twin representations of human organs. For instance, Hewlett Packard Enterprise collaborated with Ecole Polytechnique Fédérale de Lausannes (EPFL) on the Blue Brain Project, using its supercomputer to develop digital models of the brain for scientific purposes. Siemens Healthineers offers a Digital Twin model, and Philips offers their own virtual heart. Dassault Systèmes launched its Living Heart Project in 2014 to crowdsource a virtual twin of the human heart. The project has evolved as an open-source collaboration among medical researchers, surgeons, medical device manufacturers, and drug companies. Meanwhile, the company’s Living Brain project is guiding epilepsy treatment and tracking the progression of neurodegenerative diseases. The company has organized similar efforts for lungs, knees, eyes, and other systems.

YouTube video credit: Dassault Systèmes

Although digital twins have a promising future in health care, the full impact of the technology will be determined by its capacity to integrate knowledge into accurate medical advice at scale. Better data, new interactions between patients and providers, and a regulatory framework to confirm these promises will be required to support this transformation.

In-silico trials simulate the effects of a new treatment using virtual populations to supplement or even partially replace in vivo testing. Researchers can use modeling and simulation to predict trial outcomes before advancing to real-world clinical trials and ultimately design studies that are more likely to succeed. Virtual populations can diversify the biological variability of traditional trials and enable the exploration of irregular phenotypes that would be difficult to recruit for. Control or placebo arms in trials can be simulated so that real-life patients who need treatment are guaranteed to receive it. This helps encourage potential subjects to enroll in the first place. Finally, in silico methods can lead to more exploratory research outcomes that might not be feasible with conventional trials. For instance, a recent in-silico trial looked at the same virtual population twice to see how the presence or absence of a secondary risk factor affected treatment.

“You can run an in-silico Phase II trial on 10,000 virtual subjects, rather than being limited to let’s say 10 or 20 or 50 real human subjects.”

YouTube video credit: WTF Health, Berlin, November, 2018

The technology is mainly early-stage, but it has recently seen increasing adoption from medical device and pharma players. Using statistical models of disease progression, researchers can better simulate clinical outcomes for a given cohort of patients, down to the level of how specific traits impact treatment. This could result in a hyper-personalized approach to assessing a patient’s fit for a given intervention.

In-silico technology, though, is not without its drawbacks. For one, using computer-generated patient populations relies on real-life, historical data for modeling, making it tricky to test for unexpected or novel side effects to treatments. Instead, in-silico trials might be more suited to test a treatment’s efficacy (i.e., to validate “expected” results). Soon, in-silico testing will primarily be used to augment or optimize traditional in-vivo testing rather than replace it altogether. Watch the regulators too. The U.S. Food and Drug Administration also picked up on the potential of in-silico trials, and it’s actively supporting the development of virtual models – for the testing of new medical devices. The FDA and the EUA in Europe are creating frameworks outlining best practices for collecting and analyzing data like digital evidence. And the FDA is already planning for a future in which more than half of all clinical trial data will come from computer simulations.

YouTube video credit: Novadiscovery, July, 2021

Big tech has a vital role to play here. In 2019, Verily, the health and life sciences company under Google parent company Alphabet, announced it was moving into the clinical trials space. Last month, Amazon Web Services announced a collaboration with Thread Research intended to decrease clinical trial costs while improving research access and data quality. And the Apple Watch has been used in a variety of studies, recent and current, both to investigate the efficacy of treatments (in areas where the watch’s efficacy has already been satisfactorily demonstrated), as well to further investigate the watch in other use cases. Watch for new partnerships with Google, Amazon, Apple, and others to gather and collect data to support in silico clinical trials.

After reviewing the current literature, I would sum up the benefits and drawbacks of virtual clinical trials like this:

  • Benefits
    • Larger number of trial subjects
    • Decreased costs
    • No consequences for either animals or humans
    • Better patient engagement
    • Can lead to more exploratory research outcomes
  • Drawbacks
    • Not compatible with all types of clinical trials
    • Access issues
    • Difficult to test for unexpected side effects
    • Credibility factor
    • EHR interoperability challenges

While completely simulated clinical trials are not feasible with current technology and understanding of biology, their development would be expected to have significant benefits over current in-vivo clinical trials. Under the right conditions, they could rapidly supplant traditional in-person approaches and dramatically enhance the scale, data collection, geographic range, cost-effectiveness, and speed of clinical trials. Certainly, decentralized clinical trials are here to stay. As we’ve seen in other areas of health care, the last 24 months have crystalized the potential of the virtualized research model, driving a rate of deployment and progress that might otherwise have taken 5-10 years to materialize.

Some Straight Talk on How Technology Will Impact Clinical Trials

“Tech solutions can bring the trial to the patient, and automation of the data collection/cleaning process. Both would cut down costs of generating clinical trial data considerably – which is the single biggest cost to drug manufacturers.”

Ruby Saharan, Senior Medical Advisor- RWE, Novartis Oncology UK and Ireland
Image Credit:

Clinical trials are incredibly costly and time-consuming endeavors. The average cost to conduct a Phase III trial is estimated at US$20 million, with a median of $41,117 per patient and $3,562 per patient visit. These expenses have reportedly risen by 100% in the last 11 years. With a push to lower the commercial price tags of new drugs – and find ways to get them to market sooner – pharmaceutical companies and regulatory bodies are increasingly more open to new clinical trial methodologies and tools. In parallel, during the current covid-19 pandemic, the pharmaceutical industry is further forced to shift away from traditional clinical trial modalities with a bricks-and-mortar approach – where patients must go to a clinical site for dosing and follow-up – to a more patient-centric approach where the trial comes to the patients in the form of digital enablement. In just a few months, 1,100 clinical trials were disrupted due to lockdown mandates, limited access to clinical sites, and people’s shift in priorities and comfort levels.

It is clear that the $52B clinical trials market needs a makeover. Startups and big tech are actively developing clinical trial solutions, from IoT for remote monitoring to machine learning for electronic health record (EHR) processing to AI-based cybersecurity for data protection. A new report from Research2Guidance (purchase required) discusses the rise in digital decentralized clinical trial (DDCT) technologies since the COVID-19 pandemic. The DDCT solution and service market in Europe and North America (NA) is $1.79 billion (€1.54 billion) and is predicted to grow by 38.5% (CAGR) to reach $9.13 billion (€7.84 billion) by 2026.

“I am impressed by the breadth of service offerings already available from DDCT companies. Solutions are innovating every step of the clinical trial process, from site selection to patient recruitment, and patient onboarding to long term data monitoring.”

Ralf Jahns, Managing Director, Research2Guidance

Now is the time for innovations in clinical trials to provide a patient-centric approach to driving patient engagement and capturing remote and accurate clinical data (including primary endpoints and patient-reported outcomes) and to drive down clinical trial costs. So how might technology innovation impact digital clinical trials? Here are some key areas to consider:

Finding a clinical trial – Matching the proper trial with the right patient is a time-consuming and challenging process for both the clinical study team and the patient. According to research by CB Insights, Roughly 80% of clinical trials fail to meet enrollment timelines, and around one-third of Phase III clinical studies are terminated because of enrollment difficulties. Patients may occasionally get trial recommendations from their doctors if the physician is aware of an ongoing trial. Otherwise, the onus of scouring through — a comprehensive federal database of past and ongoing clinical trials — often falls on the patient. Artificial intelligence and machine learning can help extract and analyze relevant information from a patient’s EHR records, compare eligibility criteria for ongoing trials, and recommend matching studies. The challenges in making this work include unstructured data and EHR interoperability.

Challenges with enrollment – Unfortunately, enrollment challenges do not end when a patient chooses a clinical trial. To confirm eligibility, the patient must complete a preliminary phone screen and then undergo examination by a participating site in person or virtually. Every trial includes inclusion and exclusion criteria that each patient must meet to participate. These terms are often riddled with medical jargon that is difficult for patients to decipher. Telehealth services could help streamline this process. If eligible, the patient signs a consent form agreeing to the terms of the clinical trial. This includes awareness of potential side effects, willingness to provide biological samples, and covering expenses not included within the study budget. Solutions using AI to extract information from patient medical records can help simplify the enrollment process by automatically verifying some of the inclusion and exclusion criteria.

Medication adherence – Once patients enroll in a study, they receive the experimental study drug (or placebo). Patients go home with the first course of the medication (for example, a 30-day pill bottle with instructions on dosage) and a diary to fill out daily. Many clinical studies still use paper diaries instead of electronic systems. Patients are asked to note when they took the study drug, what other medications were taken on those days, and any adverse reactions (including headache, stomach ache, or muscle aches). This process is plagued with inefficiencies, including reliance on the patient’s memory, use of paper documents and fax machines to communicate with physicians, risk of dropout. AI and wearables offer real-time, continuous monitoring of physiological and behavioral changes in patients, potentially reducing the cost, frequency, and difficulty of on-site check-ups.

What about clinical trials for rare diseases? – The FDA classifies more than 6,000 diseases as rare, which means that they affect less than 200,000 people in the United States. Only 5% of these diseases currently have FDA-approved treatments. The first challenge of rare disease trials is the most obvious: it’s hard to find patients. Around 3.5%-6% of people have a disease classified as “rare.” An even smaller percentage will have the specific disease that a clinical trial is attempting to study. Rare disease trials often need to recruit patients from around the world to meet their enrollment goals. But having sites in multiple countries participating means the trial must receive approval from multiple complex regulatory bodies. It also means sponsors must collect and monitor documents and data from many different sites, which involves complex privacy and data regulations and can slow down trials.

One recent example was the decision by the FDA which refused to review Stealth BioTherapeutics’ Barth syndrome drug, telling the company results in a study of just eight patients are insufficient to support its submission. The impasse highlights the challenges of testing drugs for ultra-rare diseases. Barth is so rare that Stealth is unsure it can recruit patients to run a new study

Technology can help rare disease trials increase recruitment rates, improve communication, speed up their workflows, and make the most of the funding they have. Patient recruitment software to identify eligible patients, as well as telemedicine and eConsent to manage remote patient visits, are excellent options for rare disease studies.

How big tech is supporting digital clinical trials – Big tech companies are leveraging their mobile devices to build platforms that span across the clinical trial process. Since 2015, Apple has been building a clinical study ecosystem around the iPhone and Apple Watch, both of which enable real-time health data collection. Its open-source frameworks — ResearchKit and CareKit — help clinical trials recruit patients and monitor their health remotely.

Google has been more active in the space. The company is building a clinical research ecosystem through its Google Health Studies Android application and developing products through its life science subsidiary, Verily Life Sciences. Verily launched Project Baseline in 2017 to fuel medical research by mapping human health. By mid-2019, Novartis, Sanofi, Otsuka, and Pfizer had partnered with Verily to use its tools for more efficient clinical trials. The initiative has also partnered with Stanford Medicine, the Duke University School of Medicine, and the American Heart Association. In April 2020, Google opened its Cloud Healthcare API to health systems and quickly signed on top medical centers such as Mayo Clinic. These actions follow Google’s 2018 pledge to support healthcare interoperability and data-sharing standards (also signed by Amazon, IBM, Microsoft, and Salesforce). And just this week, Google Care Studio has unveiled a new mobile version of its clinician-facing search tool that helps organize patients’ medical records. The company pitches this new modality as a way for doctors to check in on a patient or access patient information on the go. Currently, Google is in the process of acceptance testing with Ascension and Beth Israel. The company is looking to pilot the tool in Q4 with Ascension. Here’s a short video from Google describing Care Studio:

Another tech company that may enter the space is Facebook, which launched its Preventive Health tool in late 2019. Given the depth of personal data that Facebook captures and its self-organizing communities around health issues, this may be the first step toward a clinical trial recruitment solution.

What platforms are being developed to support digital clinical trials? – Needless to say, with all of the interest in developing digital clinical trials, there are dozens of companies looking to develop platforms to streamline the workflow across the entire process. The best summary of the current state of the market that I’ve found was reported by Andrea Coravos on her Medium blog. She did a superb job of collecting and summarizing the various market segments, as you can see in the graphic below:

Image Credit: Andrea Coravos, 2018 blog post

I love her segmentation model, and her most recent article in Health Affairs on how these digital clinical trials will affect patients’ lives is a must-read.

My take – Today’s potential participants tend to be digital consumers who demand convenience, personalized engagement, and active participation in clinical trials. They want to use digital tools to integrate trial protocols (like medication adherence and care) into their daily lives and not reshape their lives to accommodate the protocols. Each year, more clinical trials incorporate digital tools to monitor patients remotely. Harvard researchers reviewed every trial registered with between 2000 and 2017 and found the use of digital tools increased at a 34% compound annual growth rate. Across the study period, the number of registered clinical trials using these devices grew more than tenfold, from eight trials in 2000 to about 1,170 trials in both 2017 and 2018.

Studies have also shown that people are more willing to participate in mobile trials than traditional ones. In a recent survey on patient preferences for using mobile technologies in clinical trials, when given a choice in how to participate in a trial, 81% of respondents reported they were willing to participate in a mobile trial. In comparison, only 51% were willing to participate in a traditional trial.

Many challenges remain, and lessons will be learned as digital research is moved into the mainstream. Still, knowledge of the innumerable benefits to clinical research reinforces the view that now is the time to support digital methods with a focus on learning the most effective and efficient processes.