COVID-19 a ‘catalyst’ for innovation in 2020: Oracle

By Jenni Spinner

- Last updated on GMT

(ipopba/iStock via Getty Images Plus)
(ipopba/iStock via Getty Images Plus)

Related tags COVID-19 Innovation Clinical trials Oracle Artificial intelligence

A leader from Oracle Health Sciences examines the dynamic, challenging year and highlights creativity and ingenuity displayed by research professionals.

While 2020 heaped a significant number of challenges and obstacles on the clinical research industry (especially regarding the COVID-19 pandemic), professionals showed a willingness to pivot in several ways to keep their important work going forward. Outsourcing-Pharma (OSP) recently discussed the dramatic shifts and developments in research over the past 12 months with Henry McNamara (HM), senior vice president and general manager of Oracle Health Sciences. 

OSP: Could you please provide a brief summary of your perspective on 2020? What were the high points, low points, lessons learned, etc.?

HM: For clinical trial professionals, 2020 was an incredibly challenging year, in large part because of the COVID-19 pandemic’s profound effects on the entire industry. The pandemic created the need for vastly accelerated trials for COVID vaccines and therapies, while at the same time leading to delays or even deferrals of trials in many other areas.

As companies have scrambled to adapt to this environment, they have turned to technology to support and streamline trials. Technologies in areas from telemedicine to artificial intelligence (AI) that had been considered experimental, or deployed only as pilot projects, moved rapidly into standard trial practice. CROs and sponsors adopted integrated systems and cloud-based technologies in an effort to reduce manual and duplicative effort, streamline activities, and improve efficiency.

While there were many low points in 2020 as a result of the global pandemic, one of the high points was watching the industry come together in an effort to keep clinical research moving forward. The pandemic provided a catalyst for new ways of working. It moved players to embrace, use, test, and implement many new ideas, approaches, and technology in clinical trials.

While some new approaches and technologies will become mainstream more rapidly than others, there will be permanent changes because of the experience of the past 12 months.

OSP: Can you please share how sponsors and CROs who have either not adopted decentralized trials and remote monitoring, or who have just dipped their toe in the waters, can set themselves up for success in this brave new world?

HM: To support the move to decentralized clinical trials, and the variety and volume of patient data that is going to come with it, you really need a single platform where the data can be collected, harmonized and analyzed quickly and efficiently. In clinical trials, data is everything.

In a survey we conducted​ late last year, 50% of respondents indicated that data quality was a top challenge in adopting decentralized clinical trial methods and their primary concern when it comes to remote data collection.

In the past, sponsors and CROs may have used point solutions designed to improve specific processes in clinical trials, such as data capture and drug randomization and supplies management, but these systems weren’t built to work together, so a lot of process redundancy and data quality issues have been introduced. Add to that the complexity of data streaming in from remote devices and patient apps, you can understand the concern. This is why we built Oracle Health Sciences Clinical One Platform, which is the only truly unified platform that can offer a streamlined, harmonized view of data.

So, for those who are just beginning to adopt decentralized clinical trial methods, it is important to think about the scope and flow of data that will be coming in as a result, and make sure your eClinical environment is set up to handle it.

OSP: Regarding mHealth devices: can you share tools and best practices that can help operations make better use of such technologies?

HM: The industry is becoming more and more focused on the patient, which is great. Study teams are thinking about how to make it easier for patients to participate in clinical research, and also how to make participation less disruptive and burdensome in patients’ lives. The adoption of mHealth devices is a great way to do this – potentially reducing the number of in-person visits a patient has to make to the site, while also providing study teams with richer data sets that provide a deeper, or more complete, picture of the patient.

In adopting mHealth technology, study teams need to think about the impact to people, process and technology. How will the introduction of the wearable, device, or app change the protocol? How will it change the data sets? How will it change the requirements of your underlying eClinical systems?

As it relates to the last question concerning eClinical technology, study teams will want to ensure the data collected from these mHealth devices is organized, digestible, and trustworthy. To do this, you need to have a “digital gateway” that easily allows a wide variety of data sources to be connected into a clinical trial ecosystem, where it can be monitored, aggregated, and analyzed.

You also need a platform that serves as a “single source of truth” for all the data. At Oracle Health Sciences, we provide this to our customers with Clinical One Platform.

OSP: What are some of the obstacles to upping study automation?

HM: Whether it’s the increased volume and variety of data coming in from wearables, sensors, and other sources used in decentralized clinical trials, or the increased volume of safety cases received by pharmacovigilance teams, the burden of data management and analysis is becoming a more urgent problem. The amount of data is far more information than humans can process or manage, and outsourcing or throwing more people at the problem is no longer sustainable or effective. Not only is there more data, but it is also much more complex.

Luckily, great advances have been made in AI and machine learning (ML), which can be applied to automate many data-heavy processes to lessen the pressure. AI and ML not only process data faster than humans, they can point to patterns and trends that humans can’t see and will ideally lead to a more accurate and detailed view of how patients are responding in trials, which can lead to better treatments in the long run.

OSP: How exactly can automation help ease the burden on trial teams, and otherwise improve results/efficiency?

OSP_OraclePredictions_HM
Henry McNamara, senior VP and general manager, Oracle Health Sciences

HM: The scale and speed at which trials – especially the COVID vaccine trials – where conducted was shocking to everyone. Given the pace, the long hours and emotional toll on the professionals involved, numbers of patients, the volume of data being generated, and the speed of the analysis, it’s unsustainable to think the speed and style in which these trials were run will become the new norm, so it’s likely companies will continue to implement technology that streamlines repetitive processes, automates trial design, and reduces the routine workload on professionals, so they can focus on high-value problems.

Specific areas where automation using AI is already having a massive positive impact is around study startup and safety case intake. At Oracle, we are using ML to aid clinical operations teams in the proactive planning of clinical trials by guiding milestone planning and study scenario planning.

Leveraging historical cycle times, the ML can automatically generate study startup milestones (in accordance to therapeutic area, countries, number of sites for study, etc.) and automate critical path management once in the study. This helps our customers expedite efficient timelines and optimal resource allocation.

In pharmacovigilance, many adverse event (AE) reports, whether they’re forms, emails, articles, or other source documents, do not arrive in E2B format, which means they have to be entered manually into safety systems. This manual data entry can take hours and represents a significant cost to the organization.

Our Oracle Health Sciences Safety One Intake Cloud Service product uses deep learning, natural language processing, and image processing algorithms to turn safety source documents—both structured and unstructured—into E2B files for easy ingestion into any safety case management system.

OSP: AI may sound like a next-generation technology to less-savvy trial professionals, rather than tech that’s already hard at work. What advice would you give research sites and sponsors who are looking to dive in?

HM: AI and ML are already being incorporated into advanced, cloud-based life sciences technology platforms to support trial design, data monitoring, and safety case management. But this is only the beginning. Machine learning technologies can help predict outcomes in clinical trials, leading to faster drug approval times, lower costs, and more funding to develop new treatments.

More accurate predictions can reduce the uncertainty in study execution by providing greater risk transparency and allowing informed data-driven decisions to be made in the risk assessment and portfolio management of investigational drugs in clinical trials.

Five years from now, a patient’s clinical trial experience could be very different. Wearables combined with cloud technologies will enable continuous and instantaneous data collection and advanced analytics that is fed back to the study teams developing new treatments. Each enrolled patient could be creating millions of data points a week—or even per day!

That could mean more accurate assessments as the data will reflect the patient’s everyday experiences. Digital biomarkers also hold great promise for the scientific community to inform disease characteristic and increase clinical trial objectivity.

For those looking to dive in, I would suggest evaluating your existing clinical trial and safety processes to identify those where there is heavy manual data management and analysis. Such processes are ripe for AI and ML.

OSP: How have regulatory attitudes toward decentralized and hybrid trials shifted in recent years?

HM: Regulators are moving faster than ever to respond to the new demands of decentralized trials created by the pandemic, while still working through difficult issues in areas like patient privacy; however, the industry want more clarity, and they want it now.

A recent Oracle survey of clinical trial professionals showed that half the respondents said that “regulatory issues are holding them back” from developing trials that have more virtual elements. Respondents were also divided regarding the clarity of current regulatory guidance surrounding decentralized trials and data collection, indicating a need for improvement.

Additionally, the vast majority of survey respondents (89%) report experiencing some difficulty complying with new guidance around decentralized clinical trial methods, most commonly maintaining the quality and integrity of the study (40%), and training, monitoring, and ensuring compliance with regard to new data collection methods (39%).

While the industry feels bogged down now, a combination of industry lobbying efforts in conjunction with the entry of more technology-focused biotech and startup companies into the mix, will help to change that moving forward.

OSP: What guidance and resource can regulatory bodies like the FDA and EMA offer trial teams, regarding introduction and operation of decentralized trials?

HM: The real change will happen as the entire ecosystem reaches a consensus on how the industry will move ahead. If more players begin to adopt a decentralized trial approach, we will see regulatory bodies step up their guidance as a result of this change.

OSP: Do you have anything else to add about the year ahead?

HM: While the industry was already shifting to adopt decentralized clinical trial methods, the pandemic has accelerated those efforts. The lockdowns of the COVID-19 pandemic had a major impact on clinical trials in 2020, leading to rapid adoption of telemedicine and decentralized trial methods.

This will continue in 2021. The industry is not going back to “the old way.” Therefore, sponsors and CROs need to set themselves up to operate successfully in this new model.

Luckily, the technology and software to support decentralized clinical trials – the devices, the data, and the technology – exists today, and are designed to carry the industry into the future of clinical trials. As approaches to clinical trials continue to evolve, study teams can rest assured that technology will not slow them down.

Related news

Show more

Related products

show more

More Data, More Insights, More Progress

More Data, More Insights, More Progress

Content provided by Saama | 04-Mar-2024 | Case Study

The sponsor’s clinical development team needed a flexible solution to quickly visualize patient and site data in a single location

Using Define-XML to build more efficient studies

Using Define-XML to build more efficient studies

Content provided by Formedix | 14-Nov-2023 | White Paper

It is commonly thought that Define-XML is simply a dataset descriptor: a way to document what datasets look like, including the names and labels of datasets...

Related suppliers

Follow us

Products

View more

Webinars