A new brief by CB Insights focuses on AI and its potential to transform clinical trials. A makeover of the $65 billion clinical trials market is well overdue. As noted in the brief, 1.7 million people in the U.S. will be newly diagnosed with cancer this year. In 2018, pharma companies will attempt to recruit thousands of patients for the 10,000 trials hoping to test new life-saving cancer drugs. Sadly, only 5 percent of cancer patients will end up taking part in a trial.
Part of the reason for this low enrollment rate has to do with terminal patients enrolling only in a trial once existing treatments have failed. Today, many patients are also finding it more difficult to even be eligible for a trial and the time and cost of participating in a trial creates difficulties for patients. The combination of these factors results in an industry in dire need of a makeover.
Is AI The Magic Bullet?
With all of the issues that seem to be preventing more efficient trials, will AI be the technology that finally streamlines the process? CB Insights notes AI is being touted as the “magic bullet” for just about everything. In the clinical space, we have the Internet of Things (IoT) for remote monitoring, machine learning for EHR processing, and AI-based cybersecurity for data protection. But that just scratches the surface. AI has the potential to impact every stage of a clinical trial.
The first of many challenges patients face is actually finding a clinical trial. Research has shown 80 percent of trials fail to meet enrollment timelines and one-third of Phase 3 trial terminations are due to enrollment challenges. At any given time, there could be as many as 18,000 trials recruiting patients. Patients rarely get trial recommendations from their physicians, and navigating the government website, ClinicalTrials.gov, can be difficult. These recruitment delays are costly to pharma. According to ISR Reports, when a trial goes beyond its intended deadline, sponsors can lose millions of dollars in sales.
Here AI can help both sponsor companies and patients by extracting pertinent information from medical records and comparing it to the requirements of ongoing trials. Studies matching conditions could then be recommended to patients. Right now, one of the greatest impediments is the ability to share health information easily across institutions and systems. This will continue to be a problem for AI systems.
Even when a patient locates a trial, inclusion and exclusion criteria can prevent them from enrolling in it. Tests needed to determine if a patient is a fit for a trial can require multiple visits to a clinic and take weeks. AI could assist in this process by extracting information from medical records that could verify the inclusion and exclusion criteria. Patient-generated data, such as that gathered by the Apple Watch, could also simplify the process. Apple is already partnering with institutions and researchers to identify patients.
Adhere To Medications
Once a patient is admitted to a trial, they need to adhere to the medication regimen. Information on a patient’s drug usage is generally maintained in paper diaries, which can be inaccurate due to human error and is also inefficient. Travel to the clinic, as well as out-of-pocket costs, increases the likelihood of patients dropping out of a study.
This is another area where technology can help. Mobile technologies remind patients to take their medicines. Ingestible sensors and wireless pill bottles are also being used to track drug intake. AI can go a step further to track adherence using visual confirmation.
Facial recognition technology is available that allows patients to use their phones to record videos of themselves taking medications. A healthcare companion and coach that uses AI is being developed to tailor conversations to patients, set reminders, and ask questions. The robot assistant will use a touchscreen or voice activation feature to communicate with patients.
Technology will clearly be a necessary component to streamline trials. But this presents another challenge: The needed technologies are relatively new, and pharma has always been slow to adopt new solutions. This is another area where Apple can play a large role. The company has been successful at bringing healthcare partners onboard, and it is already addressing information bottlenecks in the industry. Apple is also building a clinical research ecosystem around the iPhone and Apple Watch. AI requires data, and Apple can provide medical researchers with patient data that has not been available in the past.
ResearchKit and CareKit are open source frameworks available from Apple that help patients in clinical trials monitor their health remotely. The frameworks also allow researchers and developers to create apps that monitor the daily lives of patients. Researchers at Duke University have already developed an app that uses an iPhone to screen children for autism. The mPower app uses exercises like finger tapping to study patients with autism.
Apple may also provide a solution to the EHR challenge. The company’s Health Records API will allow patients to access electronic health records on their iPhone’s Health app. Apple is also working with EHR vendors Cerner and Epic to solve the previously mentioned interoperability issues.
Where Do We Go From Here?
So what does all of this mean to companies conducting clinical trials? First, CB Insights states Apple is now at the center of a new healthcare data ecosystem. The company is offering daily data that was unavailable in the past while also gathering difficult-to-consolidate EHR information. With this data, there are endless possibilities when it comes to using AI for early diagnosis. This will simplify the patient recruitment process while enabling remote monitoring to facilitate better patient retention.
Second, the industry should not overlook Google. Google’s Project Baseline could also benefit companies performing clinical trials. Project Baseline is currently attempting to enroll 10,000 patients and monitor their daily lives over the next five years. This type of patient-generated data could eliminate the need for a control (placebo) group in future clinical trials. This will help reduce recruitment bottlenecks.
Still, AI alone will not solve all of the challenges that exist with clinical trials. AI adoption is still in its early stages. In many aspects of clinical trials, CB Insights states there is a need for digitization that precedes the need for AI. Paper diaries and other handwritten notes will need to be eliminated before the benefits of AI can be realized.
Pharma will also have to understand exactly what AI can do and what its limitations will be. The first step will be to stop thinking about a futuristic state where AI eliminates all trial problems, and instead focus on achievable, short-term goals that make it easier for patients to participate in trials.