Kamya Elawadhi is Chief Client Officer at Doceree.
Clinical trials are an essential part of medical breakthroughs that help patients, but getting them off the ground and running them is often fraught with challenges. Specifically, qualification, activation, compliance and data monitoring and analysis can be complex, resource-intensive, time-consuming and expensive for pharmaceutical researchers.
Consider this: Many clinical trials aren’t able to even move past the recruitment and enrollment stage. According to Deloitte, a “study on the benefits of virtual randomized clinical trials shows that more than 80% of in-person studies are delayed because of insufficient patient recruitment, while 80% of research sites fail to meet enrollment goals.” Once past the initial stage, other problems can arise. As noted in Nature Reviews Drug Discovery, one report assessed 7,455 drug development programs that went “through the clinic between 2006 and 2015.” The researchers “found that the probability of success was 63% in Phase I trials, 31% in Phase II trials, 58% in Phase III trials and 85% during the regulatory review process, for an overall success rate of 9.6%.”
However, pharmaceutical companies can leverage AI to overcome challenges and streamline the clinical trial landscape.
Ways AI Can Help Pharmaceutical Companies Address Common Challenges With Clinical Trials
There are several key ways AI can help pharmaceutical companies address common challenges associated with clinical trials.
For one, AI can be used to improve patient recruitment. When patients have doctor’s visits, physicians capture critical data, such as concerns discussed and any medications that were prescribed, via electronic health records (EHRs). Currently, pharmaceutical researchers depend on physicians to pinpoint who might qualify for a clinical trial. In the hectic day-to-day of providing patient care, physicians may not remember which patients qualify and which don’t. That’s where AI can step in. AI can sift through structured and unstructured EHR data, such as diagnoses, lab results, prescriptions and physicians’ notes, to match patients with trial criteria more efficiently than physicians having to rely on memory alone.
From there, AI can be used to activate patient engagement. Through an app or an EHR system, physicians can receive notes that particular patients qualify or are strong candidates for given clinical trials—and can also get guidance on the details they need to share with patients, such as the purpose of the trial and next steps for getting involved (if the patient expresses interest in doing so).
Once patients enroll, researchers can use AI to monitor compliance and analyze feedback during trials. For instance, if patients have to take a medication twice a day, they can get push notifications on their phones, reminding them when it’s time to take their medication and instructing them to indicate when they’ve finished taking the medication. AI can keep track of which patients have completed the task and which haven’t—and then message them appropriately. Additionally, patients can input their feedback, such as their adverse side effects, into an app or system. AI can then analyze that feedback, uncovering common threads and outliers to present to researchers. Researchers won’t have to spend hours combing through the data themselves. Instead, they can gain a quick understanding of the risks and benefits of their drugs and adjust accordingly.
The Risks Of Using AI In Clinical Trials
AI can streamline clinical trials, but it’s not without risks. AI should be used as an assistive tool for clinical trials, not a replacement for human expertise and judgment.
While AI tools offer value, they aren’t infallible. Human oversight is crucial. Researchers and physicians should proactively review the recommendations that AI tools make. For example, an AI tool might indicate that a patient is a good fit for a clinical trial, but a physician might decide that, say, based on a contraindication, they shouldn’t participate in the trial.
Additionally, compliance with HIPAA and other privacy regulations is imperative. Pharmaceutical companies must thoroughly evaluate prospective AI vendors and review their data policies to ensure compliance
The Benefits Of A Crawl, Walk, Run Approach In AI Implementation
Leaders of pharmaceutical companies who are considering implementing AI for clinical trials should consider a crawl, walk, run approach—starting with specific use cases in their clinical trials, rather than fully overhauling their approaches at once.
Rolling out AI for clinical trials is a major organizational change. And given the stakes in clinical trials, pharmaceutical leaders should be extra cautious. By implementing AI in stages, pharmaceutical leaders can pace themselves and their teams, get a stronger sense of what is effective for patients and adjust as needed.
By streamlining clinical trials, particularly the clinical matching process, pharmaceutical companies can save time and money—and allocate that time and money to research and development. Ultimately, using AI in clinical trials can help drugs get launched sooner, helping more patients.
Forbes Business Council is the foremost growth and networking organization for business owners and leaders. Do I qualify?
Read the full article here
