The COVID-19 pandemic sent shockwaves throughout the U.S. healthcare system, and for many cancer centers the impact of the evolving crisis could be a double blow.
On the one hand, the number of patients who received care at U.S. cancer centers dipped during the pandemic, due to cancer centers and hospitals only seeing the most critical of patients and patients reluctant to risk exposure to the coronavirus. This drove a significant reduction in cancer screenings, 94 percent in 2020, according to a study published in the Journal of the National Medical Association.  One in five cancer survivors reported being less likely to enroll in clinical trials due to concerns about contracting COVID-19, according to a research letter in JAMA Oncology.
On the other hand, those trends are evolving as the pandemic evolves, with rising vaccination rates providing patients with confidence that they can safely return to healthcare settings. Many will be cancer patients who are receiving a diagnosis at a later stage of disease, due to pandemic-related delayed screenings. These patients are vested in immediately addressing their disease and may be willing to consider participating in a clinical trial of potentially new and novel, and/or personalized treatments. However, identifying a patient who meets the precise and complex criteria for a clinical trial can be painstaking, manual time-consuming work for many cancer centers. How will these clinics manage this challenge as a wave of patients emerges?
A smart, data-driven approach for matching patients to these complicated clinical trial protocols will be critical for cancer centers in the turbulent period that lies ahead. Yet, community cancer centers tasked with addressing the needs of their region’s patient population have limited budgets and resources. A data-based solution for patient matching must also have a sustainable cost.
What healthcare organizations need for matching patients to clinical trials are intuitive tools that can help them rapidly analyze database’s structured and unstructured data and extract the information they need, when they need it. Cutting-edge tools driven by artificial intelligence, machine learning, and other technologies can empower physicians and their staff to collect and transform patient data. As a result, patient matching is exponentially faster and more efficient.
For example, a biopharma sponsor requires a cancer center to fill out a lengthy document known as a feasibility survey questionnaire (FSQ) in order to demonstrate that the site will be able to enroll enough suitable patients to participate in a clinical trial of an experimental therapy. At present, it typically takes the clinical research staff at many cancer centers approximately three hours to fill out an FSQ.
But what if the clinical research staff could perform that task in minutes instead of hours? One cancer center historically completed 260 FSQs per year, on average, requiring about 780 hours of clinical research staffers’ time. After the cancer center deployed new technologies to harness their data and identify patients who met eligibility criteria for clinical trials, time spent completing FSQs decreased to five to 10 minutes per survey. We have seen healthcare teams shrink the time spent on this process from greater than 24 hours a week to just 30 minutes after implementing a smart AI-based software platform. The time saved freed up hundreds of hours that could instead be spent caring for cancer patients.
Even with a more efficient site feasibility process, on average, fewer than one in 20 cancer patients participate in clinical trials, according to the American Society of Clinical Oncology Educational Book.  A 2016 study in the Journal of the National Cancer Institute (JNCI) found that close to one in five cancer clinical trials are forced to close because they fail to enroll enough patients to be completed.  But that’s not because patients aren’t interested—a 2020 study in the JNCI found that 55 percent of cancer patients who are offered the opportunity agree to participate in clinical trials.
The problem of initiating and completing clinical trials due to low patient enrollment, which was magnified by the pandemic, creates a research bottleneck. This is a problem cancer centers can solve by using tools and knowledge to support accurately identifying candidates for clinical trials through highly precise analysis of patient databases including biomarkers. One cancer center implemented a software platform and worked with a dedicated clinical engagement specialist. Between March and June in 2020, the center enrolled 10 patients in clinical trials, a 233 percent increase over the previous four months. The center also identified three additional patients for further evaluation, which saved a trial already in progress.
Finally, these data-driven patient-matching strategies can offer community cancer centers that rely on patient reimbursement the assurance of a stable revenue stream, which can help provide a foundation for future growth and ever-improving patient care.
 Mitchell EP. Declines in Cancer Screening During COVID-19 Pandemic. J Natl Med Assoc. 2020 Dec;112(6):563-564. doi: 10.1016/j.jnma.2020.12.004. PMID: 33339569; PMCID: PMC7738274. [Article]
 Fleury ME, Farner AM, Unger JM. Association of the COVID-19 Outbreak With Patient Willingness to Enroll in Cancer Clinical Trials. JAMA Oncol. 2021 Jan 1;7(1):131-132. doi: 10.1001/jamaoncol.2020.5748. PMID: 33180102; PMCID: PMC7662493.[Article]
 Unger JM, Cook E, Tai E, Bleyer A. The Role of Clinical Trial Participation in Cancer Research: Barriers, Evidence, and Strategies. American Society of Clinical Oncology Educational Book 2016:36, 185-198 [Article]
 Bennette CS, Ramsey SD, McDermott CL, Carlson JJ, Basu A, Veenstra DL. Predicting Low Accrual in the National Cancer Institute’s Cooperative Group Clinical Trials. J Natl Cancer Inst. 2015 Dec 29;108(2):djv324. doi: 10.1093/jnci/djv324. PMID: 26714555; PMCID: PMC5964887.[Article]
 Unger JM, Hershman DL, Till C, Minasian LM, Osarogiagbon RU, Fleury ME, Vaidya R. “When Offered to Participate”: A Systematic Review and Meta-Analysis of Patient Agreement to Participate in Cancer Clinical Trials. J Natl Cancer Inst. 2021 Mar 1;113(3):244-257. doi: 10.1093/jnci/djaa155. PMID: 33022716; PMCID: PMC7936064.[Article]