For community cancer centers that rely on patient reimbursement to stay afloat, a smart data-driven approach to clinical trials provides a foundation for future growth.

By TANDY TIPPS and BRENDA NOGGY

Covid-19’s tragic, devastating impact on cancer treatment is now well documented. Cancer screenings dropped by almost 90 percent at the peak of the pandemic. Billing for some leading cancer medications dropped 30 percent last summer. Studies found a 60 percent decrease in new clinical trials for cancer drugs and biological therapies.

Cancer centers, like every part of the US health system, have a lot of ground to make up. Those community cancer centers without grants and other institutional advancement funds, experience financial and human resources as major constraints to charting a path to growth. For them, successful programs which generate revenues for expansion or break even help them maintain fiscal health. Often, unfortunately, too often their research programs lose money.

Clinical trials have not been a viable revenue source because of the difficulty in accurately predicting patient enrollment and the challenges of managing trial portfolios, a task that requires streamlined feasibility processes that include querying baseline populations for new trials and potentially eligible patients.

The hard work of patient screening and trial matching requires clinical coordinators, physician investigators and research support staff to spend between three to eight manually scouring databases of electronic medical records and unstructured files to find patients eligible for trials based on increasingly complex inclusion and exclusion criteria. This costly process does not take into consideration the pre-screening efforts in patient matching that may not be reimbursable.

Resources are also needed to implement feasibility processes to accurately predict how many patients might enroll in a trial if they are eligible. Most community-based sites do not have an accurate ability to query their current patient populations by disease cohort or mutation in real time. They often rely on physicians’ memories to estimate patient numbers for trial feasibility questionnaires, which must returned to sponsors quickly, usually before cancer centers have definitive recruitment numbers.

As a result, before COVID, an average of only 5 percent of patients had a chance of participating in trials, 50 percent of clinical trials failed to meet enrollment goals and less than 14 percent were completed on time. Cancer centers still incur the administrative and clinical resources required to maintain the protocols in the first place, however.

These false starts impact forecasting for future program budgets. Trial startup costs and per research patient accrual reimbursements are program revenues, after all.

Cancer centers today have a new way to address these challenges, however. They can leverage a new technology – a patient matching tool – to create more efficient and effective screening methods that will save research teams time and effort and help predict future revenue streams.

Including natural language parsers, optical character recognition and machine learning, these AI-related technologies match a proposed trial against cancer center patient populations to determine, with the oversight of center nurses, doctors and staff, whether it might successfully recruit patients quickly and efficiently.

The benefits of this technology to match patients to trials using cancer centers’ preexisting clinically relevant data are clear. Clinical trial patients generate research costs covered by federal grants or industry sponsors.

They also generate downstream revenues related to the standard of care procedures that patients receive regardless of their participation in a trial, usually through private insurance or Medicare.

Cancer centers can designate a dedicated area in the trial infusion unit with phlebotomy and dedicated research infusion nurses, potentially adding income to cover the cost of a service, especially for trials requiring one-to-one clinical nursing support, for instance.

Lastly but certainly not least, the technology can also help oncologists see the gaps in their treatment and find cutting edge trials that will truly help patients, especially the ones without standard of care treatment options, and provide opportunities for publishable research.

At the top administrative levels of hospitals and cancer centers, the upcoming post-Covid reset provides a chance for CFOs to challenge old assumptions about clinical trials, explore the latest patient matching solutions and reconsider the cost-benefit analysis – on both financial and patient outcomes.

At the clinical level, if AI-related technologies can help match real people to the unique needs of trials, doctors, nurses and others can spend more time connecting one-to-one with potential trial participants, reaffirming the human connections that can be drowned out by paperwork and data input.

Lastly, at the public health level, local cancer centers engaging in clinical trials can help address systemic inequities in who gets access to emerging treatments, including the geographic and racial barriers that the Covid-19 pandemic has highlighted.

There are many cancer centers that exist today that did not 10 years ago. That has helped the US make major gains in cancer care. During the same period, we have seen revolutionary advances in cancer drugs and therapeutics. But there is a research bottleneck, however.

The research bottleneck is, at its core, a data bottleneck. The widespread adoption of electronic medical records means we have more information about patients than ever, and the depth of this knowledge is increasing with every parallel advance in medical imaging and patient monitoring. Yet substantial portions of data exists as unstructured data.

What clinical providers require now are intuitive tools that can help them instantly extract the data they need, when they need it — replacing the digging through doctor’s notes to figure out whether patients meet criteria for certain treatments or trials. Executives, meanwhile, need the assurance of a stable revenue stream that won’t rise and fall with each study.

Future breakthroughs in cancer treatment will depend not only on R&D spending, but also investments in innovation around recruitment, management and the logistics of trials. Wherever the next great advancement in cancer treatment comes from, it will begin with that first group of patients joining a FIH or Phase 1 trial. That trial will need patients. Their care doesn’t come for free.

Dr. Tandy Tipps is Senior Vice President for Healthcare Solutions at Inteliquet. Brenda Noggy is Executive Director of Cancer Center Development and Deployment at Inteliquet.