The Opportunity for Digital Innovation in Oncology Drug Development

Oncology is a critical area of healthcare, posing significant challenges yet offering substantial opportunities for innovation, particularly in pharma drug development. The seriousness of cancer is universal, with nearly everyone knowing someone affected by this daunting diagnosis. 

Cancer is a leading cause of death in the US, with approximately 2 million new cases diagnosed annually and around 600,000 deaths each year. The financial burden is also significant, with the cost of cancer care exceeding $200 billion in 2020. Since then, the cost of cancer treatment has only increased due to increasing prevalence and novel, often expensive, treatments that have been introduced. 

From a pharma standpoint, oncology drugs represent about 22% of the industry’s total revenue. Sales of cancer therapies are expected to surpass $320 billion by 2026, highlighting both the economic importance of, and the critical need for, innovative solutions in this field.

Oncology as a major focus for pharma

The focus on oncology within pharma is driven by several factors. First, the high unmet medical need. Cancer is not a single disease but rather a collection of related diseases with unique genetic profiles, which necessitates individualized treatment approaches. Challenges such as genetic heterogeneity, the diversity of tumor microenvironments, immune evasion, metastases, and treatment resistance all complicate the development of effective therapies.

Second, advances in cancer research across molecular biology, genomics, and immunology have opened new avenues for treatment innovation. Research advancements have enabled the identification of new targets and the development of novel therapies, including advanced immunotherapies and precision treatments tailored to an individual patient’s profile.

Additionally, regulatory incentives, such as the FDA’s expedited approval processes for oncology drugs that target urgent, unmet needs, also motivate pharma to develop cancer therapies.  

Despite these advances and regulatory support, the path to oncology drug development is fraught with challenges. Developing new cancer drugs and treating patients with cancer entails overcoming numerous hurdles. Three major areas where pharma faces challenges, and where digital innovations show promise are (1) clinical trial design, (2) patient identification, and (3) patient engagement. This article will discuss each challenge in more detail and conclude with digital innovations that are addressing these pain points. 

Challenges in oncology drug development:  Trial design

Designing successful oncology trials is data-intensive, since it requires information from discovery phases, animal trials, and previous human trials. Data related challenges in oncology trials include: 

• Using data effectively:

Translational researchers often make critical decisions with insufficient data, lacking critical and comprehensive “omic” data and other patient information to inform their choices.

Access to siloed data also poses challenges. Valuable data from early stages are often not readily available or accessible for subsequent trial phases. But incorporating data from earlier trials is essential for optimal trial designs.

• Identifying and/or developing of appropriate biomarkers and endpoints:

New biomarkers are continually needed as our understanding of cancer deepens. Biomarkers can be used to refine the relevance and precision of inclusion and exclusion criteria in clinical trials, helping indicate which patients are most likely to respond to treatment and are less likely to experience unwanted side effects. Understanding the relationships among biomarkers is complex and usually involves intricate math and statistics.

• Modeling outcomes:

Trial design revolves around modeling outcomes to calculate the smallest cohort of patients needed to ensures statistical power and positive results. Smaller, effective trials are always preferred, because they are cheaper and easier to recruit for than large trials. 

Trial modeling can help evaluate failed trials. A successful model can help distinguish true negatives from false negatives and thus inform whether a trial’s design was flawed, such that a trial redesign, rather than abandoning the compound, is warranted.

Challenges in oncology drug development: Patient identification

A second major challenge for pharmaceutical companies in oncology drug development is patient identification. This involves not only finding suitable candidates for clinical trials but also matching them to the correct treatments.

Extensive data from electronic medical records (EMRs) can be quite useful in this process. However, accessing and evaluating these records is difficult since crucial information may be locked in image files or unstructured notes.

Rare cancers present additional challenges due to their low incidence. To recruit enough patients, trials often need to be conducted across multiple countries, which adds considerable operational complexity.

Ensuring diversity in clinical trials is another hurdle in patient identification. The FDA mandates that drugs be tested in diverse populations. But recruiting underrepresented minorities can be difficult. Even when eligible patients are identified, their participation is not guaranteed. Trust of the person and organization are crucial for a patient to choose to participate in a clinical trial. Many minority groups in the US have historically had a low level of trust in the medical system.

Challenges in oncology drug development: Patient engagement

In oncology drug development, ensuring a positive patient experience is a complex and crucial task. Once an oncology trial has been successfully designed, patients who meet the selection criteria are identified, and they agree to participate in the trial, it is vital to provide them with the best possible care and support.

Personalizing treatment is a key aspect of this process. For instance, matching a patient to the appropriate therapy, whether in a trial or real-world setting, requires a deep understanding of tumor heterogeneity. By evaluating the patient’s tumor and its microenvironment, researchers can determine the best drug for that specific patient. Additionally, using phenotypic and genotypic data to model a patient’s response can help predict how an individual will react to a particular treatment.

Virtual (or in-silico) testing of drugs represents another innovative strategy for personalization. Drugs can be tested on patients virtually using “digital twins”, which are detailed models created from individual patient data. These digital twins simulate and predict how a person will respond to therapy, helping to develop a personalized treatment plan. 

Minimizing side effects such as pain, anxiety, and sleeplessness can significantly improve the quality of life and outcomes for cancer patients. Optimizing the overall patient experience can also enhance therapy adherence and reduce the likelihood of a patient discontinuing a therapy.  

Education and support are vital to patient engagement. Providing comprehensive information to patients and caregivers about the treatment and side effects can significantly improve their experience. Engaged and well-supported patients tend to report more positive experiences with their cancer treatment.

Ensuring a positive patient experience is an ongoing challenge in oncology drug development, but it is highly correlated with positive outcomes. Ultimately, improving the patient journey helps prevent dropouts from trials.

Conclusion

In summary, the development of new oncology drugs is important to both patients and the pharmaceutical industry. But the complex, multifaceted nature of cancer results in significant unmet clinical needs in oncology. 

In attempting to develop novel oncology drugs, pharma faces hurdles in trial design, patient identification, and patient engagement. 

Fortunately, digital innovations are being developed to tackle these challenges head-on: 

• New digital biomarkers are leading to improved patient/therapy matching and enhanced effectiveness of trial selection criteria. 
• Novel access and uses of data are improving recruitment, patient selection, and treatment personalization. 
• Advanced trial design and modeling tools help ensure that trials are optimally run.
• Innovative patient identification and recruitment processes are speeding clinical trials.
• Comprehensive patient and caregiver engagement platforms are providing education and side effect management to improve the patient journey.

By leveraging these digital innovations, the pharmaceutical industry can make significant strides in oncology drug development, which will ultimately improve outcomes for cancer patients everywhere.

Credit: wildpixel, Getty Images

This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.