02/20/2025

Oncology innovation: How emerging biotechs lead through RWD & AI

Ryan Fukushima, Chief Operating Officer at Tempus, discusses how cutting-edge tools are helping biotechs streamline clinical trials, optimize patient selection, and improve decision-making, even amidst challenging market conditions.
Authors Ryan Fukushima
Chief Operating Officer, Tempus




In an evolving biotech landscape, emerging companies are harnessing the power of real-world data (RWD) and artificial intelligence (AI) to help accelerate oncology drug development. Discover how biotechs are leading the next wave of oncology innovation

The evolving biotech landscape



Investment in biotechs has declined in recent years. While there are signs of recovery, the disparity between the S&P 500’s performance and the S&P biotech index is notable, with IPOs occurring less frequently.1 This trend has limited funding opportunities for biotechs, which previously relied on capital from both private and public markets to advance their pipelines. 

The lengthy process of developing and bringing drugs to market heightens these challenges. On average, it takes about seven years from investigational new drug to new drug application approval for anti-cancer drugs and a significant financial investment, accounting for the numerous failures along the way.2 These smaller companies often concentrate their limited resources on just one or two critical trials, which creates a concentrated impact of any setbacks.

Figure 1 S&P biotech index and IPO funding1



Data shows that as promising molecules progress from preclinical to clinical stages, the risk of failure increases significantly, particularly in Phase II. This issue often stems from improper patient selection in the design of Phase II trial, which is crucial for demonstrating efficacy and mitigating high failure rates.3 In addition, approximately 25% of clinical trials fail to enroll enough patients for meaningful outcomes, a problem that affects the entire biopharma industry but is especially acute for biotechs.4

Figure 2 First-in-class oncology drug originators, 2010-20204

Despite the challenging macro environment and daunting obstacles, biotechs continue to lead in FDA drug approvals. Over the past decade, approximately 50% of the 50 FDA-approved oncology drugs originated from biotechs, demonstrating their propensity for successful innovation.5 However, there is a pressing need to address inefficiencies and support biotech development to help facilitate bringing life-saving medicines to the market.

Tempus’ strategic approach to powering discovery and development



Tempus embeds RWD and practical applications of AI to help support emerging biotechs with the resources needed to match large pharma in four key areas of clinical development for a biotech’s asset.

One of the first questions we ask revolves around whether each asset has prioritized the optimal indications for development. This strategy can be crucial when designing Phase I trials, such as choosing an all-comers or a multi-tumor type approach and narrowing down options for Phase II trials to reduce the trial size to preserve precious resources.

As clinical stage development progresses, refining not just the indication but also the inclusion and exclusion (I/E) criteria in the protocol becomes critical. Rather than making decisions based on conventional wisdom or key opinion leaders’ advice, real-world contemporaneous data could be used to support biotechs to make informed trade-off decisions about potentially diluting the efficacy signal or mitigating potential recruitment challenges. 

Another critical aspect of clinical trial optimization is determining the combination partners to pursue during Phase I or Phase II trials, which may be facilitated through leveraging standard-of-care (SoC) treatments reflected in real-world datasets. 

Lastly, endpoint optimization is a final consideration. This involves selecting endpoints that are not only practical but may also compress the study duration. While overall survival is a common endpoint for Phase III studies, we can use real world data to uncover other primary endpoints based on current outcomes on standard of care treatments. With advancements in minimal residual disease (MRD) detection and the availability of RWD, it’s possible to contextualize endpoints to accelerate comparative analyses.

Data-driven decision making



To support biotech’s decision-making in these key clinical development areas, our initial focus is on identifying an appropriate real-world dataset that is fit-for-purpose. Access to real-world data in a population of interest helps enable the biotech to refine their asset’s indications into subpopulations and hone in on the mechanisms of action driving the disease. In fact, Tempus multimodal dataset has uncovered new patient populations with severe unmet needs for multiple programs, highlighting opportunities with Accelerated Approval potential. 

Once these subpopulations are established, Tempus works collaboratively  to analyze the current SoC treatments and outcomes as reflected in the real-world data. This sets the stage for simulations that may help predict the potential impacts of novel treatments on these mechanisms, offering a glimpse into potential future states post-drug approval. There are a spectrum of possibilities, and modeling out these efficacy signals can be an effective way to help make informed go/no-go decisions during Phase II and beyond.

The overarching goal is to help biotechs enhance the efficiency of their clinical trials, and the industry is beginning to see the fruits of these efforts. By incorporating RWD analysis from the protocol design phase through to the contextualization of results, it is possible to reduce both the number of patients needed for Phase II trials and the number of sites required to run these studies.6 These are significant cost drivers in clinical trials, and for biotechs with limited budgets, it is crucial to maximize the value of every dollar spent. Tempus is at the forefront of leveraging RWD, collaborating with leading companies to not only help inform trial design but also provide insights on how to contextualize trial results against SoC, particularly when a control arm is not used in a Phase II trial.

RWD in action



Through our partnerships, we focus on understanding how our partner measures value, whether through key metrics like the probability of technical and regulatory success (PTRS) or net present value (NPV). The specific metric isn’t as important as having one to gauge and measure success. We have historically found that by leveraging data from the earliest stages of clinical development, the life sciences company is able to yield a return on investment approximately five times greater than the typical spend with Tempus.7 The aim is to deliver value not just for a single trial but to demonstrate how our collaboration can consistently add value across the portfolio. 

By leveraging our multimodal data library, we perform in-depth analyses and equip our partners with the insights needed to quickly make informed development decisions. Typically, we see an increase in PTRS by about two percentage points in our first year of engagement and grows to 7% lift by the second year of engagement.5 This process allows for a deeper focus on investments in clinical development, targeting smaller opportunities and ruling out less promising studies based on RWD insights. 

Figure 3 Increasing PTRS with AI and RWD5

Mirati’s KRYSTAL-1 study, which focused on KRAS G12C mutant patients, is a prime example of applying RWD to trial design. The study was a single-arm trial without a control group, raising questions about how the results from the interventional arm compared to SoC. Although initial data from Dana Farber provided some stratification for PD-L1 high or positive patients, the patient counts were low, limiting the strength of the conclusions.8

Fortunately, a propensity-matched analysis could be conducted against the entire I/E criteria of the KRYSTAL-1 study. This analysis revealed differences in outcomes between patients with KRAS G12 wild type and those with KRAS G12C mutation when PD-L1 or tumor proportion score (TPS) was less than or equal to 50%.6 Presenting this larger dataset as supplementary information to regulators supported the argument that these patients have poorer outcomes than previously reported, making the study results even more compelling. This is crucial for investment decisions, particularly for a Phase II trial approaching a critical go/no-go decision for advancing to Phase III.

Embedding our Data Products with our CRO solutions



Tempus offers a full-stack solution that leverages over 200 petabytes of data from millions of de-identified patient records to understand mechanisms and pathways driving unmet medical needs. While we collaborate with 19 of the top 20 pharma companies,9 our approach differs when working with biotechs due to their unique constraints. 

Tempus is excited to introduce a new offering tailored for biotechs, integrating RWD, AI expertise, and Contract Research Organization (CRO) services that will bring end-to-end support to critical clinical development studies. We call it the Tempus Biotech Program. With a full-service CRO, Tempus Compass, we can now embed our capabilities throughout clinical development to leverage data and help transform it into insights, covering trial design, feasibility, site selection, and study execution all powered by a multimodal dataset. The goal is for Tempus to act as an extension of a biotech’s team, designing clinical development strategies in tandem and applying insights at each step of the process. This partnership model goes beyond project-based collaborations, offering a comprehensive solution to biotechs. 

We have already seen some key wins with this approach. For instance, in collaboration with Sermonix, we utilized data-driven strategies to optimize recruitment. By focusing on top-tier academic medical centers and employing a rapid, just-in-time site activation approach, we enabled multiple avenues for patient recruitment, particularly for populations like ESR1-positive breast cancer patients. This method has significantly reduced startup time, saving an estimated 10 months in enrollment based on the initial trial projections.10 This type of acceleration is game-changing for biotechs where every month counts.

Most importantly, the Tempus Biotech Program is not just about bundling capabilities. What’s crucial for biotechs, particularly when cash is a constrained resource due to the current macro environment, is offering this in a shared-risk manner. We’re providing a holistic service paired with an economic model that’s designed to be more productive and conducive. We’re excited to partner with the next set of innovators, and the Tempus Biotech Program is our commitment to accelerating precision medicine for all.

To learn more about how Tempus Compass can tailor solutions to your biotech’s unique challenges, click here.

 

1. Capra E, Fougner C, Mäkitie A, Leclerc O, Suberski A, Suhendra M. What early-stage investing reveals about Biotech Innovation. McKinsey & Company. December 12, 2023. Accessed September 19, 2024.

2. Shuhang Wang, Qiuyan Yang, Lan Deng, Qi Lei, Yuqi Yang, Peiwen Ma, Yuxin Men, Bryant C. Yung, Robert J. Lee, Mengzi Zhang, Ning Li, An overview of cancer drugs approved through expedited approval programs and orphan medicine designation globally between 2011 and 2020, Drug Discovery Today, Volume 27, Issue 5, 2022, Pages 1236-1250, ISSN 1359-6446, https://doi.org/10.1016/j.drudis.2021.12.021.

3. Sertkaya A, Beleche T, Jessup A, Sommers BD. Costs of Drug Development and Research and Development Intensity in the US, 2000-2018. JAMA Netw Open. 2024;7(6):e2415445. doi:10.1001/jamanetworkopen.2024.15445

4. Fogel DB. Factors associated with clinical trials that fail and opportunities for improving the likelihood of success: A review. Contemp Clin Trials Commun. 2018 Aug 7;11:156-164. doi: 10.1016/j.conctc.2018.08.001. PMID: 30112460; PMCID: PMC6092479.

5. Kate H. Kennedy, Krisstel Gomez, Natalie J. Thovmasian, Dennis C. Chang, Small biotechs versus large pharma: Who drives first-in-class innovation in oncology?, Drug Discovery Today, Volume 28, Issue 2, 2023, 103456, ISSN 1359-6446, https://doi.org/10.1016/j.drudis.2022.103456.

6. Anagnostopoulos C, Champagne D, Devereson A, Devenyns T, Tarkkila H. How artificial intelligence can power clinical development. McKinsey & Company. November 22, 2023. Accessed September 19, 2024.
7. *Results based on 30+ analyses from Tempus to increase probability of technical and regulatory success(PTRS) across multiple strategic partners (Tempus Strategic Partners: +$100m over 3-5 yrs).
8. Slides 22-23 Mirati ESMO Investor Event
9. Based on publicly available 2022 segment revenue
10. Blau M.D., Sibel. Operational Metrics for the ELAINE 2 Study Combining a Traditional Approach with a Just-in-TIME Model. ASCO 2022.

Related Content

View more
  • post image
    02/13/2025

    AI & ML in action: Real-time advances in precision medicine

    Explore the capabilities of the Tempus platform, where cutting-edge diagnostics meet actionable data insights to enhance precision medicine. Learn how AI and ML tools seamlessly integrate biomarkers into the diagnostic process, ensuring patients receive the right treatment(s) at the right time. Experience Tempus Lens in action, with an exclusive live demonstration of our newest AI advancements, and hear perspectives on AI's expanding role in healthcare and its transformative potential.

    Watch replay
  • post image
    01/27/2025

    Addressing health disparities at a large academic medical center: AI-driven cardiac care for aortic stenosis and mitral regurgitation

    Leveraging a natural language processing (NLP) based, artificial intelligence (AI) driven protocol, Tempus Next worked to help clinicians improve management of patients with severe aortic stenosis (sAS) and severe mitral regurgitation (sMR) by identifying patients who may have been previously overlooked.

    Read more
  • post image
    12/05/2024

    Advancing IO therapeutics: The convergence of novel biomarkers and combination strategies

    Explore the latest in immuno-oncology (IO), where emerging therapies are reshaping the landscape of cancer treatment. This webinar will focus on the role of novel biomarkers and combination treatment strategies in understanding and enhancing the immune system's response to cancer. Discover the significant developments that are helping to shape clinical trials and improving patient outcomes in IO and hear perspectives from industry experts on the potential of emerging therapies.

    Watch replay