Insights from ASCO ‘24: Harnessing AI for Better Cancer Treatment Outcomes
Authored by Dane Lund, Marina Oraczewski, Jorge Durand
What you’ll learn:
AI is increasingly integrated into oncology, addressing challenges like subjective imaging, complex treatment decisions, financial toxicity, and HCP burnout.
ASCO 2024 showcased AI's utility in cancer care with over twenty talks on its impact, demonstrating advancements in clinical trial enrollment, imaging analysis, outcome prediction, risk assessments, and treatment decisions.
ASCO established six principles to ensure ethical, responsible AI use in oncology, supplementing human clinical decision-making.
Driven by our passion for oncology and leadership in AI innovation, and as a follow-up to our overview of this year’s American Society of Clinical Oncology (ASCO) Annual Meeting, we wanted to share our perspective on what our Klick's oncology leaders observed and foresee regarding the integration of artificial intelligence (AI) into oncology and cancer care.
AI is increasingly being used to tackle common challenges in oncology, including subjective imaging, complex treatment decisions, financial strain on patients, patient engagement, and the risk of healthcare provider burnout. AI usage in oncology has been steadily growing each year, and the recent ASCO meeting demonstrated that this potential is starting to be realized through broader application and increasing clinical evidence. ASCO 2024 highlighted AI's role as a "clinician copilot," reinforcing a theme from previous years and emphasizing its potential to enhance patient-centric care when implemented effectively.
Overview
This year, there were more than twenty talks on AI's impact on cancer care—nearly double the number from 2023. Additionally, there was a rise in booths showcasing AI platforms for oncologists. The focus areas included clinical trial enrollment, imaging analysis, outcome prediction, risk assessments, and treatment decisions/sequencing. Below, you'll find a selection of key presentations from ASCO that highlight the future of AI in clinical settings.
Touching every domain of medicine: AI is expected to help with image, voice, and text processing and relieve practice burdens, especially in settings where HCPs are responsible for interacting with a much higher volume of patients. Like biomarkers, AI can help guide treatment decisions, cost efficiency, and precision medicine, but “it's not magic,” as Drs Srisuwananukorn and Pearson said in their presentation: Understanding How to Use This 21st Century Tool. Additionally, on the clinical research front, AI may improve multi-trial matching in oncology.
Cost: Telo Genomics, a biotech company in telomere prognostic applications, presented proprietary AI methodologies to improve the quantifying and processing of myeloma plasma cells. CellSelect-Pro impacts the sample processing turn-around time with potential cost savings of 20–25% versus manual cell selection in their TeloView myeloma diagnostic tests. Additionally, this facilitates high-throughput sample processing while enhancing consistency and accuracy.
Treatment Decisions: Dr. Irbaz B. Riaz discussed AI's use in optimizing systemic therapy for prostate cancer patients, providing a potential solution to the increasing burden oncologists are facing with rapidly evolving treatment landscapes. This was coupled with evidence that ChatGPT demonstrated potential in proposing feasible and accurate cancer treatment plans. Additionally, several studies specified AI’s predictive prognostic capabilities:
ArteraAI introduced the first AI-enabled test providing prognostic and predictive insights for localized prostate cancer patients.
A new study highlighted AI's ability to predict survival in ovarian cancer accurately.
The AI-guided prognosis for recurrence in Stage I-III NSCLC significantly increased sensitivity compared to traditional staging.
AI also showed potential in addressing the accuracy of treatment prognosis and diagnosis of breast cancer.
Imaging: Dr. Stephanie Harmon discussed innovation and the potential for diagnostic imaging in prostate cancer. Qure.ai was sensitive and specific in categorizing chest radiographs consistently as lung cancer or tuberculosis and can potentially aid in the earlier detection and management of these diseases.
Patient uptake: The AI-based virtual patient navigator MyEleanor exhibits high potential to overcome patient attrition and improve patient volume in CRC screening. Initial results showed that it helped increase adherence to screening protocols, nearly doubling the patient uptake rate.
AI Cancer Platforms: Among new platforms, ConcertAI and Tempus, two leaders in AI applications in medicine, have shown new data at ASCO.
ConcertAI (CARA AI) is partnering with Nvidia to develop new clinical simulations that inform future AI products for clinical trials. They also have been able to define real-world baseline treatment patterns and overall survival in patients with mCRPC treated with olaparib in the US, efficient site selection for clinical trials using simulated annealing, AI-based clinical trial eligibility screening with traditional EMR-based screening, and they are using dynamic machine learning model to forecast patient availability for clinical trials.
Tempus exhibited 16 abstracts, among which their xM assay showed potential in predicting recurrence and disease-free survival in stage II and III colorectal cancer patients, outperforming traditional markers. Their xM for treatment response monitoring (TRM) assay can reduce therapy costs by shortening ineffective treatment durations and may serve as a cost-effective alternative to diagnostic imaging. Combining xM for TRM molecular data with imaging improves overall survival predictions in patients treated with immunotherapy.
The most in-depth integration of AI into oncologists' care may have been in Prostate Cancer—from diagnostic imaging to treatment decision-making to workflow integration. AI stands to have a profound impact through the treatment continuum, and across tumor types.
What’s New: Predictive versus Generative AI
In a shift from predictive AI/machine learning, generative AI can conduct medical reasoning, analyze EHR data, and guide patient care. One example, Color’s copilot, is helping clinicians create customized, comprehensive plans to start cancer treatment. With the evolution of AI in oncology, ASCO has made it clear that there “is an important boundary to draw as AI can enhance, augment, prompt, and supplement clinician decisions but should not seek to replace them.” (ASCO)
"The idea of combining Al technologies with digitally-enabled clinical workflows to expedite that process would be a positive advancement for all parties involved - the patient and their clinicians, as well as the payer covering the cost of treatment." - Dr. Karen Knudsen, CEO of the American Cancer Society
Six Guiding Principles Set by ASCO for AI in Oncology
ASCO has appointed a specialized task force to investigate AI use in oncology and make recommendations. This task force will analyze AI developments and apply its findings to future policies. More details can be found in ASCO’s guide, “Principles for the Responsible Use of Artificial Intelligence in Oncology.”
1. Transparency: AI tools and applications should be transparent throughout their life cycle.
2. Informed Stakeholders: Patients and clinicians should know when AI is used in clinical decision-making and patient care.
3. Equity and Fairness: AI developers and users should protect against bias in AI model design and use and ensure access to AI tools in applications.
4. Accountability: AI systems must comply with legal, regulatory, and ethical requirements that govern the use of data. AI developers should assume responsibility for their AI systems, their decisions, and adherence to legal, regulatory, and ethical standards.
5. Oversight and Privacy: Decision-makers should establish institutional compliance policies that govern the use of AI, including protections that guard clinician and patient autonomy in clinical decision-making and privacy of personal health information.
6. Human-Centered Application: Human interaction is a fundamental element of health-care delivery; AI does not eliminate the need for human interaction and should not be used as a substitute for sensitive interactions that require it.
The ASCO task force is expected to continually guide the application and implementation of AI in oncology care. This guidance should closely mirror that from regulatory agencies.
Summary
ASCO 2024 underscored the critical role of continuing innovation in cancer care while keeping patients at the center of our efforts. The conference highlighted promising breakthroughs, new tools, and potential cures for the future, with AI emerging as a significant player. AI is proving to be a valuable resource for oncologists, addressing established challenges in oncology such as subjective imaging, complex treatment decisions, financial strain on patients, patient engagement, and potential healthcare provider burnout.
“It's early still, but given the technology's rapid progress and the fact that health is a priority for generative AI model builders, we anticipate seeing more applications in cancer diagnosis, prognosis, and care planning, amongst other areas.” —Simon Smith, EVP Generative AI, Klick Health, Inc.
We encourage anyone to reach out with questions or comments on any of these topics.
Authors
Dane Lund
Medical Strategist
As a medical strategist, Dane brings extensive oncology experience across lung, breast, prostate, gastric, and liquid tumors as well as expertise in rare diseases, autoimmune disease, and genetic testing. He has contributed to the growth of brands like Enhertu, Verzenio, Calquence, Tepezza, Tyvyt, Invitae, Giapreza, And Lumryz. Dane is passionate about making science accessible for patients and healthcare providers through creative deliverables. He has developed and launched multiple campaigns, messaging platforms, and product theaters. Dane holds a BS and PhD from the University of Missouri and completed a postdoctoral fellowship at Memorial Sloan Kettering Cancer Center, where he studied cancer-related muscle wasting and developed AI-based drug-screening assays.
Marina Oraczewski
VP, Medical Strategy
Marina brings over a decade of experience in medical strategy, brand development, and medical communications across oncology, immunology, and rare diseases. She has shaped brands within Genentech’s HER2+ breast cancer franchise and contributed to the launches of Lenvima for solid tumors and Gavreto for RET+ cancers. As a brand strategist, she developed pre-launch strategies for Genentech’s anti-TIGIT therapy and Pfizer’s cancer pain treatment. Marina holds a BSE in chemical engineering from the University of Pennsylvania, and completed her PhD in molecular biology from Princeton University, with her doctoral research dedicated to advancing the understanding of cell cycle control in cancer.
Jorge Durand
Executive Director, Medical Strategy
With over 15 years of medical strategy experience, Jorge has helped build healthcare brands across oncology, immunology, rare disease, and more. He is passionate about practice-changing ideas grounded in deep scientific and market analysis, especially for brands significantly impacting the lives of patients.. He’s led marketing and medical affairs efforts, helped develop new messaging platforms and campaigns, optimized omnichannel strategy, and collaborated with thought leaders and patient-advocate organizations. Since joining Klick in 2017, Jorge has expanded the medical strategy department tenfold and grown the overall brand portfolio. He holds a BS and an MS in nuclear engineering from Balseiro Institute and a PhD/MS in biomedical sciences from Albert Einstein College of Medicine.
Ready to Drive Life Sciences Forward?
Experience the transformative power of Klick Health, where deep industry expertise meets cutting-edge AI-driven wisdom.
As your trusted partners in life sciences commercialization, we combine a storied history in healthcare with the latest technologies to elevate every facet of your omnichannel strategy. From crafting engaging narratives to enabling data-driven decision-making, our integrated capabilities ensure you lead the way in transforming patient outcomes through digital health innovation.
Let’s create something transformative together.
