The Way Ahead: The Convergence of Technology and Cancer Care: November 2023 Edition
By Waqas Haque, MD, MPH
This is the first post of our new blog series "The Way Ahead: Convergence of Technology and Cancer Care," in which we will delve into the latest technological advancements seeking to improve the care and outcomes of patients with cancer. In this edition, we explore the performance of a new artificial intelligence (AI) chatbot for providing National Comprehensive Cancer Network (NCCN) treatment recommendations, results of a multi-cancer early detection blood test study, and the FDA's approval of a novel hepatic delivery system for treating unresectable hepatic metastases from metastatic uveal melanoma.
Artificial intelligence corner: A recent JAMA Oncology study evaluates the performance of a large language model (LLM) chatbot in providing cancer treatment recommendations aligned with NCCN guidelines. Analyzing 104 prompts across breast, prostate, and lung cancers, the chatbot's recommendations were only concordant for 61.9% of scores; 34.3% of outputs recommended non-concordant treatments, and 12.5% included "hallucinated" (not part of any recommended treatment) recommendations. The study reflects the limitations of LLM chatbots in delivering cancer treatment information, emphasizing the importance of clinician guidance and caution when patients inevitably seek information from such technologies. Even if artificial intelligence is able to pass medical licensing exams, LLMs should not currently be perceived as an accurate source of treatment information.
Breakthrough findings: The final results of GRAIL's multi-cancer early detection (MCED) blood test study were published in the Lancet bicentennial issue, with the journal celebrating 200 years on October 5. The PATHFINDER study (NCT04241796) explored the viability of MCED blood tests using circulating cell-free DNA (cfDNA) for cancer screening in a convenience sample cohort of 6,662 asymptomatic adults aged 50 years or older. A cancer signal was detected in 92 patients (1.4%), with 35 (38%) true positives and 57 (62%) true negatives. Of the 35 confirmed cancer cases, 71% of patients were diagnosed for a cancer in which no routine screening is available. The median time to diagnostic resolution was 79 days, with true-positive cases taking 57 days and false-positive cases 162 days, largely owing to scheduled follow-up testing. While larger studies are needed to establish the clinical utility and long-term impact on cancer mortality, MCED may one day drastically reshape how we think about cancer screening on a population level and for patients who lack access to care.
New approvals: Ocular melanoma, the most prevalent intraocular malignancy, often spreads to the liver, presenting a therapeutic challenge with no established standard of care. On August 14, the FDA granted approval to the HEPZATO KIT, a hepatic delivery system by Delcath Systems, for treating adult patients with metastatic uveal melanoma and unresectable hepatic metastases affecting less than 50% of the liver.
The HEPZATO KIT, employing a novel hepatic delivery system, administers melphalan directly to the liver, maximizing drug exposure in target tissues while minimizing systemic toxicity. This approach enables practitioners to isolate the liver during melphalan infusion, enhancing locoregional drug delivery.
The FDA approval of HEPZATO KIT is grounded in the FOCUS study (NCT02678572), an open-label, single-arm phase 3 trial of 91 patients demonstrating a 36.3% objective response rate and a median duration of response of 14 months. Notably, adverse events were limited, with occurrences of hemorrhage, hepatocellular injury, and thromboembolic events in less than 5% of treated patients. This groundbreaking approval marks a significant advancement in addressing the unique challenges posed by metastatic uveal melanoma, which has an incidence of nearly 1,000 cases annually in the United States.
Stay tuned for next month's edition of the blog to read about the latest convergences of technology and cancer care!
About Waqas Haque, MD, MPH
Waqas Haque, MD, MPH, is a third-year Internal Medicine Resident at New York University (NYU) in a Clinical Investigator Track. As a Clinical Investigator Track Resident, Dr. Haque has balanced his patient care work with a variety of research projects. He hopes to begin fellowship training next year in Medical Hematology/Oncology at an academic program with opportunities to further his work in innovative clinical trial design, value-based care delivery to cancer patients, and becoming an early-stage clinical investigator.
For More Information
Chen S, Kann BH, Foote MB, et al (2023). Use of artificial intelligence chatbots for cancer treatment information. JAMA Oncol, 9(10):1459-1462. DOI:10.1001/jamaoncol.2023.2954
Kung TH, Cheatham M, Medenilla A, et al (2023). Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digital Health, 2(2):e0000198. DOI:10.1371/journal.pdig.0000198
Schrag D, Beer TM, McDonnell CH, et al (2023). Blood-based tests for multicancer early detection (PATHFINDER): a prospective cohort study. Lancet, 402(10409):1251-1260. DOI:10.1016/S0140-6736(23)01700-2
Zager JS, Orloff MM, Ferrucci, PF, et al (2022). FOCUS phase 3 trial results: Percutaneous hepatic perfusion (PHP) with melphalan for patients with ocular melanoma liver metastases (PHP-OCM-301/301A). J Clin Oncol, 41(suppl_16). Abstract 9510. DOI:10.1200/JCO.2022.40.16_suppl.9510