Novel Blood Test Could Identify Therapeutic Response and Avoid Ineffective Therapies

Determining a response to treatment in patients diagnosed with pancreatic cancer can be challenging. A new artificial intelligence (AI) technique for detecting cell-free DNA (cfDNA)*, DNA fragments, which are not encapsulated within cells, shed by tumors and circulating in plasma, could help clinicians more quickly identify and determine if pancreatic cancer therapies are working. [1]

Artificial intelligence technologies, known for their ability to integrate high-dimensional features, have been applied to non-invasive liquid biopsy diagnostics, including a test called ARTEMIS-DELFI (Analysis of RepeaT EleMents in dISease-Dna Evaluation of Fragments for early Interception), developed by researchers at Johns Hopkins Kimmel Cancer Center.

This test, which could revolutionize treatment for patients diagnosed with pancreatic cancer, was included in two clinical trials, CheckPAC trial (NCT02866383) and the PACTO trial (NCT02767557).

Two methods tested
In these trials, patients were evaluated before and after initiation of therapy using tumor-informed plasma whole-genome sequencing (WGMAF) and tumor-independent genome-wide cfDNA fragmentation profiles and repeat landscapes (ARTEMIS-DELFI).

After testing the two different methods in blood samples from patients participating in two large clinical trials of pancreatic cancer treatments, researchers found that this novel approach could could be used to identify therapeutic responses.

ARTEMIS-DELFI and WGMAF were found to be better predictors of outcome than imaging or other existing clinical and molecular markers two months after treatment initiation. However, ARTEMIS-DELFI was determined to be the superior test as it was simpler and potentially more broadly applicable.

The study results showed that in the WGMAF test molecular responders had a median overall survival (OS) of 319 days compared to 126 days for nonresponders [hazard ratio (HR) = 0.29, 95% confidence interval (CI) = 0.11–0.79, P = 0.011].

However, the results for the ARTEMIS-DELFI test in patients with low scores after therapy initiation showed a longer median OS than patients with high scores (233 versus 172 days, HR = 0.12, 95% CI = 0.046–0.31, P < 0.0001).

A description of the work was published May 21, 2025 in Science Advances. [1] It was partly supported by grants from the National Institutes of Health (NIH).**

Time is of the essence
Time is of the essence when treating patients with pancreatic cancer, explains senior study author Victor E. Velculescu, M.D., Ph.D., co-director of the cancer genetics and epigenetics program at the cancer center. Many patients with pancreatic cancer receive a diagnosis at a late stage, when cancer may progress rapidly and the overall outcomes are poor.

“Providing patients with more potential treatment options is especially vital as a growing number of experimental therapies for pancreatic cancer have become available,” Velculescu says. “We want to know as quickly as we can if the therapy is helping the patient or not. If it is not working, we want to be able to switch to another therapy.”

Currently, clinicians use imaging tools to monitor cancer treatment response and tumor progression. However, these tools produce results that may not be timely and are less accurate for patients receiving immunotherapies, which can make the results more complicated to interpret.

In the study, Velculescu and his colleagues tested two alternate approaches to monitoring treatment response in patients participating in the phase 2 CheckPAC trial of immunotherapy for pancreatic cancer.

The WGMAF test analyzed DNA from tumor biopsies as well as cell-free DNA in blood samples to detect a treatment response, while the ARTEMIS-DELFI test used machine learning, a form of artificial intelligence, to scan millions of cell-free DNA fragments only in the patient’s blood samples.

Both approaches were able to detect which patients were benefiting from the therapies. However, not all patients had tumor samples, and many patients’ tumor samples had only a small fraction of cancer cells compared to the overall tissue, which also contained normal pancreatic and other cells, thereby confounding the WGMAF test.

A simpler test
The ARTEMIS-DELFI approach worked with more patients and was simpler logistically, Velculescu says. The team then validated that ARTEMIS-DELFI was an effective treatment response monitoring tool in a second clinical trial called the PACTO trial. The study confirmed that ARTEMIS-DELFI could identify which patients were responding as soon as four weeks after therapy started.

“The ‘fast-fail’ ARTEMIS-DELFI approach may be particularly useful in pancreatic cancer where changing therapies quickly could be helpful in patients who do not respond to the initial therapy,” says lead study author Carolyn Hruban, who was a graduate student at Johns Hopkins during the study and is now a postdoctoral researcher at the Dana-Farber Cancer Institute. “It’s simpler, likely less expensive, and more broadly applicable than using tumor samples.”

Next steps
The next step for the team will be prospective studies that test whether the information provided by ARTEMIS-DELFI helps clinicians more efficiently find an effective therapy and improve patient outcomes. A similar approach could also be used to monitor other cancers. Earlier this year, members of the team published a study in Nature Communications showing that a variation of the cell-free fragmentation monitoring approach called DELFI-TF was helpful in assessing colon cancer therapy response.[2]

“Our cell-free DNA fragmentation analyses provide a real-time assessment of a patient’s therapy response that can be used to personalize care and improve patient outcomes,” Velculescu concluded.

__

Note:* Beyond plasma in the bloodstream, cell-free DNA (cfDNA) represents fragmented DNA molecules in urine, saliva, or other bodily fluids that are not encapsulated within cells. [1]

Funding:** The study was supported by the Dr. Miriam and Sheldon G. Adelson Medical Research Foundation, SU2C Lung Cancer Interception Dream Team Grant; Stand Up to Cancer-Dutch Cancer Society International Translational Cancer Research Dream Team Grant, the Gray Foundation, the Honorable Tina Brozman Foundation, the Commonwealth Foundation, the Cole Foundation, a research grant from Delfi Diagnostics and National Institutes of Health grants.

Clinical trials
Immune Checkpoint Inhibition in Combination With Radiation Therapy in Pancreatic Cancer or Biliary Tract Cancer Patients (CheckPAC) ClinicalTrials.gov ID NCT02866383
Study of Nab-Paclitaxel and Gemcitabine With or Without Tocilizumab in Pancreatic Cancer Patients (PACTO) ClinicalTrials.gov ID NCT02767557

Reference
[1] Tsui WHA, Ding SC, Jiang P, Lo YMD. Artificial intelligence and machine learning in cell-free-DNA-based diagnostics. Genome Res. 2025 Jan 22;35(1):1-19. doi: 10.1101/gr.278413.123. PMID: 39843210; PMCID: PMC11789496.
[2] Hruban C, Bruhm DC, Chen IM, Koul S, Annapragada AV, Vulpescu NA, Short S, Theile S, Boyapati K, Alipanahi B, Skidmore ZL, Leal A, Cristiano S, Adleff V, Johannsen JS, Scharpf RB, Foda ZH, Phallen J, Velculescu VE. Genome-wide analyses of cell-free DNA for therapeutic monitoring of patients with pancreatic cancer. Sci Adv. 2025 May 23;11(21):eads5002. doi: 10.1126/sciadv.ads5002. Epub 2025 May 21. PMID: 40397745; PMCID: PMC12094228.
[3] van ‘t Erve I, Alipanahi B, Lumbard K, Skidmore ZL, Rinaldi L, Millberg LK, Carey J, Chesnick B, Cristiano S, Portwood C, Wu T, Peters E, Bolhuis K, Punt CJA, Tom J, Bach PB, Dracopoli NC, Meijer GA, Scharpf RB, Velculescu VE, Fijneman RJA, Leal A. Cancer treatment monitoring using cell-free DNA fragmentomes. Nat Commun. 2024 Oct 21;15(1):8801. doi: 10.1038/s41467-024-53017-7. PMID: 39433569; PMCID: PMC11493959.

Featured image: Featured Image: Cancerous cells forming a lump in the pancreatic tissue. Photo courtesy: Scientific Animations. Licensed under the Creative Commons Attribution-Share Alike 4.0 International license.

DOI