USA: Researchers have developed a machine learning model using circulating exosomal microRNAs to identify patients with pancreatic ductal adenocarcinoma (PDAC) at increased risk of early liver metastasis following surgery. Patients with a high exosomal microRNA panel score had significantly poorer overall survival than those with a low score, highlighting its potential as a prognostic biomarker for risk stratification and personalised postoperative management.

The study was published in JAMA Surgery by Takayuki Noma, Department of Molecular Diagnostics and Experimental Therapeutics, Beckman Research Institute of City of Hope, Biomedical Research Center, Monrovia, California, and colleagues.
Early liver metastasis following pancreatic cancer surgery is associated with an aggressive disease course and poor survival. However, detecting microscopic liver metastases before surgery remains challenging, limiting clinicians’ ability to identify patients who may benefit from a different treatment strategy.
To address this gap, the researchers investigated whether microRNAs carried by circulating exosomes in plasma could help detect the risk of early liver metastasis before surgery.
The multicentre retrospective case-control study included 372 patients with PDAC treated at four medical centres in China, Japan and South Korea between 2011 and 2024. The investigation involved three stages: genome-wide discovery through exosomal microRNA sequencing, development of a machine learning model, and independent validation in two separate patient cohorts.
The researchers developed an extreme gradient boosting (XGBoost) model incorporating seven exosomal microRNAs to predict early liver metastasis, defined as liver recurrence within six months of surgery performed with curative intent.
The analysis revealed the following findings:
  • Model accuracy: The seven-microRNA model achieved an area under the receiver operating characteristic curve (AUC) of 0.899 in the training cohort. It also demonstrated consistent performance in the two external validation cohorts, with AUC values of 0.876 and 0.862, respectively.
  • Independent prediction: A high exosomal microRNA panel score was independently associated with early liver metastasis, with an odds ratio of 26.49.
  • Survival outcomes: Patients who developed early liver metastasis had a median overall survival of 9.1 months, compared with 26.6–31.8 months among patients experiencing other recurrence patterns.
  • Prognostic value: The panel score significantly distinguished patients according to overall survival. Decision curve analysis also indicated a potential clinical benefit over conventional clinicopathological variables.
The findings suggest that circulating exosomal microRNAs could help clinicians identify patients whose pancreatic cancer has a high likelihood of early metastatic recurrence despite apparently curative surgery. Such information may eventually support decisions about treatment sequencing, including whether systemic therapy should be considered before surgery in selected patients.
However, the researchers noted that the findings require prospective validation before the model can be adopted in routine clinical practice. Further studies are needed to establish its clinical utility and determine whether biomarker-guided treatment decisions improve patient outcomes.
The study highlights the potential of liquid biopsy-based biomarkers to complement conventional assessments and identify aggressive pancreatic cancer biology before surgery.
Reference:
Noma T, Yin J, Zhang J, et al. An Exosomal Signature for Preoperative Detection of Occult Liver Metastasis in Pancreatic Cancer. JAMA Surg. Published online September 02, 2026. doi:10.1001/jamasurg.2026.3840
Tags:    
Article Source : JAMA Surgery

Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.

NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.

Our comments section is governed by our Comments Policy . By posting comments at Medical Dialogues you automatically agree with our Comments Policy , Terms And Conditions and Privacy Policy .