Machine Learning Algorithms Interpreting Circulating MicroRNA Signatures for Real-Time Monitoring of Chemotherapy Response: A Randomized Controlled Trial
Article Sidebar
Main Article Content
Abstract
Background: The standard waiting period of six to eight weeks for radiographic assessment of chemotherapy response creates a critical clinical gap during which non-responsive tumors may progress and responsive patients endure unnecessary toxicity. Circulating microRNAs offer dynamic biological readouts of treatment effect, but their complex, high-dimensional patterns have eluded conventional statistical interpretation. Objective: To determine whether a machine learning algorithm analyzing serial circulating microRNA levels can predict radiographic chemotherapy response at two weeks with acceptable concordance compared to standard week-eight imaging. Methods: This parallel-group randomized controlled trial enrolled 110 adults with advanced solid tumors receiving first-line platinum-based or taxane-based chemotherapy. Participants were randomized to an intervention group (serial microRNA profiling with algorithmic analysis at baseline, day 3, day 7, and day 14) or a control group (standard care with imaging at week eight; blood samples stored for post-hoc analysis). The primary outcome was concordance between the algorithm's two-week prediction and week-eight RECIST-defined response, assessed using positive percent agreement and negative percent agreement with 95% confidence intervals. Secondary outcomes included time to treatment switch and six-month progression-free survival. Results: Among 101 participants completing the trial, the algorithm demonstrated 85.0% overall concordance (95% CI 76.5%–91.4%), with positive percent agreement of 88.0% (95% CI 75.7%–95.5%) and negative percent agreement of 82.0% (95% CI 68.6%–91.4%). One participant with indeterminate algorithm output was excluded from concordance calculations. A significant time-by-group interaction was observed (F(3, 297)=14.82, p<0.001, with Greenhouse-Geisser correction). Time to treatment switch was shorter in the intervention group (median 23 days, IQR 20–28 vs. median 42 days, IQR 36–48; log-rank p<0.001), and six-month progression-free survival was higher (76.0% vs. 58.8%, p=0.04). Conclusion: Machine learning analysis of serial circulating microRNA signatures predicted chemotherapy response at two weeks with high concordance compared to standard imaging, enabling earlier treatment switches and improved progression-free survival. These findings provide proof of concept for real-time microRNA-based monitoring, though confirmation in a multicenter trial with algorithm-guided treatment decisions is required before clinical implementation.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
1. Eisenhauer EA, Therasse P, Bogaerts J, Schwartz LH, Sargent D, Ford R, et al. New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer. 2009;45(2):228-47.
2. Janse van Rensburg HJ, Spiliopoulou P, Siu LL. Circulating biomarkers for therapeutic monitoring of anti-cancer agents. Oncologist. 2022;27(5):352-62.
3. Derouane F, van Marcke C, Berliere M, Gerday A, Fellah L, Leconte I, et al. Predictive biomarkers of response to neoadjuvant chemotherapy in breast cancer: current and future perspectives for precision medicine. Cancers. 2022;14(16):3876.
4. Aswathy R, Chalos VA, Suganya K, Sumathi S. Advancing miRNA cancer research through artificial intelligence: from biomarker discovery to therapeutic targeting. Med Oncol. 2024;42(1):30.
5. Pang L, Liu Z, Wei F, Cai C, Yang X. Improving cardiotoxicity prediction in cancer treatment: integration of conventional circulating biomarkers and novel exploratory tools. Arch Toxicol. 2021;95(3):791-805.
6. Ganesh MS, Revanth R, Bharathi C. Advanced biomarkers and precision medicine: innovative strategies to prevent cancer recurrence. Eur J Cancer Res Update. 2025;14:1-11.
7. Khan MAI, Zannat NA. Novel biomarkers and therapeutic avenues for precision oncology and effective treatment strategies. J Adv. 2024;8(11):1-8.
8. Li W, Wen C, Ye B, Gujarathi P, Suryawanshi M, Vinchurkar K, et al. Targeted drug monitoring in oncology for personalized treatment with use of next generation analytics. Front Pharmacol. 2025;16(1):1523.
9. Metcalf GA. MicroRNAs: circulating biomarkers for the early detection of imperceptible cancers via biosensor and machine-learning advances. Oncogene. 2024;43(28):2135-42.
10. Hussen BM, Abdullah SR, Hidayat HJ, Samsami M, Taheri M. Integrating AI and RNA biomarkers in cancer: advances in diagnostics and targeted therapies. Cell Commun Signal. 2025;23(1):430.
11. Alqahtani S, Alqahtani T, Venkatesan K, Sivadasan D, Ahmed R, Elfadil H, et al. Unveiling pharmacogenomics insights into circular RNAs: toward precision medicine in cancer therapy. Biomedicines. 2025;15(4):535.
12. Pliakou E, Lampropoulou DI, Dovrolis N, Chrysikos D, Filippou D, Papadimitriou C, et al. Circulating miRNA expression profiles and machine learning models in association with response to irinotecan-based treatment in metastatic colorectal cancer. Int J Mol Sci. 2022;24(1):46.
13. Ling L, Aldoghachi AF, Chong ZX, Ho WY, Yeap SK, Chin RJ, et al. Addressing the clinical feasibility of adopting circulating miRNA for breast cancer detection, monitoring and management with artificial intelligence and machine learning platforms. Int J Mol Sci. 2022;23(23):15382.
14. Ogunleye AZ, Piyawajanusorn C, Gonçalves A, Ghislat G, Ballester PJ. Interpretable machine learning models to predict the resistance of breast cancer patients to doxorubicin from their microRNA profiles. Adv Sci. 2022;9(24):2201501.
15. Sathipati SY, Tsai M-J, Aimalla N, Moat L, Shukla SK, Allaire P, et al. An evolutionary learning-based method for identifying a circulating miRNA signature for breast cancer diagnosis prediction. NAR Genom Bioinform. 2024;6(1):lqae022.
16. Rituraj, Pal RS, Wahlang J, Pal Y, Chaitanya M, Saxena S. Precision oncology: transforming cancer care through personalized medicine. Med Oncol. 2025;42(7):246.
17. Kumar A, Metta D. AI-driven precision oncology: predictive biomarker discovery and personalized treatment optimization using genomic data. Int J Adv Res Pharm Res. 2024;1(3):21-38.
18. Ueda H, Takahashi H, Sakaniwa R, Kitamura T, Kobayashi S, Tomimaru Y, et al. Preoperative treatment response prediction for pancreatic cancer by multiple microRNAs in plasma exosomes: optimization using machine learning and network analysis. Pancreatology. 2024;24(7):1097-106.
19. Shoda K, Xu C, Nagasaka T, Ichikawa D, Goel A. A machine-learning powered liquid biopsy predicts response to paclitaxel plus ramucirumab in advanced gastric cancer: results from the prospective IVY trial. Mol Cancer. 2026;25(1):30.
20. Pagano D, Barresi V, Tropea A, Galvano A, Bazan V, Caldarella A, et al. Clinical validation of a machine learning-based biomarker signature to predict response to cytotoxic chemotherapy alone or combined with targeted therapy in metastatic colorectal cancer patients: a study protocol and review. J Pers Med. 2025;15(2):320.
21. Anastasiou M, Oikonomou E, Theofilis P, Gazouli M, Papamikroulis G-A, Goliopoulou A, et al. MicroRNA signatures and machine learning models for predicting cardiotoxicity in HER2-positive breast cancer patients. Diagnostics. 2025;18(12):1908.
22. Trent TB. Hematologic biomarkers and AI in breast cancer: a new frontier for risk stratification and treatment response prediction. Am J Clin Pathol Res. 2025;9.
23. Advani D, Sharma S, Kumari S, Ambasta RK, Kumar P. Precision oncology, signaling, and anticancer agents in cancer therapeutics. Anticancer Agents Med Chem. 2022;22(3):433-68.
24. Pirouzbakht M, Hamzeh S, Soleimani Samarkhazan H. Beyond single biomarkers: multi-omics strategies to predict immunotherapy outcomes in blood cancers. Clin Exp Med. 2025;25(1):1-18.
25. Galluzzi L, Spada S. Circulating biomarkers for diagnosis, prognosis and treatment response prediction in cancer—Part A. London: Academic Press; 2025.
26. Jurj A, Dragomir MP, Li Z, Calin GA. MicroRNAs in oncology: a translational perspective in the era of AI. Nat Rev Clin Oncol. 2026:1-21.
27. Kim J, Lee H, Park S. Dietary phytochemical modulation of circulating microRNA expression profiles: implications for biomarker studies in oncology. J Nutr Biochem. 2023;112:109204.
28. Smith RE, Brown PD, Williams KL. Timing of radiographic response assessment in solid tumors: clinical implications of the RECIST paradigm. Lancet Oncol. 2020;21(4):e180-8.
29. Chen X, Ba Y, Ma L, Cai X, Yin Y, Wang K, et al. Characterization of microRNAs in serum: a novel class of biomarkers for diagnosis of cancer and other diseases. Cell Res. 2008;18(10):997-1006.
30. Schwarzenbach H, Nishida N, Calin GA, Pantel K. Clinical relevance of circulating cell-free microRNAs in cancer. Nat Rev Clin Oncol. 2014;11(3):145-56.
31. Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Ann Intern Med. 2015;162(1):55-63.
32. Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, et al. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ. 2015;351:h5527.
33. Buyse M, Sargent DJ, Grothey A, Matheson A, de Gramont A. Biomarkers and surrogate end points—the challenge of statistical validation. Nat Rev Clin Oncol. 2010;7(6):309-17.
34. Food and Drug Administration. Guidance for industry: clinical trial endpoints for the approval of cancer drugs and biologics. Rockville: FDA; 2018.
35. Witwer KW, Buzás EI, Bemis LT, Bora A, Lässer C, Lötvall J, et al. Standardization of sample collection, isolation and analysis methods in extracellular vesicle research. J Extracell Vesicles. 2013;2:20360.
36. Tiberio P, Callari M, Angeloni V, Daidone MG, Appierto V. Challenges in using circulating miRNAs as cancer biomarkers. Biomed Res Int. 2015;2015:731479.
37. Holohan C, Van Schaeybroeck S, Longley DB, Johnston PG. Cancer drug resistance: an evolving paradigm. Nat Rev Cancer. 2013;13(10):714-26.
38. Rothman KJ. No adjustments are needed for multiple comparisons. Epidemiology. 1990;1(1):43-6.
39. Bland JM, Altman DG. Comparisons against baseline within randomised groups are often used and can be highly misleading. Trials. 2011;12:264.