Identifying actionable targets: predicting imatinib nonadherence in patients with gastrointestinal stromal tumors

Gastrointestinal stromal tumors (GISTs) are a rare mesenchymal neoplasm with an incidence of 1 to 1.5 new cases per 100,000 patients annually, most commonly arising in the stomach (1). The most significant prognostic factors for patients with GISTs are most commonly tumor location, size and number of mitoses (2). Currently, the standard of care for patients who present with localized disease is surgical resection with negative margins. However, the use of imatinib mesylate (imatinib), a tyrosine kinase inhibitor targeting KIT and PDGFRA, over the past 2 decades has revolutionized the management of patients with GIST, especially in the adjuvant setting (3).

Several landmark randomized controlled trials have firmly established the clinical benefit of imatinib in the adjuvant setting, demonstrating significantly improved oncologic outcomes for patients at high risk of recurrence. First, the American College of Surgeons Oncology Group (ACOSOG) Z9001 trial published in 2009 was a phase III, double-blind, placebo-controlled, multicenter study which compared recurrence free survival between patients treated with 1-year of imatinib after curative-intent resection versus placebo (3). Not only was imatinib found to be well tolerated, but it significantly improved recurrence free survival (8%) compared to those in the placebo group (20%) as well. However, as recurrence for patients with GISTs remained high in the first years after imatinib discontinuation, it was postulated that 1-year of treatment may be too short in terms of treatment duration which led to the Scandinavian Sarcoma Group XVIII/AIO trial published in 2012 which compared 3- vs. 1-year of adjuvant imatinib (4). Of the 400 patients included in the trial, those treated with 3 years of adjuvant imatinib had significantly improved recurrence free and overall survival. Most recently, the IMADGIST trial compared 3- vs. 6-year of adjuvant imatinib, similarly demonstrating improved recurrence free survival for patients treated with 6 years of therapy (5).

Despite this strong evidence, patient adherence rates are reportedly low most likely due to the duration of treatment as well as relief of any symptoms after surgery. However, poor patient adherence to the prescribed regimen has the potential to negatively impact oncologic outcomes. For example, one previous study found that nearly 60% of patients with GISTs were nonadherent with imatinib prescription recommendations (6).

Liu et al. should be commended for their work in their recent publication entitled “Imatinib adherence prediction using machine learning approach in patients with gastrointestinal stromal tumor” as they set out to explore imatinib adherence using both machine and deep learning prediction models to identify associated risk factors (7). This study included nearly 400 adult patients diagnosed with GISTs who received imatinib for at least 1 month. Notably, the authors similarly found that over half of their patient population were nonadherent to imatinib therapy prescription, thus potentially putting them at risk for worse oncologic outcomes. The novel methodologic approach taken by the authors identified that the light gradient boosting machine algorithm demonstrated optimal performance, and additionally, they found that gender, working status, place of residence, and therapeutic drug monitoring were the factors most highly associated with predicting imatinib adherence.

This work has significant clinical implications in terms of identifying barriers to care, specifically imatinib adherence, to potentially improve long-term oncologic outcomes for this patient population. As a next step, the authors could potentially turn this into a real-world clinical application tool which could be used in practice to screen for patients at high risk for imatinib nonadherence and provide them with additional resources and education to ensure improved outcomes. This has been done in several other aspects within the field of oncology as well. For example, numerous cancer survival calculators have been developed, including using machine learning algorithms, which can be used in clinical practice to assist with patient counseling of which this work could be of similar benefit in clinical practice for patients with GISTs (8).

Furthermore, the results of this study could be used to inform the development of targeted interventions through quality improvement projects for patients at high-risk of imatinib nonadherence. Similar work has previously been conducted identifying modifiable risk factors as significant barriers to completing cancer treatment which have the potential to be intervened upon. Specifically, a previously conducted national quality improvement project was designed to identify the most common barriers to completing cancer treatment, and after designing targeted interventions for these barriers, the authors were able to reduce nonadherence rates by nearly 40% (9). Applying quality improvement methods in a similar fashion could similarly reduce the high rates of imatinib nonadherence among patients with GISTs.

In conclusion, Liu et al. should be congratulated for their interesting study and important work. This research has real-world implications by identifying patients most at risk for imatinib nonadherence, and future directions have the potential to improve long-term oncologic outcomes among patients at risk of recurrence with GISTs.

Acknowledgments

None.

Footnote

Provenance and Peer Review: This article was commissioned by the editorial office, Journal of Gastrointestinal Oncology. The article has undergone external peer review.

Peer Review File: Available at https://jgo.amegroups.com/article/view/10.21037/jgo-2026-0362/prf

Funding: None.

Conflicts of Interest: The author has completed the ICMJE uniform disclosure form (available at https://jgo.amegroups.com/article/view/10.21037/jgo-2026-0362/coif). The author has no conflicts of interest to declare.

Ethical Statement: The author is accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Khan J, Ullah A, Waheed A, et al. Gastrointestinal Stromal Tumors (GIST): A Population-Based Study Using the SEER Database, including Management and Recent Advances in Targeted Therapy. Cancers (Basel) 2022;14:3689. [Crossref] [PubMed]
2. Nilsson B, Bümming P, Meis-Kindblom JM, et al. Gastrointestinal stromal tumors: the incidence, prevalence, clinical course, and prognostication in the preimatinib mesylate era--a population-based study in western Sweden. Cancer 2005;103:821-9. [Crossref] [PubMed]
3. Dematteo RP, Ballman KV, Antonescu CR, et al. Adjuvant imatinib mesylate after resection of localised, primary gastrointestinal stromal tumour: a randomised, double-blind, placebo-controlled trial. Lancet 2009;373:1097-104. [Crossref] [PubMed]
4. Joensuu H, Eriksson M, Sundby Hall K, et al. One vs three years of adjuvant imatinib for operable gastrointestinal stromal tumor: a randomized trial. JAMA 2012;307:1265-72. [Crossref] [PubMed]
5. Blay JY, Schiffler C, Bouché O, et al. A randomized study of 6 versus 3 years of adjuvant imatinib in patients with localized GIST at high risk of relapse. Ann Oncol 2024;35:1157-68. [Crossref] [PubMed]
6. Wang Y, Zhang P, Han Y, et al. Adherence to Adjuvant Imatinib Therapy in Patients with Gastrointestinal Stromal Tumor in Clinical Practice: A Cross-Sectional Study. Chemotherapy 2019;64:197-204. [Crossref] [PubMed]
7. Liu L, Yu Z, Chen H, et al. Imatinib adherence prediction using machine learning approach in patients with gastrointestinal stromal tumor. Cancer 2025;131:e35548. [Crossref] [PubMed]
8. Janczewski LM, Cotler J, Zhu X, et al. American College of Surgeons survival calculator for biliary tract cancers: using machine learning to individualize predictions. Surgery 2025;178:108919. [Crossref] [PubMed]
9. Janczewski LM, Yang AD, Reilly E, et al. If We Build It, Why They Do Not Come? An American College of Surgeons National Quality Improvement Collaborative to Understand Barriers to Completion of Cancer Treatment. JCO Oncol Pract 2025;21:1185-92.