EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Personalized risk prediction of financial toxicity in patients with cancer: an interpretable machine learning study

Haluk Damgacioglu iD, Kalyani Sonawane iD, Gerard A Silvestri, Katherine R Sterba, Elizabeth G Hill, Scott B Cantor, Evan M Graboyes, Ashish A Deshmukh

JNCI Cancer Spectrum · 09.05.2026 · 10 (3)

DOI: 10.1093/jncics/pkag049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JNCI Cancer Spectrum, online erschienen am 05.05.2026. Verfasst von Haluk Damgacioglu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, United States. Hauptthemen laut MEDLINE: Neoplasms, Financial Stress, Machine Learning, Health Expenditures. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCI NIH HHS, American Cancer Society Institutional Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Financial toxicity (FT), the economic stress from medical care, is common among people with cancer and is associated with worse health outcomes. While risk factors for FT are known, personalized FT risk prediction tools to help mitigate FT are lacking.

Methods

This study developed and evaluated machine learning models to predict FT risk using data from the Medical Expenditures Panel Survey—Experiences with Cancer Survivorship Supplement for patients undergoing or within 1 year of cancer treatment. FT was defined as the presence of >1 of the following: bankruptcy, unpaid medical bills, payment concerns, or debt. Several models were trained using demographic, clinical, economic, and social variables. Fine-tuning was performed to enhance sensitivity in predicting FT. The Shapley additive explanations (SHAP) were used for interpretability of the model.

Results

Among 793 people with cancer, 283 (36%) experienced FT. A fine-tuned random forest algorithm achieved an AUROC of 0.84 (95% CI = 0.78 to 0.91) and an accuracy of 0.78 (95% CI = 0.71 to 0.85), with a sensitivity of 0.84 (95% CI = 0.72 to 0.92) and specificity of 0.75 (95% CI = 0.66 to 0.83), demonstrating balanced classification performance. SHAP values identified key predictors of FT risk, including younger age, lower income, higher medical expenditures, and poorer health status. To support clinical implementation, we developed a web-based FT risk calculator (https://hd-research.shinyapps.io/ftriskcalc/).

Conclusion

The fine-tuned random forest algorithm resulted in promising results for predicting personalized FT risk. Integrated into a web-based calculator, the model has strong potential to help mitigate FT by identifying high-risk patients early in the cancer care continuum.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsFinancial StressMachine LearningHealth ExpendituresHumansFemaleRandom ForestPredictive Learning ModelsMiddle AgedMaleAgedRisk FactorsRisk AssessmentBankruptcyPrediction AlgorithmsSensitivity and SpecificityAdult

Autor:innen und Institutionen

  • Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, United States.
  • Hollings Cancer Center, Medical University of South Carolina, Charleston, SC, United States.
  • Division of Pulmonary Medicine, Thoracic Oncology Research Group, Hollings Cancer Center, Medical University of South Carolina, Charleston, SC, United States.
  • Department of Health Services Research, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
  • Department of Otolaryngology-Head and Neck Surgery, Medical University of South Carolina, Charleston, SC, United States.

ORCID-Profile: Haluk Damgacioglu, Kalyani Sonawane

Förderung

  • NCI NIH HHS
  • American Cancer Society Institutional Research

Zitieren

APA

Damgacioglu, H., Sonawane, K., Silvestri, G. A., Sterba, K. R., Hill, E. G., Cantor, S. B., Graboyes, E. M., & Deshmukh, A. A. (2026). Personalized risk prediction of financial toxicity in patients with cancer: an interpretable machine learning study. JNCI Cancer Spectrum, 10(3). https://doi.org/10.1093/jncics/pkag049

Vancouver

Damgacioglu H, Sonawane K, Silvestri GA, Sterba KR, Hill EG, Cantor SB, et al. Personalized risk prediction of financial toxicity in patients with cancer: an interpretable machine learning study. JNCI Cancer Spectrum. 2026;10(3). doi:10.1093/jncics/pkag049

BibTeX
@article{Damgacioglu2026,
  author = {Damgacioglu, Haluk and Sonawane, Kalyani and Silvestri, Gerard A and Sterba, Katherine R and Hill, Elizabeth G and Cantor, Scott B and Graboyes, Evan M and Deshmukh, Ashish A},
  title = {Personalized risk prediction of financial toxicity in patients with cancer: an interpretable machine learning study},
  journal = {JNCI Cancer Spectrum},
  year = {2026},
  volume = {10},
  number = {3},
  doi = {10.1093/jncics/pkag049}
}
Kostenlos starten →