Psychosocial Distress and Radiation Treatment Interruptions in Patients With Cancer Using Machine Learning and Regression: Retrospective Cohort Study.
5 affiliations
- 1Center for Biomedical Informatics, College of Medicine, University of Tennessee Health Science Center, 50 N Dunlap Street, Memphis, TN, 38103, United States, 1 9012875836.
- 2Health Equity Program, Rhodes College, Memphis, TN, United States.
- 3University of Tennessee Graduate School of Medicine, Knoxville, TN, United States.
- 4Department of Radiation Oncology, University of Tennessee Health Science Center, College of Medicine, Memphis, TN, United States.
- 5Department of Preventive Medicine, University of Tennessee Health Science Center, College of Medicine, Memphis, TN, United States.
Abstract
Background
Uninterrupted delivery of radiation therapy is critical to cancer treatment quality. Unplanned radiation treatment interruptions compromise tumor control and survival. Although previous studies have explored clinical and sociodemographic factors influencing treatment adherence, the role of psychosocial distress and related symptoms remains unclear.Objective
This study aims to identify patient-reported psychosocial predictors of radiation treatment interruptions from patient-reported distress screening data integrated with clinical and socioeconomic correlates via traditional and machine learning-enhanced modeling.Methods
This institutional cohort study included 1953 patients who underwent external beam radiation therapy between August 2020 and May 2024. Patient demographics, clinical characteristics, treatment details, and baseline distress levels were extracted from a hospital-level electronic health record data repository. Distress was assessed using the Distress Thermometer developed by the National Comprehensive Cancer Network. These data were linked with census tract-level socioeconomic indicators. Predictors of treatment interruption (measured as missed treatment days) were evaluated using negative binomial regression and an extreme gradient boosting (XGBoost) model with a Poisson objective function.Results
The study cohort missed a mean of 1.19 (SD 2.18) treatment days (range: 0-15). Higher distress scores, the presence of learning or communication barriers, and genitourinary malignancy were significantly associated with increased interruption risk in the negative binomial regression model. The XGBoost model confirmed these features as top contributors to prediction performance, while yielding an incrementally lower root mean squared error of 2.19 (vs 2.21 for the regression model).Conclusions
Patient-reported distress and health education barriers were modestly associated with treatment interruptions, underscoring the importance of incorporating psychosocial assessments into radiation oncology workflows. Both parametric and machine learning models provided stable and closely aligned predictions of missed radiation treatment days. Key predictors identified as statistically significant in the regression model were also among the top contributors in the XGBoost model, reinforcing the robustness of these findings and supporting integration of both approaches into future intervention strategies.
Related
- Low Serum Albumin, Body Mass Index, and Feeding Route Predict Treatment Interruptions During Concurrent Chemoradiotherapy in Head and Neck Cancer: A Retrospective Cohort Study
- Treatment patterns and prognostic factors of radiation-associated esophageal fistula in patients with esophageal squamous cell carcinoma: a retrospective cohort study
- Identifying Mild Cognitive Impairment from Routinely Collected Physical, Functional and Psychosocial Measures in Community-Dwelling Older Adults: A Comparative Machine-Learning and Regression Modelling Study in the Northern Japanese ORANGE Registry.
- A retrospective mixed methods analysis of maternal psychosocial health during the COVID-19 pandemic in Ghana: lessons for future public health crises
- Effect of a person-centered care intervention on return and sustained reengagement after treatment interruptions from HIV care in Zambia: A post-hoc analysis of a stepped-wedged cluster randomized trial
BibTeX
@article{hashtarkhani2026psychosocial,
title = {{Psychosocial Distress and Radiation Treatment Interruptions in Patients With Cancer Using Machine Learning and Regression: Retrospective Cohort Study.}},
author = {Soheil Hashtarkhani and Christopher L Brett and Fekede Asefa Kumsa and Rezaur Rashid and Parnian Kheirkhah Rahimabad and Saba Kheirinejad and Robert L Davis and David L Schwartz and Arash Shaban-Nejad},
journal = {JMIR cancer},
year = {2026},
month = oct,
doi = {10.2196/92899},
url = {https://europepmc.org/article/MED/42896154},
note = {CC BY},
}
RIS
TY - JOUR
TI - Psychosocial Distress and Radiation Treatment Interruptions in Patients With Cancer Using Machine Learning and Regression: Retrospective Cohort Study.
AU - Soheil Hashtarkhani
AU - Christopher L Brett
AU - Fekede Asefa Kumsa
AU - Rezaur Rashid
AU - Parnian Kheirkhah Rahimabad
AU - Saba Kheirinejad
AU - Robert L Davis
AU - David L Schwartz
AU - Arash Shaban-Nejad
PY - 2026
DA - 2026/10/19
JO - JMIR cancer
DO - 10.2196/92899
UR - https://europepmc.org/article/MED/42896154
AB - Background Uninterrupted delivery of radiation therapy is critical to cancer treatment quality. Unplanned radiation treatment interruptions compromise tumor control and survival. Although previous studies have explored clinical and sociodemographic factors influencing treatment adherence, the role of psychosocial distress and related symptoms remains unclear.Objective This study aims to identify patient-reported psychosocial predictors of radiation treatment interruptions from patient-reported distress screening data integrated with clinical and socioeconomic correlates via traditional and machine learning-enhanced modeling.Methods This institutional cohort study included 1953 patients who underwent external beam radiation therapy between August 2020 and May 2024. Patient demographics, clinical characteristics, treatment details, and baseline distress levels were extracted from a hospital-level electronic health record data repository. Distress was assessed using the Distress Thermometer developed by the National Comprehensive Cancer Network. These data were linked with census tract-level socioeconomic indicators. Predictors of treatment interruption (measured as missed treatment days) were evaluated using negative binomial regression and an extreme gradient boosting (XGBoost) model with a Poisson objective function.Results The study cohort missed a mean of 1.19 (SD 2.18) treatment days (range: 0-15). Higher distress scores, the presence of learning or communication barriers, and genitourinary malignancy were significantly associated with increased interruption risk in the negative binomial regression model. The XGBoost model confirmed these features as top contributors to prediction performance, while yielding an incrementally lower root mean squared error of 2.19 (vs 2.21 for the regression model).Conclusions Patient-reported distress and health education barriers were modestly associated with treatment interruptions, underscoring the importance of incorporating psychosocial assessments into radiation oncology workflows. Both parametric and machine learning models provided stable and closely aligned predictions of missed radiation treatment days. Key predictors identified as statistically significant in the regression model were also among the top contributors in the XGBoost model, reinforcing the robustness of these findings and supporting integration of both approaches into future intervention strategies.
SN - 2369-1999
ER -