Quality of life and perceived care in Lynch syndrome: Associated factors and interpretable machine-learning classification.

Authors

Marta Araujo-Blesa, Manuel Pabón-Carrasco, Cristina García-Muñoz, Elena Aguado-Domínguez, Isabel María Alonso-Bellido, Miguel Fernández-Tenorio, Leticia Garduño-Ronquillo, Raquel Ruiz-Íñiguez

Published in

European journal of oncology nursing : the official journal of European Oncology Nursing Society. Volume 84. Pages 103322. Sep 10, 2026. Epub Sep 10, 2026.

Abstract

To examine associations between pathogenic variant carrier status, cancer status, health-related quality of life (QoL), and perceived quality of care in Lynch syndrome, and to inform oncology nursing supportive care.
This cross-sectional study included 288 adults with Lynch syndrome carrying a pathogenic germline variant, with or without a history of cancer, and non-carrier relatives. Clinical and demographic data were extracted from medical records. QoL and perceived quality of care were assessed using validated instruments. Analyses included descriptive and inferential statistics, logistic regression, and supervised machine learning models (Decision Tree, Random Forest, Gradient Boosting, and Logistic Regression).
Overall, 61.8% of participants were pathogenic variant carriers and 27.4% had a history of cancer, predominantly colorectal cancer. Carriers reported poorer QoL, with lower physical and cognitive functioning and greater symptom burden, particularly fatigue, insomnia, and pain. Participants with a history of cancer also showed poorer physical functioning than those without cancer (22.4 vs. 63.2; p < 0.001). Satisfaction with clinical care was high, whereas satisfaction with administrative services was lower. Logistic Regression showed the highest predictive performance (AUC = 0.826; accuracy = 80.4%). Physical functioning and family history of cancer were the strongest predictors of pathogenic variant carrier status.
Personalised supportive care is needed for individuals with Lynch syndrome. Oncology nurses play a key role in symptom assessment, patient education, psychosocial support, and care coordination. Supervised machine learning may complement conventional statistical analyses by identifying patients with greater supportive care needs, although external validation is required before clinical implementation.

PMID:
42731507
Bibliographic data and abstract were imported from PubMed on 13 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.