Background Health professionals are often faced with the need to identify women at risk of manifesting poor psychological resilience following the diagnosis and treatment of breast cancer. Machine learning algorithms are increasingly used to support clinical decision support (CDS) tools in helping health professionals identify women who are at risk of adverse well-being outcomes and plan customized psychological interventions for women at risk. Clinical flexibility, cross-validated performance accuracy, and model explainability permitting person-specific identification of risk factors are highly desirable features of such tools. Objective This study aimed to develop and cross-validate machine learning models designed to identify breast cancer survivors at risk of poor overall mental health and global quality of life and identify potential targets of personalized psychological interventions according to an extensive set of clinical recommendations. Methods A set of 12 alternative models was developed to improve the clinical flexibility of the CDS tool. All models were validated using longitudinal data from a prospective, multicenter clinical pilot at 5 major oncology centers in 4 countries (Italy, Finland, Israel, and Portugal; the Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back [BOUNCE] project). A total of 706 patients with highly treatable breast cancer were enrolled shortly after diagnosis and before the onset of oncological treatments and were followed up for 18 months. An extensive set of demographic, lifestyle, clinical, psychological, and biological variables measured within 3 months after enrollment served as predictors. Rigorous feature selection isolated key psychological resilience outcomes that could be incorporated into future clinical practice. Results Balanced random forest classifiers were successful at predicting well-being outcomes, with accuracies ranging between 78% and 82% (for 12-month end points after diagnosis) and between 74% and 83% (for 18-month end points after diagnosis). Explainability and interpretability analyses built on the best-performing models were used to identify potentially modifiable psychological and lifestyle characteristics that, if addressed systematically in the context of personalized psychological interventions, would be most likely to promote resilience for a given patient. Conclusions Our results highlight the clinical utility of the BOUNCE modeling approach by focusing on resilience predictors that can be readily available to practicing clinicians at major oncology centers. The BOUNCE CDS tool paves the way for personalized risk assessment methods to identify patients at high risk of adverse well-being outcomes and direct valuable resources toward those most in need of specialized psychological interventions.
Background Despite the continued progress of medicine, dealing with breast cancer is becoming a major socioeconomic challenge, particularly due to its increasing incidence. The ability to better manage and adapt to the entire care process depends not only on the type of cancer but also on the patient’s sociodemographic and psychological characteristics as well as on the social environment in which a person lives and interacts. Therefore, it is important to understand which factors may contribute to successful adaptation to breast cancer. To our knowledge, no studies have been performed on the combination effect of multiple psychological, biological, and functional variables in predicting the patient’s ability to bounce back from a stressful life event, such as a breast cancer diagnosis. Here we describe the study protocol of a multicenter clinical study entitled “Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back” or, in short, BOUNCE. Objective The aim of the study is to build a quantitative mathematical model of factors associated with the capacity for optimal adjustment to cancer and to study resilience through the cancer continuum in a population of patients with breast cancer. Methods A total of 660 women with breast cancer will be recruited from five European cancer centers in Italy, Finland, Israel, and Portugal. Biomedical and psychosocial variables will be collected using the Noona Healthcare platform. Psychosocial, sociodemographic, lifestyle, and clinical variables will be measured every 3 months, starting from presurgery assessment (ie, baseline) to 18 months after surgery. Temporal data mining, time-series prediction, sequence classification methods, clustering time-series data, and temporal association rules will be used to develop the predictive model. Results The recruitment process stared in January 2019 and ended in November 2021. Preliminary results have been published in a scientific journal and are available for consultation on the BOUNCE project website. Data analysis and dissemination of the study results will be performed in 2022. Conclusions This study will develop a predictive model that is able to describe individual resilience and identify different resilience trajectories along the care process. The results will allow the implementation of tailored interventions according to patients’ needs, supported by eHealth technologies. Trial Registration ClinicalTrials.gov NCT05095675; https://clinicaltrials.gov/ct2/show/NCT05095675 International Registered Report Identifier (IRRID) DERR1-10.2196/34564
Cancer patients’ quality of life (QoL) and distress are affected by dispositional factors such as attachment anxiety or avoidance. In this review, we aimed to provide a thorough overview of the relationship between attachment dimensions and QoL and distress among early-stage breast cancer patients. Following PRISMA guidelines, we conducted a systematic search using PubMed, PsycINFO, Scopus, Cinahl, Google Scholar, and PMC Europe. We reviewed 8 eligible studies describing 1180 patients. Insecure attachment appeared to be related to poorer QoL and higher distress levels. Avoidant attachment was more frequent and was more often associated with more negative outcomes. Healthcare providers should consider investigating modifiable personality traits in the immediate post diagnosis period to identify patients more vulnerable to mental health problems, deliver personalized care, and reduce emotional burden.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.