Personalized prediction of one-year mental health deterioration using adaptive learning algorithms: a multicenter breast cancer prospective study.

Identifying individual patient characteristics that contribute to long-term mental health deterioration following diagnosis of breast cancer (BC) is critical in clinical practice. The present study employed a supervised machine learning pipeline to address this issue in a subset of data from a prospective, multinational cohort of women diagnosed with stage I-III BC with a curative treatment intention. Patients were classified as displaying stable HADS scores (Stable Group; n = 328) or reporting a significant increase in symptomatology between BC diagnosis and 12 months later (Deteriorated Group; n = 50). Sociodemographic, life-style, psychosocial, and medical variables collected on the first visit to their oncologist and three months later served as potential predictors of patient risk stratification. The flexible and comprehensive machine learning (ML) pipeline used entailed feature selection, model training, validation and testing. Model-agnostic analyses aided interpretation of model results at the variable- and patient-level. The two groups were discriminated with a high degree of accuracy (Area Under the Curve = 0.864) and a fair balance of sensitivity (0.85) and specificity (0.87). Both psychological (negative affect, certain coping with cancer reactions, lack of sense of control/positive expectations, and difficulties in regulating negative emotions) and biological variables (baseline percentage of neutrophils, thrombocyte count) emerged as important predictors of mental health deterioration in the long run. Personalized break-down profiles revealed the relative impact of specific variables toward successful model predictions for each patient. Identifying key risk factors for mental health deterioration is an essential first step toward prevention. Supervised ML models may guide clinical recommendations toward successful illness adaptation.

Associations between Physical Exercise, Quality of Life, Psychological Symptoms and Treatment Side Effects in Early Breast Cancer.

Background: Identifying and understanding modifiable factors for the well-being of cancer patients is critical in survivorship research. We studied variables associated with the exercise habits of breast cancer patients and investigated if the achievement of exercise recommendations was associated with enhanced quality of life and/or psychological well-being. Material and Methods. 311 women from Finland, Portugal, Israel, and Italy receiving adjuvant therapy for stage I-III breast cancer answered questions about sociodemographic factors and physical exercise. Quality of life was assessed by the EORTC C30 and BR23 questionnaires. Anxiety and depression were evaluated using the HADS scale. Results: At the beginning of adjuvant therapy and after twelve months, 32% and 26% of participants were physically inactive, 27% and 30% exercised between 30 and 150 minutes per week, while 41% and 45% exercised the recommended 150 minutes or more per week. Relative to other countries, Finnish participants were more likely to be active at baseline and at twelve months (89% vs. 50%, p < 0.001 and 87% vs. 64%, p < 0.001). Participants with stage I cancer were more likely to be active at twelve months than those with a higher stage (80% vs. 70%,p < 0.05). The inactive participants reported more anxiety (p < 0.05) and depression (p < 0.001), lower global quality of life (p < 0.001), and more side effects (p < 0.05) than the others at twelve months. Accordingly, those who remained inactive or decreased their level of exercise from baseline to twelve months reported more anxiety (p < 0.01) and depression (p < 0.001), lower global quality of life (p < 0.001), and more side effects (p < 0.05) than those with the same or increased level of exercise. Conclusion: For women with early breast cancer, exercise was associated with a better quality of life, less depression and anxiety, and fewer adverse events of adjuvant therapy. Trial registration number: NCT05095675. Paula Poikonen-Saksela on behalf of Bounce consortium (https://www.bounce-project.eu/).

Predicting Effective Adaptation to Breast Cancer to Help Women BOUNCE Back: Protocol for a Multicenter Clinical Pilot Study.

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.

Cognitive, emotional, and behavioral mediators of the impact of coping self-efficacy on adaptation to breast cancer: An international prospective study.

OBJECTIVE: The main objective of this prospective multicenter study was to examine whether illness representations of control, affect, and coping behaviors mediate the effects of self-efficacy to cope with cancer on psychological symptoms and overall quality of life, in breast cancer patients. METHOD: Data from 413 women (Mean age = 54.87; SD = 8.01), coming from four countries (i.e., Finland, Israel, Italy, Portugal), who received medical therapy for their early breast cancer, were analyzed. Coping self-efficacy was assessed at baseline. Potential mediators were assessed three months later, and outcomes after six months. RESULTS: Coping self-efficacy was related to all mediators and outcomes. Illness representations of treatment control, positive and negative affect, and certain coping behaviors (mostly, anxiety preoccupation) mediated the effects of coping self-efficacy. Coping self-efficacy was related to each outcome through a different combination of mediators. CONCLUSIONS: Coping self-efficacy is a major self-regulation factor which is linked to well-being through multiple cognitive, emotional, and behavioral pathways. Enhancement of coping self-efficacy should be a central intervention goal for patients with breast cancer, towards promotion of their well-being.

A machine learning-based pipeline for modeling medical, socio-demographic, lifestyle and self-reported psychological traits as predictors of mental health outcomes after breast cancer diagnosis: An initial effort to define resilience effects.

Displaying resilience following a diagnosis of breast cancer is crucial for successful adaptation to illness, well-being, and health outcomes. Several theoretical and computational models have been proposed toward understanding the complex process of illness adaptation, involving a large variety of patient sociodemographic, lifestyle, medical, and psychological characteristics. To date, conventional multivariate statistical methods have been used extensively to model resilience. In the present work we describe a computational pipeline designed to identify the most prominent predictors of mental health outcomes following breast cancer diagnosis. A machine learning framework was developed and tested on the baseline data (recorded immediately post diagnosis) from an ongoing prospective, multinational study. This fully annotated dataset includes socio-demographic, lifestyle, medical and self-reported psychological characteristics of women recently diagnosed with breast cancer (N = 609). Nine different feature selection and cross-validated classification schemes were compared on their performance in classifying patients into low vs high depression symptom severity. Best-performing approaches involved a meta-estimator combined with a Support Vector Machines (SVMs) classification algorithm, exhibiting balanced accuracy of 0.825, and a fair balance between sensitivity (90%) and specificity (74%). These models consistently identified a set of psychological traits (optimism, perceived ability to cope with trauma, resilience as trait, ability to comprehend the illness), and subjective perceptions of personal functionality (physical, social, cognitive) as key factors accounting for concurrent depression symptoms. A comprehensive supervised learning pipeline is proposed for the identification of predictors of depression symptoms which could severely impede adaptation to illness.

Patients Living With Breast Cancer During the Coronavirus Pandemic: The Role of Family Resilience, Coping Flexibility, and Locus of Control on Affective Responses.

The coronavirus disease 2019 (COVID-19) pandemic has strongly affected oncology patients. Many screening and treatment programs have been postponed or canceled, and such patients also experience fear of increased risk of exposure to the virus. In many cases, locus of control, coping flexibility, and perception of a supportive environment, specifically family resilience, can allow for positive emotional outcomes for individuals managing complex health conditions like cancer. This study aims to determine if family resilience, coping flexibility, and locus of control can mitigate the negative affect caused by the pandemic and enhance positive affect in breast cancer patients. One hundred and fifty-four female patients with breast cancer completed the Walsh's Family Resilience Questionnaire, the Perceived Ability to Cope With Trauma Scale, the Positive-Negative Affect Schedule, and the Mini Locus of Control Scale. Family resilience and internality of locus of control contribute significantly to positive affective responses. Family resilience is responsible for mitigating the negative affect perceived during the pandemic and is enhanced by external locus of control. Evidence suggests that clinical psychologists should develop and propose programs to support oncology patients' family resilience, coping flexibility, and internal locus of control, allowing for decreased stress and improved adaptability for effectively managing cancer treatment during the pandemic.

Preventing chemotherapy-induced alopecia: a prospective clinical trial on the efficacy and safety of a scalp-cooling system in early breast cancer patients treated with anthracyclines.

BACKGROUND: Chemotherapy-induced alopecia (CIA) is a distressing side effect of cancer therapy. The trial aimed to assess feasibility and effectiveness of scalp-cooling system DigniCap® to prevent CIA in primary breast cancer patients receiving an anthracycline containing adjuvant chemotherapy (CT). METHODS: Hair loss (HL) was evaluated by patient self-assessment and by the physician according to the Dean's scale at baseline and after each cycle of CT. The primary efficacy endpoint was the patient self-assessment HL score evaluated at least 3 weeks after completing CT. A Dean's scale score of 0-2 (i.e. HL ≤50%) was considered a success. RESULTS: From July 2014 to November 2016, 139 consecutive breast cancer patients were enrolled and received at least one treatment with scalp cooling. Fifty-six out of 131 evaluated patients successfully prevented HL (43%, 95% CI: 34-51%). Twenty-four patients (32%) discontinued the scalp cooling because of alopecia or scalp-cooling related AE, three patients had missing information on CIA, and 48 patients (64%) had a HL greater than 50% after CT. No serious AEs were reported. CONCLUSIONS: DigniCap® System resulted as a promising medical device to be safely integrated in supportive care of early breast cancer patients. Longer follow-up is needed to assess long-term safety and feasibility. CLINICAL TRIAL REGISTRATION NUMBER: NCT03712696.