Personalized Risk Analysis to Improve the Psychological Resilience of Women Undergoing Treatment for Breast Cancer: Development of a Machine Learning–Driven Clinical Decision Support Tool

Abstract

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.

Evidências de validade da versão brasileira do Cancer Behavior Inventory - Brief Version

“…Como aplicações práticas do instrumento, tem-se: identificar os comportamentos adaptativos e desadaptativos; compreender os mecanismos de enfrentamento do paciente; evidenciar as áreas em que o paciente pode estar enfrentando dificuldades emocionais; monitorar o progresso ao longo do tempo, observando mudanças positivas ou negativas no comportamento; e Rev Gaúcha Enferm. 2024;45:e20230107 planejar cuidados específicos que visem abordar os desafios emocionais e comportamentais que o paciente está vivenciando (8,13,15,16,29,30) .…”

“…A construção de um plano de cuidados de enfermagem mais assertivo e personalizado utilizando o CBI-B/BR requer a análise detalhada das características sociodemográficas (como idade, sexo, escolaridade e renda), do perfil clínico--patológico (tipo de câncer, estágio da doença, tempo de diagnóstico, terapia empregada, comorbidades associadas, entre outros), dos recursos de enfrentamento do paciente (aspectos emocionais, autoestima e resiliência), da rede de apoio/suporte social (família, amigos e comunidade) e dos aspectos culturais do paciente (costumes, espiritualidade e crenças). Além disso, é importante incluir o paciente nesse processo, o que torna o cuidado mais centrado no indivíduo e nas suas necessidades (8,12,13,16,29,30) .…”

Evidence of validity of the Brazilian version of the Cancer Behavior Inventory - Brief Version

“…The CBI-B/BR can be used as an assessment tool and to support nursing care in oncology, encompassing the physical and emotional needs of patients. As practical applications of the instrument, there are: identify adaptive and maladaptive behaviors; understand the patient's coping mechanisms; highlight areas in which the patient may be experiencing emotional difficulties; monitor progress over time, note positive or negative changes in behavior; and plan specific care aimed at addressing the emotional and behavioral challenges that the patient is experiencing (8,13,15,16,29,30) .…”

“…The construction of a more assertive and customized nursing care plan using the CBI-B/BR requires a detailed analysis of sociodemographic characteristics (such as age, gender, education level and income), the clinical-pathological profile (type of cancer, stage of disease, time of diagnosis, therapy, associated comorbidities, among others), the patient's coping resources (emotional aspects, self-esteem and resilience), the support/social support network (family, friends and community) and the cultural aspects of the patient (customs, spirituality and beliefs). Furthermore, it is important to include the patient in this process, which makes healthcare more focused on individuals and their needs (8,12,13,16,29,30) . Rev Gaúcha Enferm.…”

Promoting Artificial Intelligence for Global Breast Cancer Risk Prediction and Screening in Adult Women: A Scoping Review

“…For instance, women who receive high-risk estimates for breast cancer could potentially be motivated to seek a physician early to begin screening and take preventative actions, like hormone therapy replacement or chemoprevention, before breast cancer arises [37]. Some AI models have been designed to also identify those women at high risk for poor psychological resilience after breast cancer diagnosis, to provide early resources to women most in need to improve mental health and quality of life in the future [43]. In addition, AI can serve as a feasible and affordable option, especially in promoting healthcare access in underserved and resource-poor populations [31,37].…”