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

Κούρου, Κωνσταντίνα; Manikis, Georgios C.; Poikonen‐Saksela, Paula; Mazzocco, Ketti; Pat‐Horenczyk, Ruth; Sousa, Berta; Oliveira‐Maia, Albino J.; Mattson, Johanna; Roziner, Ilan; Pettini, Greta; Kondylakis, Haridimos; Marias, Kostas; Karademas, Evangelos C.; Simos, Panagiotis G.; Fotiadis, Dimitrios I.

doi:10.1016/j.compbiomed.2021.104266

Cited by 35 publications

(15 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Tu et al (2020), trait resilience significantly predicted high levels of perceived growth and health-related quality of life in breast cancer patients. Kourou et al (2021) also identified low resilience as a heavy predictor of depression in a sample of 609 women recently diagnosed with breast cancer, and Mohlin et al (2020) showed that higher levels of psychological resilience were significantly related to increased levels of health-related quality of life in women with newly diagnosed breast cancer. These last authors assert that assessment of resilience at the time of breast cancer diagnosis might enable early detection of women in need of more intense psychosocial support.…”

Section: Discussionmentioning

confidence: 97%

Resilience in Newly Diagnosed Breast Cancer Women: The Predictive Role of Diurnal Cortisol and Social Support

Aizpurua-Perez,

Arregi,

Gonzalez

et al. 2023

Biological Research For Nursing

View full text Add to dashboard Cite

Background Breast cancer is currently the most prevalent malignancy among women. Psychological resilience is an important factor that diminishes the stress-related emotional and psychosocial disturbances triggered when receiving the diagnosis. Furthermore, resilience appears to be associated with cortisol, the hormonal end-product of the hypothalamic-pituitary-adrenal axis; however, further studies are needed due to the mixed results reported. Thus, we aim to examine the predictive role of social support and cortisol in resilience among breast cancer patients. Methods A total of 132 women with primary breast cancer completed the Medical Outcomes Study-Social Support Survey (MOS-SSS) and the Resilience Scale (RS-14) and provided four salivary samples for the estimation of participants’ total daily cortisol production, for which the formula of the area under the curve with respect to the ground (AUCg) was applied. Moderation analyses were performed to study the influence of social support and AUCg on psychological resilience levels. Results The regression analyses showed a direct significant effect for the emotional support subscale of MOS-SSS on resilience and the interaction between emotional support and AUCg was also found to be statistically significant. Specifically, the conditional effect of emotional support on resilience was found to be significant at middle ( M = 3.08; p < .05) and low levels ( M = .59; p < .001) of AUCg. Conclusions Our results suggest that newly diagnosed breast cancer women with middle and low diurnal cortisol profiles may benefit more from emotional support based-interventions while women with high diurnal cortisol may need more individualized therapies.

show abstract

Section: Discussionmentioning

confidence: 97%

Resilience in Newly Diagnosed Breast Cancer Women: The Predictive Role of Diurnal Cortisol and Social Support

Aizpurua-Perez,

Arregi,

Gonzalez

et al. 2023

Biological Research For Nursing

View full text Add to dashboard Cite

show abstract

“…In recent years, machine learning has been widely used in risk prediction and disease screening, which has obtained excellent performance ( Kwon et al, 2020 ; Meng et al, 2020 ; Cobb et al, 2021 ; Koteluk et al, 2021 ; Kourou et al, 2021 ). Therefore, in this research, XGBoost, an integrated machine learning algorithm, was applied to identify the complex non-linear relationship between HF and clinical variables, as well as to evaluate the importance of the variables to the HF.…”

Section: Discussionmentioning

confidence: 99%

Clinical Prediction of Heart Failure in Hemodialysis Patients: Based on the Extreme Gradient Boosting Method

et al. 2022

View full text Add to dashboard Cite

Background: Heart failure (HF) is the main cause of mortality in hemodialysis (HD) patients. However, it is still a challenge for the prediction of HF in HD patients. Therefore, we aimed to establish and validate a prediction model to predict HF events in HD patients.Methods: A total of 355 maintenance HD patients from two hospitals were included in this retrospective study. A total of 21 variables, including traditional demographic characteristics, medical history, and blood biochemical indicators, were used. Two classification models were established based on the extreme gradient boosting (XGBoost) algorithm and traditional linear logistic regression. The performance of the two models was evaluated based on calibration curves and area under the receiver operating characteristic curves (AUCs). Feature importance and SHapley Additive exPlanation (SHAP) were used to recognize risk factors from the variables. The Kaplan–Meier curve of each risk factor was constructed and compared with the log-rank test.Results: Compared with the traditional linear logistic regression, the XGBoost model had better performance in accuracy (78.5 vs. 74.8%), sensitivity (79.6 vs. 75.6%), specificity (78.1 vs. 74.4%), and AUC (0.814 vs. 0.722). The feature importance and SHAP value of XGBoost indicated that age, hypertension, platelet count (PLT), C-reactive protein (CRP), and white blood cell count (WBC) were risk factors of HF. These results were further confirmed by Kaplan–Meier curves.Conclusions: The HF prediction model based on XGBoost had a satisfactory performance in predicting HF events, which could prove to be a useful tool for the early prediction of HF in HD.

show abstract

“…However, to our knowledge, our study is the first to develop a classification machine learning model for PGD. In addition, while previous studies focused on the training and evaluation of the model [52], [53], [99], in our study, we had also codesigned and developed an online platform which could be used to implement the model by collecting data from users and providing meaningful explanation for users about their grief.…”

Section: Discussionmentioning

confidence: 99%

“…While such models could be useful in screening for psychological disorders from a public health perspective, they require users to be members of such services and have an active digital profile. An example of a study in the second group is one that aims to develop models to classify people with cancer into those with low and high levels of depression [52]. Another study utilized features such as physical health disorders, demographics and psychiatric disorders to predict suicide risk [53].…”

Section: Machine Learning Models To Monitor For Psychological Disordersmentioning

confidence: 99%

Investigation of a Web-Based Explainable AI Screening for Prolonged Grief Disorder

et al. 2022

View full text Add to dashboard Cite

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

Cited by 35 publications

References 36 publications

Resilience in Newly Diagnosed Breast Cancer Women: The Predictive Role of Diurnal Cortisol and Social Support

Resilience in Newly Diagnosed Breast Cancer Women: The Predictive Role of Diurnal Cortisol and Social Support

Clinical Prediction of Heart Failure in Hemodialysis Patients: Based on the Extreme Gradient Boosting Method

Investigation of a Web-Based Explainable AI Screening for Prolonged Grief Disorder

Contact Info

Product

Resources

About