Quality of Life and Health Sciences

Support Vector Machine Classification of Low Quality of Life Among Breast Cancer Survivors Using Fatigue, Depression, and Social Support Indicators

Aigerim Sadykova iD , Mehdi Rahimi ^* iD

Objective: This study aimed to classify low quality of life among breast cancer survivors using a support vector machine model based on fatigue, depression, and perceived social support indicators.

Methods and Materials: This cross-sectional predictive study was conducted among 312 female breast cancer survivors receiving follow-up care in oncology clinics and survivorship units in Tehran, Iran. Quality of life was assessed using the EORTC QLQ-C30, and participants with global health status/quality-of-life scores below 50 were classified as having low quality of life. Fatigue was measured using the Functional Assessment of Chronic Illness Therapy–Fatigue scale, depression using the Beck Depression Inventory-II, and perceived social support using the Multidimensional Scale of Perceived Social Support. After data screening and standardization, the dataset was divided into stratified training and testing subsets using an 80:20 ratio. A support vector machine classifier with a radial basis function kernel was developed, and model hyperparameters were optimized through grid search and cross-validation.

Findings: Participants with low quality of life had significantly higher depression scores, greater fatigue burden, and lower total perceived social support compared with survivors without low quality of life. Significant differences were also observed in family support, friend support, and significant-other support. The support vector machine model achieved strong classification performance, with cross-validation accuracy of 0.85 and independent test accuracy of 0.84. In the independent test set, sensitivity was 0.79, specificity was 0.87, precision was 0.79, F1-score was 0.79, balanced accuracy was 0.83, and the area under the receiver operating characteristic curve was 0.90. Permutation-based importance analysis showed that fatigue was the most influential predictor, followed by depression, total perceived social support, and family support.

Conclusion: The support vector machine model classified low quality of life among breast cancer survivors with high accuracy, indicating that fatigue, depression, and perceived social support are clinically meaningful indicators for identifying survivors at risk of poor quality of life.

Elastic Net Regression and Gradient Boosting for Predicting Health-Related Quality of Life Among Patients With Chronic Obstructive Pulmonary Disease

Rami Daher iD , Ali Karimi ^* iD , Gabriela Uzcátegui iD

https://doi.org/10.61838/nmxhg438

Objective: This study aimed to develop and compare Elastic Net Regression and Gradient Boosting Regression models for predicting health-related quality of life among patients with chronic obstructive pulmonary disease in Tehran.

Methods and Materials: This cross-sectional predictive modeling study was conducted on 286 patients with chronic obstructive pulmonary disease who were receiving outpatient pulmonary care in Tehran, Iran. Data were collected using a demographic and clinical information form, spirometric indices, the St. George’s Respiratory Questionnaire, the COPD Assessment Test, the modified Medical Research Council dyspnea scale, the Hospital Anxiety and Depression Scale, and physical activity assessment. The total score of the St. George’s Respiratory Questionnaire was considered the primary outcome variable. After data screening, preprocessing, standardization of continuous predictors, and coding of categorical variables, two predictive models were developed: Elastic Net Regression and Gradient Boosting Regression. The dataset was divided into training and testing subsets, and model performance was evaluated using root mean squared error, mean absolute error, and coefficient of determination.

Findings: Bivariate analyses showed that poorer health-related quality of life was significantly associated with higher COPD Assessment Test scores, greater dyspnea severity, lower FEV1 percentage predicted, lower FEV1/FVC ratio, more frequent exacerbations, more hospitalizations, higher anxiety and depression scores, lower physical activity, longer disease duration, higher body mass index, and older age. In the testing dataset, Elastic Net Regression explained 61.9% of the variance in health-related quality of life, with RMSE = 10.12 and MAE = 7.81. Gradient Boosting Regression demonstrated superior predictive performance, explaining 70.4% of the variance, with RMSE = 8.91 and MAE = 6.83. The most important predictors across models were symptom burden, dyspnea, lung function, depression, exacerbation frequency, anxiety, and physical activity.

Conclusion: Gradient Boosting Regression provided more accurate prediction of health-related quality of life than Elastic Net Regression, although both models identified clinically meaningful predictors. These findings support the use of multidimensional predictive modeling to identify chronic obstructive pulmonary disease patients at greater risk of poor quality of life.

Psychological Capital and Quality of Life Among Cancer Survivors: The Mediating Role of Post-Traumatic Growth and the Moderating Role of Fear of Recurrence

Yanelis Batista iD , Thiago Moreira ^* iD

https://doi.org/10.61838/0gpc3m64

Objective: This study aimed to examine the relationship between psychological capital and quality of life among cancer survivors in Brazil, with post-traumatic growth as a mediating variable and fear of cancer recurrence as a moderating variable.

Methods and Materials: This descriptive-correlational cross-sectional study was conducted among 384 adult cancer survivors in Brazil who had completed the main phase of cancer treatment and were receiving follow-up or survivorship care. Participants completed standardized self-report measures assessing psychological capital, post-traumatic growth, fear of cancer recurrence, and quality of life. Data were analyzed using SPSS and AMOS. Pearson correlation coefficients were used to examine relationships among the main variables. Mediation was tested through bootstrapping with 5,000 resamples, and moderation and moderated mediation effects were examined using interaction terms and conditional effect analysis. Model fit was evaluated using χ², CFI, TLI, RMSEA, and SRMR indices.

Findings: Psychological capital was significantly and positively associated with post-traumatic growth (β = 0.45, p < 0.001) and quality of life (β = 0.36, p < 0.001). Post-traumatic growth also had a significant positive effect on quality of life (β = 0.20, p < 0.001). The indirect effect of psychological capital on quality of life through post-traumatic growth was significant (B = 0.10, 95% CI [0.05, 0.16]), indicating partial mediation. Fear of cancer recurrence had a significant negative effect on quality of life (β = -0.42, p < 0.001) and significantly moderated the direct path between psychological capital and quality of life (β = -0.16, p = 0.001) and the path between post-traumatic growth and quality of life (β = -0.12, p = 0.009). The index of moderated mediation was significant (B = -0.002, 95% CI [-0.004, -0.001]).

Conclusion: Psychological capital was associated with better quality of life among cancer survivors both directly and indirectly through post-traumatic growth, while fear of recurrence weakened these positive pathways. These findings highlight the importance of integrating positive psychological resource enhancement with fear-of-recurrence management in survivorship care.

LightGBM-Based Prediction of Poor Quality of Life Among Patients With Heart Failure Using Clinical, Behavioral, and Psychological Features

Rúnar Guðmundsson iD , Elin Sjöberg ^* iD

https://doi.org/10.61838/eqrm4q87

Objective: This study aimed to develop and interpret a LightGBM-based machine learning model for predicting poor quality of life among patients with heart failure using clinical, behavioral, and psychological features.

Methods and Materials: This multicenter cross-sectional predictive modeling study was conducted among 428 patients with heart failure recruited from cardiology outpatient clinics and heart failure units in Sweden. Clinical data included left ventricular ejection fraction, NYHA functional class, duration of heart failure, comorbidities, hospitalization history, blood pressure, heart rate, and medication-related indicators. Behavioral variables included physical activity, sleep quality, and heart failure self-care behaviors. Psychological variables included depressive symptoms, anxiety symptoms, perceived stress, and perceived social support. Quality of life was assessed using the Kansas City Cardiomyopathy Questionnaire, and poor quality of life was defined as an overall summary score below 50. The dataset was divided into training and testing subsets, and an optimized LightGBM model was developed using cross-validation and hyperparameter tuning. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, precision, F1-score, balanced accuracy, and Brier score. SHAP analysis was used for model interpretation.

Findings: Poor quality of life was identified in 174 patients, representing 40.7% of the sample. Compared with patients without poor quality of life, patients with poor quality of life had significantly lower left ventricular ejection fraction, higher NYHA class, longer disease duration, higher comorbidity burden, more previous heart failure hospitalization, lower physical activity, poorer sleep quality, weaker self-care, higher depression, higher anxiety, higher perceived stress, and lower perceived social support. The optimized LightGBM model achieved strong predictive performance in the test set, with an AUC of 0.859, accuracy of 0.806, sensitivity of 0.788, specificity of 0.818, F1-score of 0.764, balanced accuracy of 0.803, and Brier score of 0.137. SHAP analysis identified depressive symptoms, NYHA functional class, sleep quality, anxiety symptoms, previous hospitalization, self-care maintenance, physical activity, ejection fraction, perceived stress, and social support as the most influential predictors.

Conclusion: The LightGBM model demonstrated strong ability to predict poor quality of life among patients with heart failure and showed that quality-of-life impairment is influenced by a combination of clinical severity, behavioral limitations, sleep disturbance, psychological distress, and reduced social support.

Perceptions of Self-Care, Treatment Burden, and Quality of Life Among Adults With Uncontrolled Hypertension: A Grounded Theory Study

Veronica Longo ^* iD , Chidinma Chikwe iD , Mehdi Rostami iD , Kamdin Parsakia iD

https://doi.org/10.61838/3pjyke77

Objective: This study aimed to develop a grounded theory explaining how adults with uncontrolled hypertension perceive and negotiate self-care, treatment burden, and quality of life.

Methods and Materials: This qualitative study was conducted using a grounded theory design among 34 adults with uncontrolled hypertension in Ontario, Canada. Participants were recruited from primary health care clinics, community health centers, and outpatient cardiovascular services through purposive and theoretical sampling. Eligibility criteria included being 30 years of age or older, having a diagnosis of hypertension for at least one year, and having uncontrolled blood pressure based on recent clinical records. Data were collected through semi-structured individual interviews, demographic and clinical information forms, and researcher field notes. Interviews were audio-recorded, transcribed verbatim, and analyzed concurrently with data collection using constant comparative analysis, including initial coding, focused coding, axial coding, and theoretical integration. Recruitment continued until theoretical saturation was achieved.

Findings: The analysis generated one core category, “negotiating control under cumulative treatment burden,” and five main categories: living with an invisible but threatening condition, translating medical advice into daily self-care, carrying the burden of treatment, quality of life under pressure, and reconstructing control through practical adaptation. The findings indicated that participants experienced uncontrolled hypertension as a condition marked by uncertainty, emotional strain, and repeated self-care demands. Treatment burden emerged through the accumulation of medication routines, lifestyle restrictions, home monitoring, appointments, costs, information management, and relational pressures. Participants’ quality of life was affected by worry, guilt, reduced confidence, social restriction, and diminished spontaneity. However, participants also developed adaptive strategies, including selective adherence, family-supported routines, trigger recognition, and realistic self-care prioritization.

Conclusion: Adults with uncontrolled hypertension experience self-care as a continuous negotiation between clinical expectations and everyday capacity. Hypertension care should therefore address treatment burden, emotional distress, feasibility of self-care behaviors, and quality of life alongside blood pressure control.

Explainable XGBoost Modeling of Quality of Life Among Patients with Fibromyalgia Using Pain, Sleep, and Psychological Flexibility Variables

Khadijeh Irandoust ^* iD , Morteza Taheri iD

https://doi.org/10.61838/9khfxt92

Objective: This study aimed to develop and interpret an explainable XGBoost model for predicting quality of life among patients with fibromyalgia based on pain intensity, sleep quality, psychological flexibility, and relevant demographic and clinical variables.

Methods and Materials: This cross-sectional predictive modeling study was conducted among 318 patients with fibromyalgia receiving services from rheumatology and pain management clinics in Tehran, Iran. Data were collected using a demographic and clinical information form, the Short Form Health Survey for quality of life, the Visual Analog Scale for pain intensity, the Pittsburgh Sleep Quality Index for sleep quality, and the Acceptance and Action Questionnaire-II for psychological flexibility. After data screening and preprocessing, quality of life was considered the continuous outcome variable. Predictive modeling was performed using XGBoost regression, and model performance was compared with linear regression, support vector regression, and random forest regression. Model accuracy was evaluated using mean absolute error, root mean square error, coefficient of determination, and cross-validation. SHAP analysis was used to explain the final XGBoost model.

Findings: Correlation analysis showed that quality of life was significantly and negatively associated with pain intensity (r = -0.58, p < 0.01) and poor sleep quality (r = -0.52, p < 0.01), while it was significantly and positively associated with psychological flexibility (r = 0.49, p < 0.01). The XGBoost model demonstrated the strongest predictive performance, with a test MAE of 7.84, test RMSE of 10.18, test R² of 0.66, and cross-validated R² of 0.63. SHAP analysis identified pain intensity as the most influential predictor, followed by poor sleep quality and psychological flexibility.

Conclusion: The findings indicated that quality of life among patients with fibromyalgia can be predicted with acceptable accuracy using an explainable XGBoost model, with pain intensity, sleep quality, and psychological flexibility emerging as the most important predictors.

Quality of Life Among Patients With Heart Failure: A Qualitative Study of Symptom Monitoring, Functional Limitation, and Psychological Uncertainty

Arben Krasniqi iD , Ryan MacDonald ^* iD

https://doi.org/10.61838/j5j67w39

Objective: This study aimed to explore the quality of life experiences of patients with heart failure in Canada, with particular attention to how symptom monitoring, functional limitation, and psychological uncertainty shaped daily functioning, emotional well-being, self-management, and perceived autonomy.

Methods and Materials: This qualitative descriptive study was conducted among 26 adult patients with clinically diagnosed heart failure recruited from outpatient cardiology and heart failure clinics in Canada through purposive sampling. Participants were selected to ensure variation in age, sex, duration of diagnosis, functional status, hospitalization history, and treatment experience. Data were collected using a demographic and clinical information form, semi-structured individual interviews, and researcher field notes. Interviews focused on patients’ experiences of living with heart failure, daily symptom monitoring, physical and social limitations, treatment-related routines, emotional responses, uncertainty about disease progression, and coping strategies. Interviews were audio-recorded, transcribed verbatim, anonymized, and analyzed using conventional qualitative content analysis. Meaning units were extracted, coded inductively, grouped into subcategories and categories, and then abstracted into main themes. Credibility was enhanced through team-based review, member checking, reflexive notes, and an audit trail.

Findings: The analysis identified three main themes explaining quality of life among patients with heart failure. The first theme, living under continuous symptom monitoring, showed that participants constantly observed breathing, swelling, fatigue, weight change, dizziness, and treatment effects, which created both perceived control and emotional vigilance. The second theme, restriction of daily function and social participation, indicated that reduced walking capacity, difficulty climbing stairs, activity pacing, dependence on family members, occupational changes, and social withdrawal weakened autonomy and identity. The third theme, psychological uncertainty and emotional burden, revealed persistent fear of sudden deterioration, hospitalization, disease progression, and mortality. Adaptive coping strategies, including acceptance, family support, spiritual coping, communication with healthcare providers, and prioritizing meaningful activities, moderated but did not eliminate these burdens.

Conclusion: Quality of life among patients with heart failure was shaped by the interaction of symptom vigilance, functional restriction, and psychological uncertainty, indicating the need for patient-centered care that integrates self-management education, emotional support, family involvement, rehabilitation, and early supportive care.

Disease Uncertainty and Quality of Life Among Patients With Inflammatory Bowel Disease: The Mediating Role of Anxiety and Health Literacy

Mette Kristiansen iD , Natalie Singh ^* iD , Nikola Petrović iD

https://doi.org/10.61838/56mqgh55

Objective: This study aimed to examine the relationship between disease uncertainty and quality of life among Canadian adults with inflammatory bowel disease and to determine the mediating roles of anxiety and health literacy in this relationship.

Methods and Materials: This descriptive-correlational study was conducted using a cross-sectional predictive design. The study population consisted of adults with inflammatory bowel disease in Canada, and the final sample included 326 patients recruited from gastroenterology clinics, outpatient digestive disease centers, and patient support networks. Data were collected using a demographic and clinical information form, the Mishel Uncertainty in Illness Scale, the Inflammatory Bowel Disease Questionnaire, the Generalized Anxiety Disorder-7 scale, and the Health Literacy Questionnaire. Data were analyzed using SPSS and AMOS. Pearson correlation coefficients were used to examine relationships among the variables, and structural equation modeling was applied to test the direct and indirect effects of disease uncertainty on quality of life through anxiety and health literacy. The significance of indirect effects was examined using the bootstrap method with 5,000 resamples and 95% confidence intervals.

Findings: Disease uncertainty was significantly and negatively correlated with quality of life (r = -0.61, p < 0.001) and health literacy (r = -0.49, p < 0.001), and significantly positively correlated with anxiety (r = 0.58, p < 0.001). Anxiety was negatively associated with quality of life (r = -0.67, p < 0.001), while health literacy was positively associated with quality of life (r = 0.52, p < 0.001). The structural model showed acceptable fit. Disease uncertainty had significant direct effects on anxiety (β = 0.58, p < 0.001), health literacy (β = -0.49, p < 0.001), and quality of life (β = -0.28, p < 0.001). Anxiety (β = -0.43, p < 0.001) and health literacy (β = 0.24, p < 0.001) significantly predicted quality of life. Bootstrap analysis confirmed significant indirect effects through anxiety and health literacy.

Conclusion: Disease uncertainty was associated with poorer quality of life among patients with inflammatory bowel disease, and this relationship was partially mediated by increased anxiety and reduced health literacy.

Quality of Life and Health Sciences

About the Journal

Current Issue

Articles

Perceptions of Self-Care, Treatment Burden, and Quality of Life Among Adults With Uncontrolled Hypertension: A Grounded Theory Study

Explainable XGBoost Modeling of Quality of Life Among Patients with Fibromyalgia Using Pain, Sleep, and Psychological Flexibility Variables

Disease Uncertainty and Quality of Life Among Patients With Inflammatory Bowel Disease: The Mediating Role of Anxiety and Health Literacy

Support Vector Machine Classification of Low Quality of Life Among Breast Cancer Survivors Using Fatigue, Depression, and Social Support Indicators

Elastic Net Regression and Gradient Boosting for Predicting Health-Related Quality of Life Among Patients With Chronic Obstructive Pulmonary Disease

Quality of Life Among Patients With Heart Failure: A Qualitative Study of Symptom Monitoring, Functional Limitation, and Psychological Uncertainty

Psychological Capital and Quality of Life Among Cancer Survivors: The Mediating Role of Post-Traumatic Growth and the Moderating Role of Fear of Recurrence

LightGBM-Based Prediction of Poor Quality of Life Among Patients With Heart Failure Using Clinical, Behavioral, and Psychological Features

Language

Support Vector Machine Classification of Low Quality of Life Among Breast Cancer Survivors Using Fatigue, Depression, and Social Support Indicators

Elastic Net Regression and Gradient Boosting for Predicting Health-Related Quality of Life Among Patients With Chronic Obstructive Pulmonary Disease

Psychological Capital and Quality of Life Among Cancer Survivors: The Mediating Role of Post-Traumatic Growth and the Moderating Role of Fear of Recurrence

LightGBM-Based Prediction of Poor Quality of Life Among Patients With Heart Failure Using Clinical, Behavioral, and Psychological Features

Perceptions of Self-Care, Treatment Burden, and Quality of Life Among Adults With Uncontrolled Hypertension: A Grounded Theory Study

Explainable XGBoost Modeling of Quality of Life Among Patients with Fibromyalgia Using Pain, Sleep, and Psychological Flexibility Variables

Quality of Life Among Patients With Heart Failure: A Qualitative Study of Symptom Monitoring, Functional Limitation, and Psychological Uncertainty

Disease Uncertainty and Quality of Life Among Patients With Inflammatory Bowel Disease: The Mediating Role of Anxiety and Health Literacy