Machine learning-derived model for predicting poor post-treatment quality of life in Korean cancer survivors.

PURPOSE: A substantial number of cancer survivors have poor quality of life (QOL) even after completing cancer treatment. Thus, in this study, we used machine learning (ML) to develop predictive models for poor QOL in post-treatment cancer survivors in South Korea. METHODS: This cross-sectional study used online survey data from 1,005 post-treatment cancer survivors in South Korea. The outcome variable was QOL, which was measured using the global QOL subscale of the European Organization of Cancer and Treatment for Cancer Quality of Life Questionnaire, where a global QOL score < 60.4 was defined as poor QOL. Three ML models (random forest (RF), support vector machine, and extreme gradient boosting) and three deep learning models were used to develop predictive models for poor QOL. Model performance regarding accuracy, area under the receiver operating characteristic curve, F1 score, precision, and recall was evaluated. The SHapely Additive exPlanation (SHAP) method was used to identify important features. RESULTS: Of the 1,005 participants, 65.1% had poor QOL. Among the six models, the RF model had the best performance (accuracy = 0.85, F1 = 0.90). The SHAP method revealed that survivorship concerns (e.g., distress, pain, and fatigue) were the most important factors that affected poor QOL. CONCLUSIONS: The ML-based prediction model developed to predict poor QOL in Korean post-treatment cancer survivors showed good accuracy. The ML model proposed in this study can be used to support clinical decision-making in identifying survivors at risk of poor QOL.

Factors Associated With Quality of Life Among Posttreatment Cancer Survivors in Korea: A Meta-analysis.

BACKGROUND: Identification of factors associated with quality of life (QOL) among cancer survivors is crucial for identifying potential targets for intervention. OBJECTIVES: We aimed to provide evidence of factors associated with the QOL among posttreatment cancer survivors in Korea. METHODS: We performed a systematic literature search from January 2000 to September 2022 using PubMed, EMBASE, CINAHL, PsycINFO, and Korean databases (RISS, SCIENCEON). We evaluated study quality using the Joanna Briggs Institute Quality Appraisal Checklists for Analytical Cross-sectional Studies and performed statistical analysis using the R 3.0 software (R Foundation for Statistical Computing, Vienna, Austria) package. We analyzed the pooled effect sizes of potential QOL correlates by the random-effects model. RESULTS: This meta-analysis included 31 studies with 8934 participants. The pooled estimates were significantly large for economic status (r = -0.53); significantly medium for fatigue (r = -0.39), anxiety (r = -0.29), depression (r = -0.42), self-efficacy (r = 0.37), and social support (r = 0.30); and significantly small for education level (r = -0.18), job status (r = -0.09), cancer stage (r = -0.20), and time since diagnosis (r = -0.26). CONCLUSIONS: Low education level, having no job, low economic status, advanced cancer stage, short disease period, fatigue, anxiety, and depression were significantly associated with worse QOL, whereas self-efficacy and social support were significantly associated with better QOL. IMPLICATIONS FOR PRACTICE: The findings have potential implications for identifying "at-risk survivors" of deteriorated QOL and for suggesting powerful strategies (eg, enhancing self-efficacy or social support) for improving QOL.

Patient Empowerment in Cancer Care: A Scoping Review.

BACKGROUND: Patient empowerment is receiving increasing attention in cancer care, and its relevance has led to a growing body of literature. Empowerment-related evidence, however, has not been comprehensively reviewed. OBJECTIVE: The purpose of this scoping review was to summarize the available evidence on patient empowerment in cancer care. Specifically, we examined how patient empowerment has been defined and measured and what we have learned. METHODS: We searched 6 databases (MEDLINE, PubMed, CINAHL, EMBASE, Cochrane Library, and PsycINFO), adapting key search terms (eg, "neoplasm," "empowerment") to each. Extracted data included author, publication year, country of data collection, main study purpose, study design, sampling method, setting, cancer trajectory, definition of empowerment and its source, measurement of empowerment, correlates, intervention (if applicable), and major results. RESULTS: Of the 2987 articles we initially identified, we included 64 studies (18 quantitative, 9 qualitative, 9 psychometric validation, 8 mixed methods, 6 reviews, and 14 others). Across designs, randomized controlled trials were the most frequent. A comprehensive summary by study designs was provided. CONCLUSIONS: The review highlights the importance of defining the empowerment concept, which is generally vague. There is a paucity of research on examining the relationship between empowerment and its related concepts. More nonexperimental studies (eg, cross-sectional, longitudinal, case-control studies) are required. IMPLICATIONS FOR PRACTICE: Nurses are in an optimal position to engage in the process of empowerment, leading to its benefits. To achieve the best outcomes, nurses need to clarify the definition, select an appropriate measurement, and be trained in empowerment strategies.

Effects of a partnership-based, needs-tailored self-management support intervention for post-treatment breast cancer survivors: A randomized controlled trial.

OBJECTIVE: To examine the effectiveness of partnErship-based, needs-tailored self-Management support Program fOr Women with breast cancER (EMPOWER), a partnership-based, needs-tailored, self-management (SM) support intervention designed to empower post-treatment breast cancer survivors (BCSs) and ultimately improve their health outcomes. METHODS: This multi-center, two-armed, randomized controlled trial comprised 94 female BCSs who had completed primary cancer treatment in South Korea. Participants were randomly assigned (1:1) to the intervention group or the wait-list control group. The intervention group received a 7-week EMPOWER intervention via telephone counseling. The primary outcome was empowerment. Secondary outcomes included self-efficacy for post-treatment SM behaviors, mental adjustment, anxiety, depression, and health-related quality of life. Data were collected via a self-reported questionnaire at baseline (T0) and at 8 (T1) and 20 weeks (T2) of follow-up. Linear mixed models were used to assess group differences over time. Effective sizes were calculated using Cohen's d. RESULTS: Retention rates were excellent (95.7% at T1; 94.7% at T2). Linear mixed model analyses revealed that the EMPOWER group showed significantly improved empowerment (mean difference 2.24, 95% CI = 0.18 to 4.29; p = 0.016) and general health perception (mean difference 3.68, 95% CI = 0.67 to 6.72; p = 0.037) compared with the control group. Time point analysis showed that several secondary outcomes significantly improved at T1, but the effects were not sustained. CONCLUSION: EMPOWER was effective in improving empowerment and general health perception among post-treatment BCS. Further studies are needed to determine the effectiveness of the EMPOWER intervention in other cancer populations.

Psychometric evaluation of patient assessment of chronic illness care among Korean cancer survivors.

BACKGROUND: The Patient Assessment of Chronic Illness Care (PACIC) was developed in the United States to assess the implementation of the Chronic Care Model (CCM)-based intervention from the patient's perspective. Although the psychometric properties of the PACIC have been reported in other chronically ill patients, it has not been reported in cancer survivors. Our aim was to evaluate the acceptability, validity, and reliability of a Korean version of the PACIC among cancer survivors (K-PACIC-CS). METHODS: Among 204 cancer survivors at a university-based hospital in South Korea, we performed psychometric evaluation of the K-PACIC-CS according to acceptability (descriptive statistics, missing values, and floor and ceiling effects), validity (confirmative factor analysis [CFA] and convergent validity), and reliability (internal consistency, i.e., Cronbach's alpha). RESULTS: The item response was high (missing rate = 0.5%). The floor effect was 3.9%- 43.6% and the ceiling effect was 6.9%- 41.2%. The CFA revealed good indices of fit and confirmed the five structures predetermined in the original version of PACIC. The K-PACIC-CS scores had significant positive relationships with cancer survivors' self-efficacy and health-related quality of life. The total K-PACIC-CS showed excellent internal consistency (Cronbach's alpha = .94) and those of the subscales were acceptable (Cronbach's alpha = .76 -.86). CONCLUSIONS: This study suggests that the K-PACIC-CS is a valid and reliable instrument for measuring implementation of CCM-based chronic care from the survivor's perspective.

Design of a randomized controlled trial of a partnership-based, needs-tailored self-management support intervention for post-treatment breast cancer survivors.

BACKGROUND: Self-management is becoming essential for breast cancer survivors, but evidence about the effectiveness of self-management support (SMS) intervention is lacking. To address this issue, we developed a theory-based SMS intervention, the 'EMPOWER', aimed at empowering breast cancer survivors. Here we describe the rationale of the intervention and its development. METHODS: The conceptual framework of this study is the Chronic Care Model, which posits that SMS can influence patient-provider relationships and ultimately improve health outcomes. We will conduct a multi-center, 2-armed randomized controlled trial to assess the effectiveness of EMPOWER among post-treatment breast cancer survivors in South Korea. The trial will include 94 women who completed primary breast cancer treatment within the last 6 months. Participants will be randomly assigned to the intervention group or the wait-list control group (1:1). The intervention group will receive a 7-week partnership-based and needs-tailored SMS intervention via telephone counseling. The primary outcome is empowerment. The secondary outcomes include self-efficacy for post-treatment self-management behaviors, mental adjustment, psychological distress, and health-related quality of life (HRQOL). Data will be collected by self-reported questionnaire at baseline, post-intervention, and 3-month follow-up. DISCUSSION: We believe that the EMPOWER intervention could improve HRQOL of post-treatment breast cancer survivors by enhancing their empowerment. If found successful, it could aid clinicians engaged in the long-term care of breast cancer survivors. TRIAL REGISTRATION: Clinical Research Information Service, KCT0004794. Registered 5 March 2020.