scholarly journals An Application of the Multivariate Linear Mixed Model to the Analysis of Shoulder Complexity in Breast Cancer Patients

2016 ◽  
Vol 13 (3) ◽  
pp. 274 ◽  
Author(s):  
Gholamreza Oskrochi ◽  
Emmanuel Lesaffre ◽  
Youssof Oskrochi ◽  
Delva Shamley
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Breast Cancer Patients

A dyadic study of employment outcomes and quality of life in patients with breast cancer and their support persons.

2019 ◽  
Vol 37 (27_suppl) ◽  
pp. 176-176
Author(s):  
Christine M Veenstra ◽  
Thomas Braun ◽  
Chandler McLeod ◽  
Daniela Wittmann ◽  
Sarah T. Hawley
Keyword(s):  
Breast Cancer ◽  
Quality Of Life ◽  
Cancer Patients ◽  
Job Loss ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Employment Outcomes ◽  
Breast Cancer Patients ◽  
Employment Impacts

176 Background: Many women with breast cancer face job loss related to their diagnosis, but little is known about employment outcomes among their partners and other supporters. Moreover, virtually nothing is known about associations between patients’ quality of life and supporters’ employment outcomes. Methods: Breast cancer patients reported to Georgia and LA SEER registries in 2014-15 (N = 2,502, 68% RR) and their key decision support person (DSP) were surveyed separately. 1234 DSPs responded (71% RR). Patients and DSPs were asked about employment impacts of the patient’s breast cancer. Patients’ quality of life (QOL) was measured with the PROMIS scale for global health. Descriptive analyses of employment outcomes (job loss, missed days due to cancer) were generated for patients and DSPs. Associations between patients’ QOL and employment outcomes of patients and their DSPs were assessed using linear mixed model regression analyses stratified by dyad type (partner vs. non-partner DSP). Results: Among DSPs, 43% were partners. 57% were non-partners (daughters, other family, friends). 67% were employed at time of patient’s diagnosis. Among these, 11% were no longer employed at survey completion. 39% missed >30 days work. Non-partner DSPs were as likely as partners to lose their job or miss work because of the patient’s cancer. 65% patients were employed at diagnosis. Compared to patients whose DSP was a partner, patients with non-partner DSP were more likely to lose their job (39% vs. 24%; p<0.01) or miss >30 days work (55% vs. 45%; p<0.01). For patients with partner and non-partner DSPs, having an employed DSP at diagnosis and having an employed DSP who stays employed were associated with improved patient QOL after adjustment for DSP sociodemographic and patient clinical variables. Conclusions: Both non-partner and partner DSPs faced negative employment impacts related to patients’ breast cancer. Job loss and >30 days of missed work were more likely among patients with non-partner DSPs. Having an employed DSP and having an employed DSP who stays employed positively contributed to patients’ QOL.

Understanding the Relationship between Mood Symptoms and Mobile App Engagement Among Breast Cancer Patients: A Machine Learning Process (Preprint)

2021 ◽  
Author(s):  
Anna N Baglione ◽  
Lihua Cai ◽  
Aram Bahrini ◽  
Isabella Posey ◽  
Mehdi Boukhechba ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Mental Health ◽  
Random Forest ◽  
Cancer Patients ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Self Report ◽  
Breast Cancer Patients ◽  
The Relationship

BACKGROUND Health interventions delivered via smart devices are increasingly being used to address mental health challenges associated with cancer treatment. Engagement with mobile interventions has been associated with treatment success, yet the relationship between mood and engagement among cancer patients remains poorly understood. One reason is the lack of a data-driven process for analyzing mood and app engagement data for cancer patients. OBJECTIVE The purpose of this study is to provide a step-by-step process for using app engagement metrics to predict continuously assessed mood outcomes in breast cancer patients. We describe the steps of data preprocessing, feature extraction, and data modeling and prediction. We then apply this process as a case study to data collected from breast cancer patients who engaged with a mobile mental health app intervention (IntelliCare) over 7-weeks. We compare engagement patterns over time (e.g., frequency, days of use) between high- and low-anxious and high- and low-depressed participants. We then use a Linear Mixed Model to identify significant effects and evaluate the performance of Random Forest and XGBoost classifiers in predicting weekly state mood from baseline affect and engagement features. METHODS We describe the steps of data preprocessing, feature extraction, and data modeling and prediction. We then apply this process as a case study to data collected from breast cancer patients who engaged with a mobile mental health app intervention (IntelliCare) over 7-weeks. We compare engagement patterns over time (e.g., frequency, days of use) between high- and low-anxious and high- and low-depressed participants. We then use a Linear Mixed Model to identify significant effects and evaluate the performance of Random Forest and XGBoost classifiers in predicting weekly state mood from baseline affect and engagement features. RESULTS We observed differences in engagement patterns between high- and low-anxious and depressed participants. Linear Mixed Model results varied by the featureset; these results revealed weak effects for several features of engagement, including duration-based metrics and frequency. Accuracy of predicting state mood varied according to classifier and featureset. The XGBoost classifier achieved the highest accuracy for state anxiety prediction when self-report scores and engagement features were used for only the most highly-used apps. The Random Forest classifier achieved the highest accuracy for state depression prediction when self-report scores and engagement features were used from all apps. CONCLUSIONS The results from the case study support the feasibility and potential of our analytic process for understanding the relationship between app engagement and mood outcomes in breast cancer patients. The ability to leverage both self-report and engagement features to predict state mood during an intervention could be used to enhance decision-making for researchers and clinicians, as well as assist in developing more personalized interventions for breast cancer patients.

scholarly journals Impact of the COVID-19 pandemic on patient-reported outcomes of breast cancer patients and survivors

2020 ◽  
Author(s):  
Claudia A Bargon ◽  
Marilot C T Batenburg ◽  
Lilianne E van Stam ◽  
Dieuwke R Mink van der Molen ◽  
Iris E van Dam ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Social Functioning ◽  
Cancer Patients ◽  
Active Treatment ◽  
Patient Reported Outcomes ◽  
Mixed Model ◽  
Emotional Functioning ◽  
Breast Cancer Patients ◽  
Patient Reported ◽  
The Impact

Abstract Background The COVID-19 pandemic (officially declared on the 11th of March, 2020), and the resulting measures, are impacting daily life and medical management of breast cancer patients and survivors. We evaluated to what extent these changes have affected quality of life, physical and psychosocial wellbeing of patients (being) treated for breast cancer. Methods This study was conducted within a prospective, multicentre cohort of breast cancer patients and survivors (UMBRELLA). Shortly after the implementation of COVID-19 measures, an extra survey was sent to 1,595 participants, including validated EORTC QLQ-C30/BR23 and HADS questionnaires. Patient-reported outcomes (PROs) were compared to the most recent PROs collected within UMBRELLA pre-COVID-19. The impact of COVID-19 on PROs was assessed using mixed model analysis, adjusting for potential confounders. Results 1,051 patients and survivors (65.9%) completed the survey; 31.1% (n = 327) reported a higher threshold to contact their general practitioner amid the COVID-19 pandemic. A statistically significant deterioration in emotional functioning was observed (82.6 [SD = 18.7] to 77.9 [SD = 17.3], p &lt; .001), and 505 (48.0%, 95%CI = 45.0 to 51.1%) reported moderate to severe loneliness. Small improvements were observed in QoL, physical-, social- and role functioning. In the subgroup of 51 patients under active treatment, social functioning strongly deteriorated (77.3 [95%CI = 69.4 to 85.2] to 61.3 [95%CI = 52.6 to 70.1], p = .002). Conclusion During the COVID-19 pandemic, breast cancer patients and survivors were less likely to contact physicians and experienced a deterioration in their emotional functioning. Patients undergoing active treatment reported a substantial drop in social functioning. One in two reported loneliness that was moderate or severe. Online interventions supporting mental health and social interaction are needed during times of social distancing and lockdowns.

Sign in / Sign up

Export Citation Format

Share Document