Associating persistent self-reported cognitive decline with neurocognitive decline in older breast cancer survivors using machine learning: The Thinking and Living with Cancer study

Use of Patient-Reported Outcomes in Risk Prediction Model Development to Support Cancer Care Delivery: A Scoping Review

PURPOSE

The integration of patient-reported outcomes (PROs) into electronic health records (EHRs) has enabled systematic collection of symptom data to manage post-treatment symptoms. The use and integration of PRO data into routine care are associated with overall treatment success, adherence, and satisfaction. Clinical trials have demonstrated the prognostic value of PROs including physical function and global health status in predicting survival. It is unknown to what extent routinely collected PRO data are used in the development of risk prediction models (RPMs) in oncology care. The objective of the scoping review is to assess how PROs are used to train risk RPMs to predict patient outcomes in oncology care.

METHODS

Using the scoping review methodology outlined in the Joanna Briggs Institute Manual for Evidence Synthesis, we searched four databases (MEDLINE, CINAHL, Embase, and Web of Science) to locate peer-reviewed oncology articles that used PROs as predictors to train models. Study characteristics including settings, clinical outcomes, and model training, testing, validation, and performance data were extracted for analyses.

RESULTS

Of the 1,254 studies identified, 18 met inclusion criteria. Most studies performed retrospective analyses of prospectively collected PRO data to build prediction models. Post-treatment survival was the most common outcome predicted. Discriminative performance of models trained using PROs was better than models trained without PROs. Most studies did not report model calibration.

CONCLUSION

Systematic collection of PROs in routine practice provides an opportunity to use patient-reported data to develop RPMs. Model performance improves when PROs are used in combination with other comprehensive data sources.

Self-perceived cognitive impairment in the first year after breast cancer and the identification of at-risk patients

PURPOSE

This study investigated self-reported clinically relevant cognitive impairment of breast cancer patients in routine clinical care and assessed factors associated with new-onset clinically relevant cognitive impairment.

METHODS

Cognitive functioning was assessed before start of any treatment (T0) and at 6 (T6) and 12 (T12) months after diagnosis. Cognitive functioning (CF) was measured on a scale of 0-100 with the EORTC QLQ-C30 questionnaire, and the EORTC pre-defined threshold for clinical importance. Multivariable logistic regression analyses was used to identify factors associated with new-onset clinically relevant cognitive impairment at T6 ((CF > 75 at T0 and CF < 75 at T6 and T12) or (CF > 75 at T0 and T6 and <75 at T12)).

RESULTS

Pre-treatment, 21% of patients reported clinically relevant cognitive impairment. At T12, percentage was 32%; 20% of patients reported new-onset clinically relevant cognitive impairment at T6 and/or T12. New-onset clinically relevant cognitive impairment was associated with chemo(immuno)therapy and impairment in role and emotional functioning. Younger patients and patients receiving chemo(immuno)therapy were more likely to report new-onset clinically relevant cognitive impairment post treatment.

CONCLUSION

One in five breast cancer patients reported clinically relevant cognitive problems before start of treatment. This percentage further increased within the first year, particularly among patients treated with chemo(immuno)therapy. One in five patients reported new-onset clinically relevant cognitive impairment. Ultimately, these patients may benefit from systematic monitoring and potential referral to interventions.

Physical Activity and Cognition: Longitudinal findings from the Thinking and Living with Cancer Study

BACKGROUND

Physical activity can improve cognition; however, little is known regarding the relationships between longitudinal objectively-measured physical activity, cognition, and inflammation in older breast cancer survivors.

METHODS

Older (≥60 yrs) breast cancer survivors (n = 216) and frequency-matched non-cancer controls (n = 216) were assessed at baseline (pre-systemic therapy for survivors) and annually for up to five years. Assessments included hip-worn ActiGraphs worn for seven days, neuropsychological tests, the Functional Assessment of Cancer Therapy-Cognitive Function Perceived Cognitive Impairment (FACT-Cog PCI) subscale, and circulating levels of C-reactive protein (CRP) and interleukin-6 (IL-6). Data were analyzed using linear mixed-effect, random-effect contemporaneous fluctuation, and multi-level mediation models, considering covariates; p < .05 (two-sided) was considered significant.

RESULTS

Survivors had fewer minutes of moderate-to-vigorous physical activity (MVPA) than controls at 36-, 48-, and 60-month time points (p < .03). Fewer survivors met Aerobic Physical Activity Guidelines at 36 months than controls (17.7% vs 33.0%, p = .030). When Guidelines were met (vs not), FACT-Cog PCI scores were 2.1 ± 1.0 (p = .034) points higher. Higher MVPA and meeting Aerobic Guidelines were not related to objective neuropsychological performance. MVPA was inversely associated with CRP and IL-6 (p < .001), but inflammation did not mediate physical activity effects on perceived cognition.

CONCLUSIONS

Older breast cancer survivors were less physically active than older non-cancer controls, especially farther from baseline. Meeting Aerobic Guidelines was associated with better perceived cognition in survivors. Survivorship care should consider physical activity monitoring and referral to rehabilitation and supervised exercise programs to promote physical activity and improve recovery in older survivors.

Prediction of cognitive decline in older breast cancer survivors: the Thinking and Living with Cancer study

PURPOSE

Cancer survivors commonly report cognitive declines after cancer therapy. Due to the complex etiology of cancer-related cognitive decline (CRCD), predicting who will be at risk of CRCD remains a clinical challenge. We developed a model to predict breast cancer survivors who would experience CRCD after systematic treatment.

METHODS

We used the Thinking and Living with Cancer study, a large ongoing multisite prospective study of older breast cancer survivors with complete assessments pre-systemic therapy, 12 months and 24 months after initiation of systemic therapy. Cognition was measured using neuropsychological testing of attention, processing speed, and executive function (APE). CRCD was defined as a 0.25 SD (of observed changes from baseline to 12 months in matched controls) decline or greater in APE score from baseline to 12 months (transient) or persistent as a decline 0.25 SD or greater sustained to 24 months. We used machine learning approaches to predict CRCD using baseline demographics, tumor characteristics and treatment, genotypes, comorbidity, and self-reported physical, psychosocial, and cognitive function.

RESULTS

Thirty-two percent of survivors had transient cognitive decline, and 41% of these women experienced persistent decline. Prediction of CRCD was good: yielding an area under the curve of 0.75 and 0.79 for transient and persistent decline, respectively. Variables most informative in predicting CRCD included apolipoprotein E4 positivity, tumor HER2 positivity, obesity, cardiovascular comorbidities, more prescription medications, and higher baseline APE score.

CONCLUSIONS

Our proof-of-concept tool demonstrates our prediction models are potentially useful to predict risk of CRCD. Future research is needed to validate this approach for predicting CRCD in routine practice settings.

Perceived Executive Functioning Deficits After Diagnosis in Women with Non-Metastatic Breast Cancer Prior to Adjuvant Therapies

BACKGROUND

Perceived deficits in executive functioning are among the many difficulties that women diagnosed with breast cancer experience. This study assessed the presence of perceived deficits in executive functioning among women with breast cancer prior to systemic treatment and radiation and associations between perceived deficits in executive function and comorbid fatigue, sleep, and mood disturbance.

METHOD

Participants were recruited following their breast cancer diagnosis and assessed using the Behavior Rating Inventory of Executive Function for Adults (BRIEF-A), subjective and objective measures of sleep duration and efficiency, and self-report measures of insomnia severity, sleep quality, fatigue, and mood disturbance. Hierarchical regression was used to examine associations between symptoms, adjusting for age and education.

RESULTS

The final sample included 92 women with a mean age of 60.7 years and 13.5 years of education. Thirteen percent of participants reported global executive dysfunction. After partitioning out variability from other independent variables, fatigue (p = < .001), perceived sleep quality (p = .030), and symptoms of insomnia (p = .008) accounted for 13.3%, 5.7%, and 8.5% of unique variance in perceived executive functioning, respectively. Emotional fatigue was most strongly associated with perceived deficits in executive functioning. Neither subjective or objective sleep duration or efficiency was associated with perceived deficits in executive functioning.

CONCLUSION

Fatigue, particularly emotional fatigue, insomnia, and poor sleep quality had the strongest associations with perceived deficits in executive functioning. Sleep interventions and fatigue management strategies may prove useful for women who seek to improve their perceived executive functioning.