The Use of Natural Language Processing to Assess Social Support in Patients With Advanced Cancer.

BACKGROUND: Data examining associations among social support, survival, and healthcare utilization are lacking in patients with advanced cancer. METHODS: We conducted a cross-sectional secondary analysis using data from a prospective longitudinal cohort study of 966 hospitalized patients with advanced cancer at Massachusetts General Hospital from 2014 through 2017. We used NLP to identify extent of patients' social support (limited versus adequate as defined by NLP-aided review of the Electronic Health Record (EHR)). Two independent coders achieved a Kappa of 0.90 (95% CI: 0.84-1.00) using NLP. Using multivariable regression models, we examined associations of social support with: 1) OS; 2) death or readmission within 90 days of hospital discharge; 3) time to readmission within 90 days; and 4) hospital length of stay (LOS). RESULTS: Patients' median age was 65 (range: 21-92) years, and a plurality had gastrointestinal (GI) cancer (34.3%) followed by lung cancer (19.5%). 6.2% (60/966) of patients had limited social support. In multivariable analyses, limited social support was not significantly associated with OS (HR = 1.13, P = 0.390), death or readmission (OR = 1.18, P = 0.578), time to readmission (HR = 0.92, P = 0.698), or LOS (ß = -0.22, P = 0.726). We identified a potential interaction suggesting cancer type (GI cancer versus other) may be an effect modifier of the relationship between social support and OS (interaction term P = 0.053). In separate unadjusted analyses, limited social support was associated with lower OS (HR = 2.10, P = 0.008) in patients with GI cancer but not other cancer types (HR = 1.00, P = 0.991). CONCLUSION: We used NLP to assess the extent of social support in patients with advanced cancer. We did not identify significant associations of social support with OS or healthcare utilization but found cancer type may be an effect modifier of the relationship between social support and OS. These findings underscore the potential utility of NLP for evaluating social support in patients with advanced cancer.

Sharing and caring: The impact of social support on quality of life and health outcomes in hematopoietic stem cell transplantation.

BACKGROUND: Social support is crucial for successful recovery after hematopoietic stem cell transplantation (HSCT) and has the potential to affect patient quality of life (QOL) and health outcomes. However, there are limited data on the relationship between a patient's perception of his or her social support and these outcomes. METHODS: The authors conducted a secondary analysis of 250 autologous and allogeneic HSCT recipients enrolled in 2 supportive care trials at Massachusetts General Hospital from April 2011 through February 2016. They assessed social support as a patient's perception of his or her social well-being via the social well-being subscale of the Functional Assessment of Cancer Therapy. The authors used multivariate regression analyses to examine the relationship between pretransplant social well-being and QOL (Functional Assessment of Cancer Therapy-Treatment Outcome Index), psychological distress (Hospital Anxiety and Depression Scale), posttraumatic stress disorder [PTSD] symptoms (PTSD Checklist), fatigue (Functional Assessment of Cancer Therapy-Fatigue), and health care utilization (hospitalizations and days alive and out of the hospital) 6 months after HSCT. RESULTS: Participants were on average 56.4 years old (SD, 13.3 years); 44% (n = 110) and 56% (n = 140) received autologous and allogeneic HSCT, respectively. Greater pre-HSCT social well-being was associated with higher QOL (B = 0.10; 95% CI, 0.06-0.13; P < .001), lower psychological distress (B = -0.21; 95% CI, -0.29 to -0.12; P < .001), and lower PTSD symptoms (B = -0.12; 95% CI, -0.19 to -0.06; P < .001). Pre-HSCT social well-being was not significantly associated with fatigue or health care utilization 6 months after HSCT. CONCLUSIONS: Patients with higher pre-HSCT perceptions of their social support reported better QOL and lower psychological distress 6 months after HSCT. These findings underscore the potential for social support as a modifiable target for future supportive care interventions to improve the QOL and care of HSCT recipients.

Association of Social Support With Overall Survival and Healthcare Utilization in Patients With Aggressive Hematologic Malignancies.

BACKGROUND: Social support plays a crucial role for patients with aggressive hematologic malignancies as they navigate their illness course. The aim of this study was to examine associations of social support with overall survival (OS) and healthcare utilization in this population. METHODS: A cross-sectional secondary analysis was conducted using data from a prospective longitudinal cohort study of 251 hospitalized patients with aggressive hematologic malignancies at Massachusetts General Hospital from 2014 through 2017. Natural Language Processing (NLP) was used to identify the extent of patients' social support (limited vs adequate as defined by NLP-aided chart review of the electronic health record). Multivariable regression models were used to examine associations of social support with (1) OS, (2) death or readmission within 90 days of discharge from index hospitalization, (3) time to readmission within 90 days, and (4) index hospitalization length of stay. RESULTS: Patients had a median age of 64 years (range, 19-93 years), and most were White (89.6%), male (68.9%), and married (65.3%). A plurality of patients had leukemia (42.2%) followed by lymphoma (37.9%) and myelodysplastic syndrome/myeloproliferative neoplasm (19.9%). Using NLP, we identified that 8.8% (n=22) of patients had limited social support. In multivariable analyses, limited social support was associated with worse OS (hazard ratio, 2.00; P=.042) and a higher likelihood of death or readmission within 90 days of discharge (odds ratio, 3.11; P=.043), but not with time to readmission within 90 days or with index hospitalization length of stay. CONCLUSIONS: In this cohort of hospitalized patients with aggressive hematologic malignancies, we found associations of limited social support with lower OS and a higher likelihood of death or readmission within 90 days of hospital discharge. These findings underscore the utility of NLP for evaluating the extent of social support and the need for larger studies evaluating social support in patients with aggressive hematologic malignancies.

Coping in caregivers of patients with hematologic malignancies undergoing hematopoietic stem cell transplantation.

Caregivers of patients with hematologic malignancies undergoing hematopoietic stem cell transplantation (HSCT) must cope with substantial caregiving burden, high rates of psychological distress, and diminished quality of life (QOL). However, data describing coping strategies before HSCT and the association between coping, QOL, and psychological outcomes in this population are lacking. We conducted a secondary analysis of data collected during a multisite randomized clinical trial of a supportive care intervention in HSCT recipients and their caregivers. Caregivers completed the Brief COPE, Hospital Anxiety and Depression Scale, and the Caregiver Oncology Quality of Life Questionnaire to measure coping strategies, psychological distress, and QOL, respectively. We grouped coping into 2 higher-order domains: approach-oriented (ie, emotional support and active coping) and avoidant (ie, self-blame and denial). We used the median split method to describe the distribution of coping and multivariate linear regression models to assess the relationship between coping and caregiver outcomes. We enrolled 170 caregivers, with a median (range) age of 53 (47-64) years. Most were White (87%), non-Hispanic (96%), and female (77%). Approach-oriented coping was associated with less anxiety (ß = -0.210, P = .003), depression symptoms (ß = -0.160, P = .009), and better QOL (ß = 0.526, P = .002). In contrast, avoidant coping was associated with more anxiety (ß = 0.687, P<.001), depression symptoms (ß = 0.579, P < .001), and worse QOL (ß = -1.631, P < .001). Our findings suggest that coping is related to distress and QOL among caregivers of HSCT recipients even before transplant. Hence, caregivers of patients with hematologic malignancies undergoing HSCT may benefit from resources that facilitate adaptive coping with the demands of caregiving.

Association Between Baseline Patient-Reported Outcomes and Complications of Hematopoietic Stem Cell Transplantation.

Hematopoietic cell transplantation (HCT) is a potentially curative therapy for hematologic malignancies, but it often results in significant toxicities and impaired quality of life (QOL). Although the value of patient-reported outcomes (PROs) is increasingly recognized in HCT, data are limited regarding the relationship between PROs and HCT complications. We conducted a secondary data analysis of 250 patients who were hospitalized for autologous or allogeneic HCT at Massachusetts General Hospital from 2011 through 2016. We assessed QOL (Functional Assessment of Cancer Therapy-General), mood (Hospital Anxiety and Depression Scale), and fatigue (FACT-Fatigue) at baseline. We abstracted from the Electronic Health Record (1) hospitalization during the first 100 days after HCT, (2) days alive and out of the hospital in the first 100 days after HCT, and (3) cumulative incidence of acute graft-versus-host disease (GVHD) among allogeneic HCT recipients. We assessed the association of baseline PROs with HCT complications using multivariable models adjusting for patient and transplant characteristics. Overall, 44.4% (111/250) of patients underwent an autologous HCT, 25.2% (63/250) received a myeloablative allogeneic HCT, and 30.4% (76/250) underwent a reduced-intensity allogeneic HCT. In multivariable logistic regression, higher anxiety (odds ratio [OR] = 1.14, P = .004) was associated with higher likelihood of rehospitalization within 100 days after HCT. In multivariable Poisson regression, lower fatigue (ß = 0.003, P = .015) was associated with increased days alive and out of the hospital in the first 100 days post-HCT. In multivariable logistic regression, lower baseline QOL (OR = 0.97, P = .034), higher fatigue (OR = 0.95, P = .004), and higher depression (OR = 1.15, P = .020) were associated with increased likelihood of acute GVHD. Baseline PROs are associated with health care utilization after HCT and risk of acute GVHD in allogeneic HCT recipients. These findings underscore the potential utility of pretransplantation PROs as important prognostic factors for HCT.

Distress in a Pandemic: Association of the Coronavirus Disease-2019 Pandemic with Distress and Quality of Life in Hematopoietic Stem Cell Transplantation.

The global coronavirus disease 2019 (COVID-19) pandemic has drastically disrupted cancer care, potentially exacerbating patients' distress levels. Patients undergoing hematopoietic stem cell transplantation (HSCT) may be especially vulnerable to this pandemic stress. However, the associations of the COVID-19 pandemic with distress, fatigue, and quality of life (QoL) are not well understood in this population. In a cross-sectional analysis of data from 205 patients undergoing HSCT enrolled in a supportive care trial, we compared baseline pre-HSCT distress symptoms (depression, anxiety, and posttraumatic stress disorder [PTSD]), fatigue, and QoL between enrollees before (ie, March 2019-January 2020) and during (ie, March 2020-January 2021) the COVID-19 pandemic. We used linear regression models adjusting for sociodemographics and cancer diagnosis to examine the associations between enrollment period and patient-reported outcomes. We used semistructured qualitative interviews in 20 allogeneic HSCT recipients who were ≥3-months post-HSCT to understand the impact of the COVID-19 pandemic on their recovery post-HSCT. One hundred twenty-four participants enrolled before COVID-19, and 81 participants enrolled during the pandemic. The 2 cohorts had similar baseline demographics and disease risk factors. In multivariate regression models, enrollment during COVID-19 was not associated with pre-HSCT symptoms of depression, anxiety, PTSD, fatigue, or QoL impairment. COVID-19-era participants reported themes of negative (eg, increased isolation) and positive (eg, engagement with meaningful activities) implications of the pandemic on HSCT recovery. We found no differences in pre-HSCT distress, fatigue, or QoL in patients undergoing HSCT before or during the COVID-19 pandemic; however, patients in early recovery post-HSCT report both negative and positive implications of the COVID-19 pandemic in their lives.