Social and Health-Related Factors Associated with Enrollment in Medicare Advantage Plans in Older Adults

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 (β = -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.

Healthcare utilization and costs among high-need and frail Mexican American Medicare beneficiaries

Objectives

To examine Medicare health care spending and health services utilization among high-need population segments in older Mexican Americans, and to examine the association of frailty on health care spending and utilization.

Methods

Retrospective cohort study of the innovative linkage of Medicare data with the Hispanic Established Populations for the Epidemiologic Study of the Elderly (H-EPESE) were used. There were 863 participants, which contributed 1,629 person years of information. Frailty, cognition, and social risk factors were identified from the H-EPESE, and chronic conditions were identified from the Medicare file. The Cost and Use file was used to calculate four categories of Medicare spending on: hospital services, physician services, post-acute care services, and other services. Generalized estimating equations (GEE) with a log link gamma distribution and first order autoregressive, correlation matrix was used to estimate cost ratios (CR) of population segments, and GEE with a logit link binomial distribution was applied to estimate odds ratios (OR) of healthcare use.

Results

Participants in the major complex chronic illness segment who were also pre-frail or frail had higher total costs and utilization compared to the healthy segment. The CR for total Medicare spending was 3.05 (95% CI, 2.48–3.75). Similarly, this group had higher odds of being classified in the high-cost category 5.86 (95% CI, 3.35–10.25), nursing home care utilization 11.32 (95% CI, 3.88–33.02), hospitalizations 4.12 (95% CI, 2.88–5.90) and emergency room admissions 4.24 (95% CI, 3.04–5.91).

Discussion

Our findings highlight that frailty assessment is an important consideration when identifying high-need and high-cost patients.

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.