1
|
Bhatt S, Johnson PC, Markovitz NH, Gray T, Nipp RD, Ufere N, Rice J, Reynolds MJ, Lavoie MW, Clay MA, Lindvall C, El-Jawahri A. The Use of Natural Language Processing to Assess Social Support in Patients With Advanced Cancer. Oncologist 2022; 28:165-171. [PMID: 36427022 PMCID: PMC9907037 DOI: 10.1093/oncolo/oyac238] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2022] [Accepted: 10/12/2022] [Indexed: 11/26/2022] Open
Abstract
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.
Collapse
Affiliation(s)
| | - P Connor Johnson
- Corresponding author: P. Connor Johnson, MD, Massachusetts General Hospital Cancer Center, 55 Fruit St., Yawkey 9A, Boston, MA 02114, USA. Tel: +1 617 724 4000; Fax: +1 617 724 1135; E-mail:
| | - Netana H Markovitz
- Department of Medicine, Division of Hematology & Oncology, Massachusetts General Hospital, Boston, MA, USA
| | - Tamryn Gray
- Harvard Medical School, Boston, MA, USA,Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Ryan D Nipp
- Department of Medicine, Division of Hematology & Oncology, Massachusetts General Hospital, Boston, MA, USA,Harvard Medical School, Boston, MA, USA
| | - Nneka Ufere
- Harvard Medical School, Boston, MA, USA,Division of Gastroenterology, Department of Medicine, Massachusetts General Hospital, Brigham and Women’s Hospital, Boston, MA, USA
| | - Julia Rice
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
| | - Matthew J Reynolds
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
| | - Mitchell W Lavoie
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
| | - Madison A Clay
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
| | | | | |
Collapse
|
2
|
Rivera-Hernandez M, Kumar A, Chou LN, Keeney T, Ferdows N, Karmarkar A, Markides KS, Ottenbacher K. Healthcare utilization and costs among high-need and frail Mexican American Medicare beneficiaries. PLoS One 2022; 17:e0262079. [PMID: 35030180 PMCID: PMC8759642 DOI: 10.1371/journal.pone.0262079] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2021] [Accepted: 12/16/2021] [Indexed: 11/26/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Maricruz Rivera-Hernandez
- Department of Health Services, Policy & Practice, Brown University School of Public Health, Providence, Rhode Island, United States of America
- Center for Gerontology and Healthcare Research, Brown University School of Public Health, Providence, Rhode Island, United States of America
- * E-mail:
| | - Amit Kumar
- College of Health and Human Services, Northern Arizona University, Flagstaff, Arizona, United States of America
- Center for Health Equity Research, Northern Arizona University, Flagstaff, Arizona, United States of America
| | - Lin-Na Chou
- Office of Biostatistics, University of Texas Medical Branch, Galveston, Texas, United States of America
- Department of Preventive Medicine and Population Health, University of Texas Medical Branch, Galveston, Texas, United States of America
| | - Tamra Keeney
- Center for Gerontology and Healthcare Research, Brown University School of Public Health, Providence, Rhode Island, United States of America
| | - Nasim Ferdows
- Department of Health Administration and Policy, Hudson College of Public Health, The University of Oklahoma Health Sciences Center, Oklahoma City, OK, United States of America
| | - Amol Karmarkar
- Department of Physical Medicine and Rehabilitation, Virginia Commonwealth University, Richmond, Virginia, United States of America
- Sheltering Arms Institute, Richmond, Virginia, United States of America
| | - Kyriakos S. Markides
- Department of Preventive Medicine and Population Health, University of Texas Medical Branch, Galveston, Texas, United States of America
- Sealy Center on Aging, University of Texas Medical Branch, Galveston, Texas, United States of America
| | - Kenneth Ottenbacher
- Sealy Center on Aging, University of Texas Medical Branch, Galveston, Texas, United States of America
- Division of Rehabilitation Sciences, School of Health Professions, University of Texas Medical Branch, Galveston, Texas, United States of America
| |
Collapse
|
3
|
Johnson PC, Markovitz NH, Gray TF, Bhatt S, Nipp RD, Ufere N, Rice J, Reynolds MJ, Lavoie MW, Topping CEW, Clay MA, Lindvall C, El-Jawahri A. Association of Social Support With Overall Survival and Healthcare Utilization in Patients With Aggressive Hematologic Malignancies. J Natl Compr Canc Netw 2021:1-7. [PMID: 34653964 DOI: 10.6004/jnccn.2021.7033] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2020] [Accepted: 03/02/2021] [Indexed: 11/17/2022]
Abstract
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.
Collapse
Affiliation(s)
- P Connor Johnson
- 1Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital
- 2Harvard Medical School
| | - Netana H Markovitz
- 1Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital
| | - Tamryn F Gray
- 2Harvard Medical School
- 3Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute
| | - Sunil Bhatt
- 1Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital
| | - Ryan D Nipp
- 1Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital
- 2Harvard Medical School
| | - Nneka Ufere
- 2Harvard Medical School
- 4Division of Gastroenterology, Department of Medicine, Massachusetts General Hospital; and
| | - Julia Rice
- 5Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Matthew J Reynolds
- 5Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Mitchell W Lavoie
- 5Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Carlisle E W Topping
- 5Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Madison A Clay
- 5Department of Psychiatry, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Charlotta Lindvall
- 2Harvard Medical School
- 3Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute
| | - Areej El-Jawahri
- 1Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital
- 2Harvard Medical School
| |
Collapse
|