Social Risk Factors are Associated with Risk for Hospitalization in Home Health Care: A Natural Language Processing Study.

J Am Med Dir Assoc

Columbia University School of Nursing, New York City, NY, USA; Center for Home Care Policy & Research, VNS Health, New York, NY, USA; Data Science Institute, Columbia University, New York City, NY, USA.

Published: December 2023

AI Article Synopsis

  • This study developed a natural language processing (NLP) system to identify social risk factors in home health care clinical notes and analyzed their link to hospitalizations or emergency department visits.
  • The research involved a retrospective cohort study of over 86,000 care episodes for nearly 66,000 patients, using expert-guided vocabulary to pinpoint relevant social risks documented in clinical notes.
  • Results showed the NLP system performed well, identifying key risk factors like Social and Physical Environment and highlighting their association with increased hospitalization and ED visits, emphasizing the importance of addressing these factors in patient care.

Article Abstract

Objective: This study aimed to develop a natural language processing (NLP) system that identified social risk factors in home health care (HHC) clinical notes and to examine the association between social risk factors and hospitalization or an emergency department (ED) visit.

Design: Retrospective cohort study.

Setting And Participants: We used standardized assessments and clinical notes from one HHC agency located in the northeastern United States. This included 86,866 episodes of care for 65,593 unique patients. Patients received HHC services between 2015 and 2017.

Methods: Guided by HHC experts, we created a vocabulary of social risk factors that influence hospitalization or ED visit risk in the HHC setting. We then developed an NLP system to automatically identify social risk factors documented in clinical notes. We used an adjusted logistic regression model to examine the association between the NLP-based social risk factors and hospitalization or an ED visit.

Results: On the basis of expert consensus, the following social risk factors emerged: Social Environment, Physical Environment, Education and Literacy, Food Insecurity, Access to Care, and Housing and Economic Circumstances. Our NLP system performed "very good" with an F score of 0.91. Approximately 4% of clinical notes (33% episodes of care) documented a social risk factor. The most frequently documented social risk factors were Physical Environment and Social Environment. Except for Housing and Economic Circumstances, all NLP-based social risk factors were associated with higher odds of hospitalization and ED visits.

Conclusions And Implications: HHC clinicians assess and document social risk factors associated with hospitalizations and ED visits in their clinical notes. Future studies can explore the social risk factors documented in HHC to improve communication across the health care system and to predict patients at risk for being hospitalized or visiting the ED.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10839109PMC
http://dx.doi.org/10.1016/j.jamda.2023.06.031DOI Listing

Publication Analysis

Top Keywords

social risk
48
risk factors
44
clinical notes
20
social
14
risk
14
factors associated
12
health care
12
nlp system
12
factors
11
natural language
8

Similar Publications

Background: Currently, paradoxical findings exist regarding the level of functioning in individuals with Hikikomori (prolonged social withdrawal).

Aims: This systematic review aimed to clarify the functioning, disability, and health of individuals with Hikikomori and their families in comparison to those without Hikikomori.

Method: Relevant studies were searched from April 22 to 25, 2022, using MEDLINE, PsycINFO, Scopus, and two Japanese databases.

View Article and Find Full Text PDF

Objective: To assess the association between prostate-specific antigen (PSA) density (PSAD) and prostate cancer mortality after a benign result on systematic transrectal ultrasonography (TRUS)-guided prostate biopsy.

Patients And Methods: This retrospective study used data from the Finnish Randomised Study of Screening for Prostate Cancer (FinRSPC) collected between 1996 and 2020. We identified men aged 55-71 years randomised to the screening arm with PSA ≥4.

View Article and Find Full Text PDF

This qualitative study was carried out with 30 high-risk pregnant women from a Brazilian referral service in women's health. The objective was to analyze the perception of participants regarding their condition, emphasizing their psychosocial needs, to deepen the understanding of subjective, relational, and sociocultural aspects associated with high-risk pregnancy. Data were collected through interviews and participant observation and then explored by thematic content analysis.

View Article and Find Full Text PDF

Exploring Social-Ecological Pathways From Sexual Identity to Sleep Among Chinese Women: Structural Equation Modeling Analysis.

JMIR Public Health Surveill

January 2025

School of Nursing, Li Ka Shing Faculty of Medicine, The University of Hong Kong, 5/F, Academic Building, 3 Sassoon Road, Pok Fu Lam, Hong Kong, China (Hong Kong), 852 39176972.

Background: Women and sexual minority individuals have been found to be at higher risk for experiencing poor sleep health compared to their counterparts. However, research on the sleep health of sexual minority women (SMW) is lacking in China.

Objective: This study aimed to examine sleep quality and social support for Chinese women with varied sexual identities, and then investigate the in-depth relationships between sexual identity and sleep.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!