Classifying Refugee Status Using Common Features in EMR**

Morrison, Malia; Nobles, Vanessa; Johnson-Agbakwu, Christa; Bailey, Celeste V.; Liu, Li

doi:10.1002/cbdv.202200651

Cited by 4 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kentucky Office for Refugees reports that Swahili, Arabic, Kinyarwanda, Ukrainian, Bembe, Lingala, Somali, Haitian Creole, Chin, Tigrinya, Mai Mai, Bantu, Pashto, Dari/Farsi, Karen, Kurdish and “Other” are spoken among refugees relocated to Lexington and Louisville, Kentucky [ 7 , 8 ]. The study population included patients with these documented primary languages who are referred to in the paper as “patients with a primary refugee-associated language.” The method of using language, local resettlement data, and geographic location, has been validated for prediction of refugee status [ 9 ].…”

Section: Methodsmentioning

confidence: 99%

COVID-19 in Patients with a Primary Refugee-Associated Language in a Kentucky Emergency Department During 2020

Hamm

Duncan

Robertson

et al. 2022

J Immigrant Minority Health

View full text Add to dashboard Cite

COVID-19 has heavily impacted the refugee population in the United States due to exposure risks, living and working conditions, and healthcare access, but little is known about outcomes. We reviewed emergency department visits to a Kentucky hospital among 2163 patients from March-December 2020, studying incidence of COVID-19 diagnosis for patients with a primary refugee-associated language compared to English speakers, and outcomes after diagnosis including hospitalization, length of stay, and in-hospital mortality. Patients in the population of interest had higher odds of COVID-19 diagnosis in the hospital (OR = 12.31, 95% CI 7.80–19.40), but, among those with COVID-19, lower odds of hospital admission (OR = 0.58, 95% CI 0.37–0.90) and shorter median length of stay (4.1 vs. 10.5 days) compared to English speakers. The study corroborates reports of comparatively higher COVID-19 incidence in patients speaking a primary refugee-associated language, but implies milder illness severity, possibly reflecting this population’s baseline health.

show abstract

Section: Methodsmentioning

confidence: 99%

COVID-19 in Patients with a Primary Refugee-Associated Language in a Kentucky Emergency Department During 2020

Hamm

Duncan

Robertson

et al. 2022

J Immigrant Minority Health

View full text Add to dashboard Cite

show abstract

SARS-CoV-2 Prevalence in a Delivering Refugee Population: Refugee Status, Payor Type, Race, and Vaccination Status

Johnston,

Bhattarai,

Johnson-Agbakwu

et al. 2024

J Immigrant Minority Health

View full text Add to dashboard Cite

Underserved communities were disproportionately affected during the coronavirus (COVID-19) pandemic. Limited data exist on the impact of COVID-19 among refugee populations because refugee status is not often classified in electronic medical record (EMR) systems, unlike race or primary language. The study aim was to evaluate the PCR-based prevalence of SARS-CoV-2 in a delivering population over the first 2 years of the pandemic by refugee status, ethnicity, insurance, and vaccination status. A cross-sectional study examined parturient patients admitted to an urban safety-net hospital from May 2020 to May 2022 who were tested for SARS-CoV-2on admission. Percentages and prevalence ratios of SARS-CoV-2 between refugee status, insurance type, vaccination status, and race/ethnicity were calculated across four time periods, corresponding with variant surges of the pandemic. 3,502 patients delivered, 476 (13.6%) were refugees. Self-pay (46.4%) and Medicaid (46.4%) were the most frequent insurance types with a Hispanic predominance (64.5%) by race/ethnicity. Only 12.8% of patients received at least one vaccine before delivery: 13.2% in non-refugees versus 10.3% refugees 192 (5.5%) of the mothers tested positive during the study period with 6.1% refugees positive versus 5.4% among non-refugees, (prevalence ratio, 1.13; P = 0.53, 95% confidence interval [0.77, 1.66]). Positive tests ranged between 4.7% and 6.3% across insurance types and between 4.4% and 7.5% across race/ethnicity categories. The highest prevalence ratio (refugee/non-refugee) of 2.01 was during the Delta Surge (P = 0.12, 95% confidence interval [0.84, 4.82]) and the lowest prevalence ratio of 0.64 was during the Omicron Surge (P = 0.21, 95% CI [0.32, 1.30]). Among refugees when examined by primary language, 51.7% of positive tests were from those speaking languages of the African Great Lakes region (Kinyarwanda, Kirundi, Swahili, Kiswahili). We observed only small differences in SARS-CoV-2 prevalence between refugees and non-refugees or in vaccination status. Variations in prevalence ratio were seen by refugee status by variant surge. Subsets of the refugee population, when grouped by language/region, appeared to be more affected. This warrants future research on the impact of the SARS-CoV-2 pandemic on specific refugee communities, rather than refugee communities as a heterogenous unit.

show abstract

Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Health Care Professionals

Choudhury,

Chaudhry

2024

J Med Internet Res

View full text Add to dashboard Cite

As the health care industry increasingly embraces large language models (LLMs), understanding the consequence of this integration becomes crucial for maximizing benefits while mitigating potential pitfalls. This paper explores the evolving relationship among clinician trust in LLMs, the transition of data sources from predominantly human-generated to artificial intelligence (AI)–generated content, and the subsequent impact on the performance of LLMs and clinician competence. One of the primary concerns identified in this paper is the LLMs’ self-referential learning loops, where AI-generated content feeds into the learning algorithms, threatening the diversity of the data pool, potentially entrenching biases, and reducing the efficacy of LLMs. While theoretical at this stage, this feedback loop poses a significant challenge as the integration of LLMs in health care deepens, emphasizing the need for proactive dialogue and strategic measures to ensure the safe and effective use of LLM technology. Another key takeaway from our investigation is the role of user expertise and the necessity for a discerning approach to trusting and validating LLM outputs. The paper highlights how expert users, particularly clinicians, can leverage LLMs to enhance productivity by off-loading routine tasks while maintaining a critical oversight to identify and correct potential inaccuracies in AI-generated content. This balance of trust and skepticism is vital for ensuring that LLMs augment rather than undermine the quality of patient care. We also discuss the risks associated with the deskilling of health care professionals. Frequent reliance on LLMs for critical tasks could result in a decline in health care providers’ diagnostic and thinking skills, particularly affecting the training and development of future professionals. The legal and ethical considerations surrounding the deployment of LLMs in health care are also examined. We discuss the medicolegal challenges, including liability in cases of erroneous diagnoses or treatment advice generated by LLMs. The paper references recent legislative efforts, such as The Algorithmic Accountability Act of 2023, as crucial steps toward establishing a framework for the ethical and responsible use of AI-based technologies in health care. In conclusion, this paper advocates for a strategic approach to integrating LLMs into health care. By emphasizing the importance of maintaining clinician expertise, fostering critical engagement with LLM outputs, and navigating the legal and ethical landscape, we can ensure that LLMs serve as valuable tools in enhancing patient care and supporting health care professionals. This approach addresses the immediate challenges posed by integrating LLMs and sets a foundation for their maintainable and responsible use in the future.

show abstract

Classifying Refugee Status Using Common Features in EMR**

Cited by 4 publications

References 10 publications

COVID-19 in Patients with a Primary Refugee-Associated Language in a Kentucky Emergency Department During 2020

COVID-19 in Patients with a Primary Refugee-Associated Language in a Kentucky Emergency Department During 2020

SARS-CoV-2 Prevalence in a Delivering Refugee Population: Refugee Status, Payor Type, Race, and Vaccination Status

Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Health Care Professionals

Contact Info

Product

Resources

About