Dataset Information

Comparison of Use of Health Care Services and Spending for Unauthorized Immigrants vs Authorized Immigrants or US Citizens Using a Machine Learning Model.

ABSTRACT:

Importance

Knowledge about use of health care services (health care utilization) and expenditures among unauthorized immigrant populations is uncertain because of limitations in ascertaining legal status in population data.

Objective

To examine health care utilization and expenditures that are attributable to unauthorized and authorized immigrants vs US-born individuals.

Design, setting, and participants

This cross-sectional study used the data on documentation status from the Los Angeles Family and Neighborhood Survey (LAFANS) to develop a random forest classifier machine learning model. K-fold cross-validation was used to test model performance. The LAFANS is a randomized, multilevel, in-person survey of households residing in Los Angeles County, California, consisting of 2 waves. Wave 1 began in April 2000 and ended in January 2002, and wave 2 began in August 2006 and ended in December 2008. The machine learning model was then applied to a nationally representative database, the 2016-2017 Medical Expenditure Panel Survey (MEPS), to predict health care expenditures and utilization among unauthorized and authorized immigrants and US-born individuals. A generalized linear model analyzed health care expenditures. Logistic regression modeling estimated dichotomous use of emergency department (ED), inpatient, outpatient, and office-based physician visits by immigrant groups with adjusting for confounding factors. Data were analyzed from May 1, 2019, to October 14, 2020.

Exposures

Self-reported immigration status (US-born, authorized, and unauthorized status).

Main outcomes and measures

Annual health care expenditures per capita and use of ED, outpatient, inpatient, and office-based physician care.

Results

Of 47?199 MEPS respondents with nonmissing data, 35?079 (74.3%) were US born, 10?816 (22.9%) were authorized immigrants, and 1304 (2.8%) were unauthorized immigrants (51.7% female; mean age, 47.6 [95% CI, 47.4-47.8] years). Compared with authorized immigrants and US-born individuals, unauthorized immigrants were more likely to be aged 18 to 44 years (80.8%), Latino (96.3%), and Spanish speaking (95.2%) and to have less than 12 years of education (53.7%). Half of unauthorized immigrants (47.1%) were uninsured compared with 15.9% of authorized immigrants and 6.0% of US-born individuals. Mean annual health care expenditures per person were $1629 (95% CI, $1330-$1928) for unauthorized immigrants, $3795 (95% CI, $3555-$4035) for authorized immigrants, and $6088 (95% CI, $5935-$6242) for US-born individuals.

Conclusions and relevance

Contrary to much political discourse in the US, this cross-sectional study found no evidence that unauthorized immigrants are a substantial economic burden on safety net facilities such as EDs. This study illustrates the value of machine learning in the study of unauthorized immigrants using large-scale, secondary databases.

SUBMITTER: Wilson FA

PROVIDER: S-EPMC7733155 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Use of Health Care Services and Spending for Unauthorized Immigrants vs Authorized Immigrants or US Citizens Using a Machine Learning Model.

Wilson Fernando A FA Zallman Leah L Pagán José A JA Ortega Alexander N AN Wang Yang Y Tatar Moosa M Stimpson Jim P JP

JAMA network open 20201201 12

<h4>Importance</h4>Knowledge about use of health care services (health care utilization) and expenditures among unauthorized immigrant populations is uncertain because of limitations in ascertaining legal status in population data.<h4>Objective</h4>To examine health care utilization and expenditures that are attributable to unauthorized and authorized immigrants vs US-born individuals.<h4>Design, setting, and participants</h4>This cross-sectional study used the data on documentation status from ...[more]

PMID: 33306118

Similar Datasets

Project description:Background and aimsEleven million unauthorized immigrants reside in the United States and may account for 3% of deceased organ donors. Recently introduced federal and state legislation propose to address access to organ transplantation among unauthorized immigrants. The national landscape of liver transplantation (LT) for unauthorized immigrants is unknown.Approach and resultsWe included all US LT recipients between March 2012 and December 2018 who were linked to Pew Center of Research data to estimate the population of unauthorized immigrants in each US state and by country of origin, based on US Census data. We categorized patients as unauthorized immigrants versus US citizens/residents. The main outcome measures were (1) the proportion of LTs performed for unauthorized immigrants compared with the proportion of unauthorized immigrants among total population in each US state and (2) graft failure and death post-LT. Of 43,192 LT recipients, 43,026 (99.6%) were US citizens/residents and 166 (0.4%) were unauthorized immigrants. Among unauthorized immigrants, most LTs were performed in California (47%) and New York (18%). The absolute difference in proportion of LTs performed for unauthorized immigrants compared with the proportion of unauthorized immigrants among the total population differed among states, ranging from +20% in California to -12% in Texas. The most common countries of birth among LT recipients who were unauthorized immigrants were Mexico (52%), Guatemala (7%), China (6%), El Salvador (5%), and India (5%). In competing risk analysis, unauthorized immigration status (vs. US citizens/residents) was associated with a similar risk of graft failure (subdistribution hazard ratio [sHR] 0.74; 95% confidence interval [CI], 0.40-1.34; P = 0.38) and death (sHR 0.68; 95% CI, 0.36-1.29; P = 0.23).ConclusionsLT for unauthorized immigrants is rare, and disparities in access to LT by state are present. Patient and graft survival among unauthorized immigrants is comparable with citizens/residents.

Project description:ImportanceStudies using data from before 2011 concluded that the cost of US cancer care is justified given improved outcomes compared with European countries. However, it is unclear whether contemporary US cancer care provides better value than that of other high-income countries.ObjectiveTo assess whether cancer mortality rates in 2020 were lower in countries with higher cancer-related spending, and to estimate across countries the incremental cost per averted cancer death.Design setting and participantsCross-sectional, national-level analysis of 22 high-income countries, assessing the association between cancer care expenditures and age-standardized population-level cancer mortality rates in 2020, with and without adjustment for smoking. In addition, US incremental costs per averted death compared with the other countries were calculated. This study was conducted from September 1, 2021, to March 31, 2022.Main outcomes and measuresAge-standardized population-level cancer mortality rates.ResultsIn this cross-sectional study of 22 countries, the median cancer mortality rate was 91.4 per 100 000 population (IQR, 84.2-101.6). The US cancer mortality rate was higher than that of 6 other countries (86.3 per 100 000). Median per capita spending in USD for cancer care was $296 (IQR, $222-$348), with the US spending more than any other country ($584). After adjusting for smoking, 9 countries had lower cancer care expenditures and lower mortality rates than the US. Of the remaining 12 countries, the US additionally spent more than $5 million per averted death relative to 4 countries, and between $1 and $5 million per averted death relative to 8 countries. Cancer care expenditures were not associated with cancer mortality rates, with or without adjustment for smoking (Pearson R = -0.05 [95% CI, -0.46 to 0.38]; P = .81; and R = -0.05 [95% CI, -0.46 to 0.38]; P = .82).Conclusions and relevanceIn this cross-sectional study of national cancer care expenditures and cancer mortality rates across 22 countries, although the cancer mortality rate in the US was lower than the median, the US spent twice as much on cancer care as the median country. Findings of this study suggest that the US expenditure on cancer care may not be commensurate with improved cancer outcomes.

Project description:BackgroundDespite endeavors to achieve the Joint United Nations Programme on HIV/AIDS 95-95-95 fast track targets established in 2014 for HIV prevention, progress has fallen short. Hence, it is imperative to identify factors that can serve as predictors of an adolescent's HIV status. This identification would enable the implementation of targeted screening interventions and the enhancement of healthcare services. Our primary objective was to identify these predictors to facilitate the improvement of HIV testing services for adolescents in Ethiopia.MethodsA study was conducted by utilizing eight different machine learning techniques to develop models using demographic and health data from 4,502 adolescent respondents. The dataset consisted of 31 variables and variable selection was done using different selection methods. To train and validate the models, the data was randomly split into 80% for training and validation, and 20% for testing. The algorithms were evaluated, and the one with the highest accuracy and mean f1 score was selected for further training using the most predictive variables.ResultsThe J48 decision tree algorithm has proven to be remarkably successful in accurately detecting HIV positivity, outperforming seven other algorithms with an impressive accuracy rate of 81.29% and a Receiver Operating Characteristic (ROC) curve of 86.3%. The algorithm owes its success to its remarkable capability to identify crucial predictor features, with the top five being age, knowledge of HIV testing locations, age at first sexual encounter, recent sexual activity, and exposure to family planning. Interestingly, the model's performance witnessed a significant improvement when utilizing only twenty variables as opposed to including all variables.ConclusionOur research findings indicate that the J48 decision tree algorithm, when combined with demographic and health-related data, is a highly effective tool for identifying potential predictors of HIV testing. This approach allows us to accurately predict which adolescents are at a high risk of infection, enabling the implementation of targeted screening strategies for early detection and intervention. To improve the testing status of adolescents in the country, we recommend considering demographic factors such as age, age at first sexual encounter, exposure to family planning, recent sexual activity, and other identified predictors.

Project description:Streptococcus pneumoniae is a human pathogen that is a major cause of infant mortality. Identifying the pneumococcal serotype is an important step in monitoring the impact of vaccines used to protect against disease. Genomic microarrays provide an effective method for molecular serotyping. Previously we developed an empirical Bayesian model for the classification of serotypes from a molecular serotyping array. With only few samples available, a model driven approach was the only option. In the meanwhile, several thousand samples have been made available to us, providing an opportunity to investigate serotype classification by machine learning methods, which could complement the Bayesian model.We compare the performance of the original Bayesian model with two machine learning algorithms: Gradient Boosting Machines and Random Forests. We present our results as an example of a generic strategy whereby a preliminary probabilistic model is complemented or replaced by a machine learning classifier once enough data are available. Despite the availability of thousands of serotyping arrays, a problem encountered when applying machine learning methods is the lack of training data containing mixtures of serotypes; due to the large number of possible combinations. Most of the available training data comprises samples with only a single serotype. To overcome the lack of training data we implemented an iterative analysis, creating artificial training data of serotype mixtures by combining raw data from single serotype arrays.With the enhanced training set the machine learning algorithms out perform the original Bayesian model. However, for serotypes currently lacking sufficient training data the best performing implementation was a combination of the results of the Bayesian Model and the Gradient Boosting Machine. As well as being an effective method for classifying biological data, machine learning can also be used as an efficient method for revealing subtle biological insights, which we illustrate with an example.

Dataset Information

Comparison of Use of Health Care Services and Spending for Unauthorized Immigrants vs Authorized Immigrants or US Citizens Using a Machine Learning Model.

Importance

Objective

Design, setting, and participants

Exposures

Main outcomes and measures

Results

Conclusions and relevance

Publications

Comparison of Use of Health Care Services and Spending for Unauthorized Immigrants vs Authorized Immigrants or US Citizens Using a Machine Learning Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets